Sustainability 13 07925

See discussions, stats, and author profiles for this publication at: https://www.researchgate.
net/publication/353279102
An Integrated Approach for Post-Disaster Flood Management Via the Use of

Cutting-Edge Technologies and UAVs: A Review
Article in Sustainability · July 2021

DOI: 10.3390/su13147925
CITATIONS READS
30 550
5 authors, including:
Steven Travis Waller Muhammad Jamaluddin Thaheem

Technische Universität Dresden Deakin University
386 PUBLICATIONS 8,054 CITATIONS 127 PUBLICATIONS 2,953 CITATIONS
SEE PROFILE SEE PROFILE
Asheem Shrestha
Deakin University
47 PUBLICATIONS 922 CITATIONS
SEE PROFILE
All content following this page was uploaded by Muhammad Jamaluddin Thaheem on 19 July 2021.
The user has requested enhancement of the downloaded file.

sustainability
Review
An Integrated Approach for Post-Disaster Flood Management
via the Use of Cutting-Edge Technologies and UAVs: A Review
Hafiz Suliman Munawar 1 , Ahmed W. A. Hammad 1 , S. Travis Waller 2 , Muhammad Jamaluddin Thaheem 3, *
and Asheem Shrestha 3
1 School of Built Environment, University of New South Wales, Kensington, Sydney, NSW 2052, Australia;
h.munawar@unsw.edu.au (H.S.M.); a.hammad@unsw.edu.au (A.W.A.H.)
2 School of Civil and Environmental Engineering, University of New South Wales, Kensington,
Sydney, NSW 2052, Australia; s.waller@unsw.edu.au
3 Geelong Waterfront Campus, School of Architecture and Built Environment, Locked Bag 20001,
Deakin University, Geelong, VIC 3220, Australia; asheem.shrestha@deakin.edu.au
* Correspondence: jamal.thaheem@deakin.edu.au
Abstract: Rapid advances that improve flood management have facilitated the disaster response by
providing first aid services, finding safe routes, maintaining communication and developing flood
maps. Different technologies such as image processing, satellite imagery, synthetic imagery and
integrated approaches have been extensively analysed in the literature for disaster operations. There
is a need to review cutting-edge technologies for flood management. This paper presents a review
of the latest advancements in the flood management domain based on image processing, artificial
intelligence and integrated approaches with a focus on post-disaster. It answers the following

research questions: (1) What are the latest developments in image processing for flood management
in a post-disaster scenario? (2) What are the latest techniques for flood management based on artificial
Citation: Munawar, H.S.; Hammad,
intelligence in a post-disaster scenario? (3) What are the existing gaps in the selected technologies
A.W.A.; Waller, S.T.; Thaheem, M.J.;
Shrestha, A. An Integrated Approach
for post-disaster? (4) How can the authorities improve the existing post-disaster management
for Post-Disaster Flood Management operation with cutting-edge technologies? A novel framework has been proposed to optimise flood
via the Use of Cutting-Edge management with the application of a holistic approach.
Technologies and UAVs: A Review.
Sustainability 2021, 13, 7925. https:// Keywords: natural disaster; early warning system; artificial intelligence; image processing
doi.org/10.3390/su13147925
Academic Editor: Chunjiang An

1. Introduction
Received: 23 May 2021
Climate change impacts have increased the events of natural disasters around the
Accepted: 7 July 2021
world. The impacts of these natural events, such as floods, drought, fire, cyclones, hur-
Published: 15 July 2021
ricanes and others, are profound on developing countries as well as on developed coun-
tries [1–3]. A lot of research has been carried out lately to build efficient early warning
Publisher’s Note: MDPI stays neutral
systems and improve disaster management ways. Natural events cannot be stopped from
with regard to jurisdictional claims in
being happening; however, effective disaster management approaches can minimise the
published maps and institutional affil-
iations.
destruction and reduce the number of casualties [4,5]. Different methods of disaster man-
agement are applicable at three stages of the event. First is the pre-disaster stage, which
emphasises monitoring or early warning system to alert the authorities about the incoming
natural event; second is damage control during the event, and third is the post-disaster
recovery phase to bring life back to normality [6–8]. To address the challenges of natural
Copyright: © 2021 by the authors.
events, the International Emergency Management System (IEMS) was established in 1993
Licensee MDPI, Basel, Switzerland.
to set up procedures and guidelines for countries to adapt during a crisis scenario. Accord-
This article is an open access article
ing to the Millenium Development Goals (MDG) 2015, the latest information technology
distributed under the terms and
conditions of the Creative Commons
and communication tools can be used for improving the relief response during a natural
Attribution (CC BY) license (https://
disaster [9–12]. The relief efforts can be accelerated to reach out to a maximum number of
creativecommons.org/licenses/by/ people in a short time with the use of advanced technology. Emerging technologies can,
4.0/).
Sustainability 2021, 13, 7925. https://doi.org/10.3390/su13147925 https://www.mdpi.com/journal/sustainability

Sustainability 2021, 13, 7925 2 of 22
therefore, play a vital role in developing disaster resilient infrastructure and attain effective
disaster management.
There is a knowledge gap in the field of the disaster management process. Special
focus needs to be laid on climate change and associated risks with the use of advanced
tools. Advanced early warning systems need to be developed based on the framework,
algorithms and concepts. Achieving disaster resilience is a major goal aimed by the UN to
achieve by 2030 [13–15]. Different countries around the world have prioritised to achieve
this target which can be achieved by tapping into human resources, developing cutting-
edge technologies and increasing adaptability through authorities. Resilience infrastructure
and capabilities should focus on reducing calamities and economic losses [16–18]. The
only way forward is to timely detect the hazard and minimise it with the application of
appropriate technology.
Innovative disaster management approaches that implement information technology,
artificial intelligence, ICT tools and machine learning will facilitate all stages of a disaster,
such as floods [19–21]. The innovation can take place either through different concepts,
ways, technology or community-based approaches. Interdisciplinary concepts and ideas
will develop different processes to carry out efficient pre- and post-flood management prac-
tices [22–24]. Collaborating with different stakeholders, integrating science and technology
and active participation from the community will facilitate the development of effective
tools and methodologies, their implementation and uptake at different levels. Japan, being
prone to disasters, experiences human casualties, damage to infrastructure and economic
losses each year [25]. Specialised emergency management systems have been devised to
mitigate hazards [26]. A multi-level system was established for assessing the capabilities
of emergency management from the top government level to the authorities below [27].
Similarly, in China, emergency management systems were developed after the spread of
SARS to cope with any disaster crisis through formulating different laws and applying
computational intelligence. A lot of research has been carried out in China to introduce
unconventional emergency plans and practices that involve developing new rules, taking
into consideration various constraints and contradictory issues. It involves challenging
intelligent data estimations and making supportive decisions [28,29].
The decision-making process is essential in each phase of disaster management, as
it impacts the effectiveness of the rescue mission and events [30–32]. This decision mak-
ing is reliant on big data analysis, which is challenging as compared to traditional data
analysis. This highlights the need for computational intelligence, real-time algorithms that
can make timely decisions, analyse the different structures of data, extract the data and
present it through visualisation strategies [33–36]. In most flood management systems, the
application of computational intelligence is viral for making timely decisions. There is a
lot of traction on the applicability of the computationally intelligent technique for flood
management systems. There is a need to review the latest computational technology and
identify existing gaps in flood management [37]. A recent development in computational
technologies is applying artificial intelligence and machine learning algorithms for weather
predictions, flood-affected regions, damage detection and others [38]. Researchers are also
investigating various algorithms for analysing large scale data sets that would solve the
real-time issues with minimum computational time. Robust risk-related data analysis,
enhancing computational potential and applying different sensors within drones and satel-
lites for capturing real-time data analysis are a few of the many domains that researchers
are investigating [38–41]. These include observing disaster areas by employing drones and
analysing real-time data for mapping the area and finding the safest route to reach the
victims during floods.
The information systems can be improved for meteorological purposes by applying
remote sensors and drones, enabling planning for disaster events [42]. Such information
about the oncoming flood will enable the authorities to use diversion strategies or plan
routes for evacuating the area before the region is hit by the flood [39]. These resilient
measures are only possible with the help of innovative technologies and carrying out further
development in this field. It is estimated that weather forecasting and meteorological data
analysis will be highly reliant on artificial and computational intelligence in the future.
The authorities will utilise these technologies for communicating disaster predictions, the
extent of risks, creating awareness among the community to take safety precautions and
devising strategies [43].
Systematic background research will be carried out to identify the latest technologies
that have been used in this domain for accurately determining a natural disaster: floods.
The paper will classify technologies based on image processing techniques, artificial intelli-
gence and integrative approaches for capturing the data and analysing it. Techniques will
be evaluated based on their importance, performance, application and limitations and their
potential acceptance by the authorities as management systems and decision-making based
on real-time data. This review will improve the understanding of the latest technology and
select a suitable model for flood management in a specific area. The following research
questions are formulated and will be answered based on this review:
RQ-1. What are the latest developments in image processing for flood management in a
post-disaster scenario?
RQ-2. What are the latest techniques for flood management based on artificial intelligence
in a post-disaster scenario?
RQ-3. What are the existing gaps in the selected technologies for post-disaster?
RQ-4. How can the authorities improve the existing post-disaster management operation
with cutting-edge technologies?
The rest of the paper is organised as follows: Section 2 defines the methods and
materials carried out during this study, while Section 3 presents the results of the study
by providing a comprehensive analysis of the selected cutting-edge flood management
techniques. Section 4 discusses the results of this research, identifies the research gaps and
presents a solution to overcome them. Section 5 outlines the conclusion of the study.
2. Materials and Methods

The aim was to assess the development in this field and how these advanced tools are
facilitating post-disaster scenarios. To achieve the desired goals, top journals were searched
for recent and significant work carried out in the domain. The review process was carried
out in two phases, i.e., retrieving articles and screening them.
To retrieve the research articles for this study, the chosen search engines were Scopus,
Google Scholar, Science Direct, Elsevier and Springer for finding the latest developments
and interdisciplinary research in the field. The next step was to formulate a set of queries
to be used in each of these search engines to retrieve the articles. The major aim was to
fully exhaust the search database and retrieve a maximum number of articles matching
our domain of interest. We used three categories of terms representing the subdomains to
extract a variety of research articles. After entering the search queries, a set of articles ranked
based on their relevance were retrieved. The first category of phrases was formulated to
retrieve articles that proposed flood prediction models using image processing technologies
that utilised multispectral sensors. The phrases were formed by using keywords related to
flood prediction, which includes “flood prediction”, “flood risk analysis” and “flood hazard
mapping”, along with phrases such as “image processing” and “artificial intelligence”. The
second category of terms was formulated to retrieve articles that proposed flood prediction
methods using these technologies. For this purpose, we used flood prediction keywords
along with the keywords “edge detection”, “mining patterns from images”, “Synthetic
Aperture Radar” and “Image-based flood Alarm model”. The number of articles retrieved
from each category of search keywords is shown in Figure 1.
Sustainability 2021, 13, x FOR PEER REVIEW 4 of 22
Figure 1. The detailed screening process of the latest articles for flood management.
Figure 1. The detailed screening process of the latest articles for flood management.
After the first phase based on article retrieval, the articles were passed through a
screening the
After firsttophase
phase based
further on down
narrow article the
retrieval, thecriteria.
selection articles Four
were assessment
passed through a
criteria
screening phase to further narrow
were defined to evaluate the articles: down the selection criteria. Four assessment criteria
were defined to evaluate the articles:
1. No Duplicates
1.2. No Duplicates
Time Interval: 2010–2021
2.3. Time Interval:
Document 2010–2021
Type: research article, abstract, book chapter
3.4. Document Type: research
English language only article, abstract, book chapter
4. English language only
Thus, by filtering the articles based on these metrics, the most recent, applicable and
Thus,
unique by filtering
research thewritten
articles articles inbased on theselanguage
the English metrics, the
were most recent, applicable
extracted. From the 1250and
unique
articlesresearch
retrievedarticles
in the written in the
first phase, 94English
articles language
passed allwere
four extracted. From theHence,
selection criteria. 1250
articles retrieved
this review in theon
is based first phase,
these 94 articles
screened passed
articles. Theallnumber
four selection criteria.
of articles fromHence, this
each term
review is based
category, on these
i.e., image screenedartificial
processing, articles. intelligence
The numberand of articles
integratedfromapproach
each termthat category,
passed
i.e.,
the image
screening processing, artificialin intelligence
phase, is shown Figure 1. Theand integrated
articles approach
were screened forthat passed non-
duplicates, the
screening phase, and
English articles is shown
review in papers.
Figure 1.Around
The articles were screened
520 papers were removedfor duplicates, non-Eng-
for duplicates, 240
for articles
lish non-English articlespapers.
and review and 396Around
for review520 papers. Hence,
papers were overall,for
removed 94 papers were240
duplicates, finally
for
collected as articles
non-English an output andof396thefor
screening phase. Hence, overall, 94 papers were finally col-
review papers.
lectedFigure 2 shows
as an output of the screening
year-wise phase.
distribution of articles retrieved from each category.
It shows
Figurea 2significant
shows theincrease
year-wise in distribution
the use of image processing
of articles retrievedandfromartificial
each intelligence-
category. It
based techniques for flood management as compared to integrated
shows a significant increase in the use of image processing and artificial intelligence-basedapproaches in the past
decade. On
techniques forthe other
flood hand, a comparatively
management as comparedsmaller number
to integrated of articlesinfocused
approaches the pastondec-the
use On
ade. of image
the otherprocessing
hand, aand artificial intelligence
comparatively for flood
smaller number ofmanagement
articles focused in aonpost-disaster
the use of
scenario.
image An evenand
processing smaller number
artificial of papers
intelligence forfocused on holistic approaches
flood management for disaster
in a post-disaster sce-
management. The search was extended to include reports, magazine
nario. An even smaller number of papers focused on holistic approaches for disaster man- articles and web
pages from authentic websites, thus increasing the scope and
agement. The search was extended to include reports, magazine articles and web pages collecting a wide range of
articles based on the subject matter. All the articles published before
from authentic websites, thus increasing the scope and collecting a wide range of articles 1 January 2010 were
discarded.
based on theThis was to
subject include
matter. Allthethemost recent
articles technologies
published beforein 1the review.2010
January Onewere
exception
dis-
to this rule
carded. Thiswas waskeeping
to includesome theearlier
most papers that introduced
recent technologies basic
in the concepts
review. One and definitions
exception to
related to the technologies discussed in this study.
ability 2021, 13, x FOR PEER REVIEW 5 of 22

this rule was keeping some earlier papers that introduced basic concepts and definitions
related to the technologies discussed in this study.
Figure 2. Yearly
Figuredistribution of the papers
2. Yearly distribution published
of the in the selected
papers published domains.
in the selected domains.
3. Results
3. Results
RQ-1. What are the
RQ-1. latest
What aredevelopments in image processing
the latest developments for flood for
in image processing management
flood management in the
in the post-disaster scenario?
post-disaster scenario?
3.1. Image Processing

3.1. Image Processing
3.1.1. Edge Detection
3.1.1. Edge Detection
Edge detectionEdge detection
techniques havetechniques havetobeen
been applied appliedwater
measuring to measuring water
levels. The levels. The major
major
steps involve
steps involve selecting selecting
a Region a Region
of Interest of Interest
(ROI), applying (ROI), applying pre-processing
pre-processing methods and methods and
then performing then performing
edge detection toedge detection
finally compute to an
finally computevalue
approximate an approximate
of the water value
sur- of the water
face levels of a surface levels[44–46].
water body of a water body
These [44–46].
steps These steps
are discussed are discussed below:
below:
A. Region of A. Region
Interest: of Interest:
the Region the Region
of Interest (ROI)oftechnique
Interest (ROI)
is usedtechnique is useda for
for extracting seg-extracting a seg-
ment of an image where several operations need
ment of an image where several operations need to be performed. In simple words, to be performed. In simple words, it
is similar to cropping an image to a reduced form.
it is similar to cropping an image to a reduced form. ROI helps in removing noise ROI helps in removing noise (the
unwanted image) so that the process runs smoothly
(the unwanted image) so that the process runs smoothly and effectively. Figure 3a and effectively. Figure 3a shows
an input
shows an input image, image,
Figure 3bFigure
shows 3b theshows the highlighted
highlighted ROI and ROI and3cFigure
Figure demon- 3c demonstrates
the extraction
strates the extraction of ROI from of ROI
the from
imagethe image [47].
[47].
B. BrightnessB.and Contrast:
Brightnessitand is a Contrast:
basic methodit is aaffecting
basic method affecting
the quality the quality
of images. Thisof images. This
method makes the image bright. Brightness is directly proportional to the number of to the number
method makes the image bright. Brightness is directly proportional
pixels in x and yof pixels in xand
coordinates andthey coordinates
constant á of and
thethe constant
image. á of the
A positive image.
value makesA positive value
makes the image brighter and vice versa. Figure 3d
the image brighter and vice versa. Figure 3d shows the noise-filtered image and Figure shows the noise-filtered image
and Figure 3e shows the
3e shows the output image with increased brightness.output image with increased brightness.
C. Grayscale C. Grayscale the
and Threshold: andgreyscale
Threshold: the greyscale
image only holdsimage only holds
the intensity the intensity information.
information.
The image is black and white textured, with
The image is black and white textured, with black being the weakest intensity black being the weakest
and intensity and
white colour depicting a strong intensity range.
white colour depicting a strong intensity range. Threshold, on the other hand, is Threshold, on thea other hand, is
a point that converts a grayscale image into a binary image. Figure 3f illustrates a
point that converts a grayscale image into a binary image. Figure 3f illustrates a gray-
grayscale image, while Figure 3g shows a binary (black and white) image.
scale image, while Figure 3g shows a binary (black and white) image.
D. Edge Detection: this algorithm helps to find out the edge points on the water surface
and the point of the dam’s height. The algorithm was found helpful in determining
the edge of the water. The output consists of a segmented image separating the water

D. Edge Detection: this algorithm helps to find out the edge points on the water surface
and the point of the dam’s height. The algorithm was found helpful in determining
the edge of the water. The output consists of a segmented image separating the water
areafrom
area fromthe
therest
restofof the
the image.
image. TheThe system
system calculates
calculates the the existing
existing water
water surface
surface level
level by comparing the edge pixel coordinate. If the water level increases, the pixel
by comparing the edge pixel coordinate. If the water level increases, the pixel coor-
coordinates drops resulting in altered segmentation. The system should be calibrated
dinates drops resulting in altered segmentation. The system should be calibrated
properly for accurate estimation of results [48]. A warning system can be established
properly for accurate estimation of results [48]. A warning system can be established
by using this method. The water surface level of any region can be calculated by
by using this method. The water surface level of any region can be calculated by pro-
processing the captured image. Moreover, the image can be spread on social media
cessing the captured image. Moreover, the image can be spread on social media as a
as a piece of evidence for alerting people of the upcoming disaster. Figure 3a–h
piece of evidence for alerting people of the upcoming disaster. Figure 3a–h shows the
shows the edge detection results on the test image.
edge detection results on the test image.
Figure Input image

Figure 3.3. (a) Input image (b)
(b) ROI
ROI(c)
(c)extracted
extractedROI
ROI(d)
(d)filtered
filteredimage
image(e)(e)enhanced
enhanced brightness
brightness (f)
grayscale
(f) grayscaleimage (g)(g)
image binary image
binary image(h)(h)
edge detection
edge results.
detection results.
Detection
Detection of significant landmarks
landmarksfromfromimages
imagesisisanother
another method
method being
being usedused to
to an-
analyse various features from the images to determine whether
alyse various features from the images to determine whether a region a region is flooded or not.
not.
Researchers
Researchersarearefocusing
focusingononextracting
extractinglandmarks
landmarkspresent
presentononthe
theground,
ground,such
suchas as bridges,
bridges,
roads,
roads,houses
housesandandbuildings
buildings[48–51].
[48–51].These
Thesefeatures
featurescan
canbebefurther
furtherprocessed
processedusing
usingimage
image
processing techniques to aid in disaster response. For example, houses and
processing techniques to aid in disaster response. For example, houses and buildings canbuildings
can be identified
be identified to locate
to locate stranded
stranded people.
people. Roads
Roads andand bridges
bridges can can be used
be used to identify
to identify the
the routes available in a certain area, which can assist in reaching and evacuating people.
These features can also be processed separately for damage assessment due to a disaster
routes available in a certain area, which can assist in reaching and evacuating people.
These features can also be processed separately for damage assessment due to a disaster
and to verify the occurrence of disaster in the region. Munawar et al. [51] used isotropic
and to verify the occurrence of disaster in the region. Munawar et al. [51] used isotropic
surround suppression and Hough transforms for target recognition from aerial images and
surround suppression and Hough transforms for target recognition from aerial images
performed rule-based verification of strategic targets detected from these images. Recently,
and
edgeperformed
detection rule-based
techniques verification of strategic
on multispectral targets to
aerial images detected from these
mine strategic images.
bridge Re-
locations
cently, edge detection techniques on multispectral aerial images to mine strategic
to provide aid in disaster relief missions have been applied [51–53]. Table 1 summarises bridge
locations to provide using
the methodologies aid in edge
disaster relief missions
detection have
for various beenmanagement
flood applied [51–53]. Table 1 sum-
processes.
marises the methodologies using edge detection for various flood management processes.
Table 1. Edge-detection-based techniques for flood management.
Table 1. Edge-detection-based techniques for flood management.
Imaging
Method Features
Features Imaging Device Resources
Resources Results
Results Limitations
Limitations Authors
Authors
Device
Target recogni-
Image
Image segmentation Target
tion ofrecognition
linear- Unmanned Aer- Application to ob-
Unmanned Application to
segmentation of linear-shaped Computational time =
Computational
using canny edge shaped land- ial Aerial
VehicleVehicle
Optical imagery
Optical imagery jects of a single
objects of a [54]
[54]
using canny landmarks: bridges time = 0.8913
0.8913 s s
detection marks: bridges (UAV)(UAV) single category
category
edge detection and runways
and runways
Mining patterns
Mining Bridgeand
patterns Bridge androad
road Multispectral Accuracy
Accuracy = 95%,
UAV Multispectral aerial = 95%, [29]
from images Detection UAV aerial images comp time = 0.8 s [29]
from images Detection images comp time = 0.8 s
3.1.2.
3.1.2.Image-Based
Image-BasedFlood FloodAlarm
AlarmModel
Model(IFAM)
(IFAM)
IFAM
IFAM is a flood alert system. The systemutilises
is a flood alert system. The system utilisesimages
imagesforformonitoring
monitoringrising
risingwater
water
levels
levels in real-time. The IFAM receives videos through digital camera sensors. Thesensors
in real-time. The IFAM receives videos through digital camera sensors. The sensors
are
areinstalled
installedaround
aroundrivers.
rivers.The
Thevideos
videosare
areprocessed
processedininJPEG
JPEGimages.
images.Image
Imageenhancement
enhancement
isiscompleted.
completed.The Theflood
floodrisks
risksare
arethen
thencalculated
calculatedby bydevising
devisingmodules
modulesthat
thatestimate
estimatethe
the
water
waterlevel
level[28].
[28].Figure
Figure44shows
showsthe
theschematic
schematicdiagram
diagramof ofan
anIFAM.
IFAM.
Schematicdiagram
Figure4.4.Schematic
Figure diagramofofaaflood-alert
flood-alertmonitoring
monitoringsystem.
system.
IFAMutilises
IFAM utilisesthe
theimage
image segmentation
segmentation technique
technique to remove
to remove noise
noise and and unwanted
unwanted ob-
objects. The image segmentation follows several algorithms, such as point-based segmen-
jects. The image segmentation follows several algorithms, such as point-based segmenta-
tation,
tion, edge-based
edge-based segmentation,
segmentation, region-based
region-based segmentation
segmentation and hybrid
and hybrid segmentation.
segmentation. The
The outside sources are likely to affect the image segmentation techniques [55,56]. These
outside sources are likely to affect the image segmentation techniques [55,56]. These in-
include reflection, humidity, bad environment, smoke, storm and other sources. If the
clude reflection, humidity, bad environment, smoke, storm and other sources. If the out-
outdoor environment changes, the technique would be unable to detect the flooded area
door environment changes, the technique would be unable to detect the flooded area and
and the correct boundaries of the area will not be identified [57]. Therefore, image segmen-
the correct boundaries of the area will not be identified [57]. Therefore, image segmenta-
tation should be coupled with flood-risk classifiers for lowering the risk level. After the
tion should be coupled with flood-risk classifiers for lowering the risk level. After the
image processing module, a risk detection module is generated, which informs the relevant
organisation of upcoming risks [28].
During the first module of image processing, the images received from sensors are
processed by converting the colour space from the Red–Green–Blue (RGB) domain to the
Hue–Saturation-Value (HSV) domain [58]. The HSV colours are relevant to the Cartesian
coordinate system. Histogram equalisation is applied to equalise the image colours of
water and surrounded areas such as forests or land by increasing the contrast level [59].
Different parts of an image are classified into components such as buildings, rivers and
other surrounding things [55]. A Region Growing (RegGro) algorithm is then applied,
which is used for segmentation and creating a binary mask. A binary mask outlines the
areas of water. The second module consisted of an alarm system that generates an alarm
when a flood is detected. Thus, the system performs real-time flood water monitoring
based on IFAM sensors installed near water bodies.
After the acquisition of images from satellite sources, the information is collected in
different data sets. Data processing tools then help in processing the information, followed
by database development [60]. A comparative analysis of information is carried out, which
produces a draft of damage estimation accompanied by flood monitoring.
3.1.3. Post-Disaster Assessment Using UAV

Ezequiel et al. [61] proposed UAV-based aerial imagery for post-disaster assessment
and monitoring of infrastructure. Collaborative research was conducted for data acquisi-
tion, path planning and processing of UAV based aerial imagery. This assists in gaining
background information for making the right decisions. In the Philippines, after Typhoon
Haiyan, damage estimation was carried out using initial aerial imagery. UAV-based aerial
imagery assisted in relocation and rehabilitation efforts within the region. Besides damage
assessment of building and infrastructure, damage to the agriculture industry was also
estimated with aerial imagery and ground survey. The damage to crops was identified
using aerial imagery based on normal RGB and multispectral cameras. Vegetation indices
were calculated using the image processing technique, while ground-based knowledge
was gathered from the field experts. An accurate estimate of damage facilitated making a
decision for recovery assistance from the Government and implementing recovery plans.
Table 2 summarises the latest developments in the field of image processing for flood
management.
Table 2. Comparison of image processing methods for flood management.
Technique Method Imaging Device Outcome Limitation Authors

Application of ROI,
pre-processing and edge Imprecise results for
detection algorithm to Webcam Accuracy = 96% low contrast regions in [51]
estimate water levels on the images
surface of a water body
Edge Detection
Landmark detection using Results highly depend
Unmanned Aerial Detection of
image segmentation and on image [54]
Vehicle (UAV) bridges in 0.8913 s
canny edge detection segmentation results
Detection of bridges and
roads by mining patterns UAV Accuracy = 95% - [29]
from multispectral images
Use of sensors to capture
images from water bodies,
Detection of Environmental factors
conversion from RGB to HSV,
changes in the flow such as reflection,
application of histogram Digital camera
IFAM of water and humidity, smoke and [28]
equalisation and finally a sensors
real-time flood risk storm affect the system
RegGro algorithm for
assessment performance
measurement of the water
levels
One of the basic post-disaster assessments involves the estimation of the area and
volume of the flood. Several studies have applied remote sensing for computing the
volume and volumetric changes of the forest areas, as a ground-based survey of patch
forest is difficult to conduct [62–65]. For example, Esteban et al. [62] estimate the changes
in the volume and biomass of the forest cover using remote sensing data. Two regional
study areas, i.e., Spain and Norway, were selected for the study. Random Forest algorithm
was used to predict forest volume or above-ground biomass using remote sensing data.
Similarly, different methods such as UAV-based monitoring, tracer test analysis, UAS
photogrammetry, ArcGIS, etc., have been applied for estimating flood induced changes,
volumetric and topographic changes [66–69]. Akay et al. [66] conducted a two-year study
on the Buyuk Menderes river basin, Turkey, to quantify and visualise flood-induced mor-
phological changes through UAV surveys. To evaluate the change in river morphology,
multi-temporal orthomosaics and digital surface models (DSMs) were constructed using
the Structure from Motion (SfM) technique. Diachronic spatial and volumetric changes in
the meander structures were assessed by the Digital Shoreline Analysis System (DSAS)
and Digital Elevation Model (DEM) of Difference (DoD) tools. Aerial and volumetric
changes of the river bank were achieved using the SfM photogrammetry technique through
UAV-derived imagery. Hence, the processing time of the technique is important to consider
when applying for the flood monitoring system. Additionally, the accuracy of the image
processing technique for predicting the flood area needs to be evaluated. The compari-
son of the techniques and the one with the best performance need to be considered for
implementation in the system for the monitoring. Even though image processing has been
extensively used for flood detection and finding safe routes in the affected region, the
technique used independently has found to be less accurate due to various factors that
limit its higher uptake. These factors are mainly environmental pollution, clouds, contrast
and brightness that reduces the quality of the images. Besides these factors, it is difficult to
obtain consistent results with a different set of images. To overcome these issues, machine
learning algorithms can be applied to improve datasets, train the models and achieve
higher accuracy and prediction.
RQ-2. What is the latest techniques for flood management based on artificial intelligence
in a post-disaster scenario?
3.2. Artificial Intelligence (AI)

AI methods are frequently being used to deal with several flood-related problems.
These include flood prediction, flood hazard analysis, flood detection, mapping flood-prone
regions and assessing the damage of infrastructure components after the flood. Table 3
summarises the most recent techniques based on AI for flood management. Each of these
methods has been discussed in detail in this section [67].
A tool referred to as the Qatar Computing Research Institute (QCRI) was developed
in Qatar for managing disasters. It was created by the Qatar Foundation to educate and
make people more aware of responding to disasters and emergencies. QCRI aims to
facilitate volunteer workers and disaster management authorities. This tool has a built-in
AI component that detects disaster-related tweets and text from any given data. It then
formulates an instant solution to recover from the calamity [68].
1Concern is another AI-based tool for disaster management. During a flood-related
emergency, this tool forms a rich image of the scenario. Emergency management organ-
isations use this image to further examine and probe the situation [69]. Based on their
analysis, these centres immediately provide relief items to the disaster victims and initiate
rescue operations. The tool has a planning module that maps disaster-prone regions. After
identifying these regions, people can be immediately evacuated to save their lives. Hence,
this software provides pre-disaster disaster risk assessment as well as aids post-disaster
response. This tool has been implemented in up to 163,696 square miles region and has
saved 39 million people [67,68]. It has also been used to examine 11 million infrastructure
components in disaster-hit areas.
BlueLine Grid is another disaster management tool that has been created by a police
commissioner in the USA. To provide aid in rescue operations after a disaster, this tool
works as a portable communication platform [64]. It also maintains a connection between
relief workers, police and security squads by connecting them in one network. This network
allows the communication of data in sound and text formats and provides location and
group services. The location services allow users to locate people and rescue workers in
nearby areas. Hence, this tool provides instant response to disasters and emergencies [68].
In India, AI-based systems are evolving. A tool using Google Maps and Google Search
has been developed by Google for flood forecasting and warning. Rainfall and past flood
data are used to train the AI model [69]. This system simulates floods based on the acquired
weather and rainfall data. It has also been used to forecast floods in urban areas. Research
conducted at the University of Dundee, United Kingdom, used this tool to determine the
urban flooding rate using crowd-sourced data collected from social media platforms [18].
Recently, more work is being directed towards applying AI and machine learning
technologies for disaster management. Chen et al. [14] applied machine learning along
with the Random Forest method for risk evaluation of floods. The main flood prediction
methods are Random Forest, Decision Trees (DT) and Lazy method. The training data
consists of Big data collected from the weather data from past flood events. A Flood Data
Aggregation Tool (FDAT) is developed using MATLAB to extract features to be used for
training. The main aim is to enable the AI models to learn from the previous flood incidents,
identify the flood behaviours and understand patterns in the data to predict future flood
incidents. This would help in preventing the destruction, reducing fatalities and building
resilience against such disasters.
Chapi et al. proposed a hybrid approach to generate flood susceptibility maps. The
model is called “Bagging LMT” as it combines bagging ensemble with a logistic model tree
(LMT) [24]. The target region was Haraz, Northern Iran. Images from this region were
used to build the image dataset. Eleven flood-conditioning factors were included in the
dataset. These factors were shortlisted by using an information gain ratio method along
with average merit (AM) calculation. Results were compared with the LMT model, logistic
regression, Random Forest and Bayesian logistic regression to prove that it outperformed
these models in performance. The system achieved an overall accuracy and precision of
95.5%, making it highly effective and reliable for flood susceptibility assessment.
In the literature, the researchers have attempted to overcome the performance limita-
tions of various existing machine learning models by incorporating statistical methods into
them. This approach is used by Tehrany, Pradhan [16], who developed an ensemble model
using frequency ratio (FR) along with SVM. A spatial model for flood prediction was built
using this method [16]. Several conditioning factors were identified, and a numerical value
was estimated using the proposed algorithm that represented the dependency between the
incidence of flood and these conditioning factors. FR is calculated for each conditioning
factor, and after that, the normalised values of weights within the range [0,1] were obtained
by applying the given formula:
ym − ymin
Ym = (1)
ymax − ymin
In Equation (1), Ym denotes the normalised values of ym . The minimum value of yj is

represented by ymin , and the maximum value is denoted by ymax . The conditioning factors
are allocated the weights determined by this method. The resultant conditioning factors are
applied to an SVM-based method to determine the link between each of the conditioning
factors and the occurrence of a flood.
ANN is among the most widely used machine learning models to forecast disasters
with good performance. There are three main layers in an ANN model, which are referred
to as input, hidden and output layers. Only one or two hidden layers are present in a
typical ANN. Liu et al. [70] combined Stacked Autoencoders and Back Propagation Neural
Network (SAE-BPNN) to develop a flood prediction model. An autoencoder extracts
ANN is among the most widely used machine learning models to forecast disasters
with good performance. There are three main layers in an ANN model, which are referred
Sustainability 2021, 13, 7925 to as input, hidden and output layers. Only one or two hidden layers are present 11 ofin22a
typical ANN. Liu et al. [70] combined Stacked Autoencoders and Back Propagation Neu-
ral Network (SAE-BPNN) to develop a flood prediction model. An autoencoder extracts
non-linear features from input image data using unsupervised learning [70]. A stacked
non-linear
autoencoder features
has many from inputofimage
layers data using unsupervised
thin autoencoders forming a neural learning
network. [70].Each
A stacked
layer’s
autoencoder has many layers of thin autoencoders forming
output is applied to the subsequent layer as input. The model used multiple SAE-BP a neural network. Each layer’s
mod-
output
ules. The is applied to the subsequent
data is classified into several layer as input.
groups usingThe modelclustering.
k-means used multiple EachSAE-BP
SAE-BP
modules.
module would The data is classified
simulate into several groups
its corresponding using The
data class. k-means
resultsclustering.
demonstrated Each SAE-BP
by this
module would simulate its corresponding data class. The
model surpassed the performance of all benchmarks chosen for the study. Let yi ((m)) results demonstrated by
((m)) bethis
the
model surpassed
activation function theofperformance
the ith unit inoflayer all benchmarks
m. The output chosen
〖x〗for the study. Let yi
mi of this unit is applied
beas
the activation function of the ith unit in layer m. The output [x] i of this unit is applied as
input to the next. The weights connecting units in various autoencoder layers are denoted m
input to the next. The weights connecting units in various autoencoder layers are denoted
by W. The mathematical function specifying encoding for autoencoder is:
by W. The mathematical function specifying encoding for autoencoder is:
𝒚(𝒎) = 𝒇(𝒙(𝒎) ) (2)
(m)
y = f ( x(m) ) (2)
Multiple conditioning factors causing floods can be used to identify flood-prone ar-
eas. Multiple
Tehrany,conditioning
Pradhan [16]factors used causing
a set of floods
these factors
can be usedfor flood susceptibility
to identify flood-prone mapping.
areas.
Their model used the weights of evidence (WoE) method
Tehrany, Pradhan [16] used a set of these factors for flood susceptibility mapping. to find the impact of each con-
Their
ditioning factor on the flood incidents along with a bivariate
model used the weights of evidence (WoE) method to find the impact of each conditioning statistical analysis (BSA)
technique
factor on the [16].
floodThe positivealong
incidents and negative weightsstatistical
with a bivariate are calculated
analysis to (BSA)
find the WoE values
technique [16].
using
The the following
positive and negative formulas:weights are calculated to find the WoE values using the following
formulas: 𝑷{𝑩|𝑨}
𝒘𝒋 = 𝐥𝐧 P{B|A} (3)
wj+ = ln 𝑷{𝑩|𝑨} (3)
P{B|A}
In Equations
In Equations (2) (2) and
and(3), (3),lnlndenotes
denotes thethe
natural
naturallog,log,
whereas
whereas P is Ptheisprobability
the probabilityfunc-
tion. The variables B, B ̅
, A and A ̅ represent the absence
function. The variables B, B− , A and A− represent the absence and presence of the and presence of the conditioning
factors. The conditioning
conditioning factors. Thefactors are again
conditioning classified
factors are using
again the acquired
classified weights.
using Then, an
the acquired
SVM model was used to find the relationship between each
weights. Then, an SVM model was used to find the relationship between each conditioning conditioning factor and the
occurrence of a flood. Results demonstrated improved
factor and the occurrence of a flood. Results demonstrated improved performance overperformance over independent us-
age of BSA and SVM.
independent usage of BSA and SVM.
Statistical methods
Statistical methods have have beenbeen employed
employed frequently
frequently in in the
theliterature
literatureto toimprove
improvethe the
performanceof
performance ofmachine
machinelearning learningmodels.
models.Shafizadeh-Moghadam
Shafizadeh-Moghadametetal. al.[30]
[30]experimented
experimented
witheight
with eightmachine
machinelearning
learning and and statistical
statistical methods
methods for for flood
flood prediction
prediction [30]. [30]. They
They pro-pro-
posed seven new ensemble models by analysing the individual
posed seven new ensemble models by analysing the individual working of these methods. working of these methods.
Amongthe
Among themachine
machinelearning
learningmodels, models,Boosted
BoostedRegression
RegressionTrees Trees(BRT)
(BRT)demonstrated
demonstratedthe the
highest performance when independently used, with
highest performance when independently used, with an Area Under Curve (AUC) equal an Area Under Curve (AUC) equal
to0.975.
to 0.975. Among
Among ensemble
ensemble techniques,
techniques, the the Emmedian
Emmedian method method showed
showed the the highest
highest perfor-
perfor-
mancewith
mance withAUCAUC== 0.976.
0.976. ThisThis method
method calculated
calculated the the median
medianvalues
valuesof of probabilities
probabilitiesacross across
thepredictions.
the predictions.
Figure55shows
Figure showsthe thefloodfloodmapping
mappingresults resultson onan aninput
inputmultispectral
multispectralaerial aerialimage.
image.The The
system classifies the flooded (Red) and non-flooded (Blue)
system classifies the flooded (Red) and non-flooded (Blue) regions and highlights them regions and highlights them
using different
using different colours in in the
the output
outputso sothat
thatthe
therescue
rescue workers
workers can easily
can easily distinguish
distinguish be-
tween them.
between them.
Figure 5. Flood mapping results (a) Input RGB aerial image (b) Flooded regions (Red), Non-flooded
regions (Blue).
Table 3 shows the comparison results of the most recent, state of the art flood man-
agement and detection models that used AI. The current research shows a wide range of
articles focusing on the standard AI and machine learning techniques such as Random
Forest, Bayesian Linear Model, ANN, Decision Trees and SVM [71]. Most techniques
focused on ensemble and hybrid approaches, which are known to boost performance
outcomes. Integrating results of multiple independent classifiers form an ensemble model,
while a hybrid model uses two or more classifiers to produce an output. A rising trend
has been in the use of statistical analysis along with machine learning. Statistical methods
such as FR and BSA have been incorporated with machine learning models such as SVM,
demonstrating a noticeable improvement in results. Other statistical methods such as EM-
mean and EMmedian have been observed in the literature for solving the flood prediction
problem, demonstrating results at par or better than the standard machine learning or AI
techniques [72].
Table 3. Comparison of AI techniques for flood management.
Tool/Tech Method Study Area Outcome Limitation Reference

A tool to filter and classify Process thousands Does not reflect on
QCRI social media messages Qatar of messages per disaster mitigation [18]
related to disaster minute strategies
Predicts the way a
disaster would
Machine learning impact an area on Some reports of
prediction algorithms, building to inaccurate predictions
1Concern - [18]
trained on data collected building basis needed to enhance
from various cities Accuracy = 85% training data
Time = Upto
15 min
Locates nearby
Relies on a wireless
Use of Promontory for New York, help sources and
Blueline Grid connection which may [18]
emergency response USA aids
fail during a disaster
communication
Successful
recognition of
Flood warning
urban flooding Not yet integrated by
systems integrated AI model trained using
India from Google for mainstream [18]
into Google Search rainfall and climate data
crowdsourced use
and Google Maps
images retrieved
from social media
Highest accuracy
Trained Random Forest, Results highly
(80%) achieved
AI and machine DT J48, Lazy methods dependent on the
UK through the [19]
learning models using big data for flood quality of data and
Random Forest
prediction input parameters
algorithm
Bagging ensemble and
The depth of water in
logistic model tree (LMT)
Bagging LMT - Accuracy = 95.5% a flooded region [24]
integrated to map flood
cannot be estimated
risks
Needs careful selection
FR-based calculation of
of conditioning factors
weights for conditioning Kelantan, Best accuracy for
FR-SVM to obtain the most [16]
factors; use of SVM for Malaysia kernel width = 0.1
discriminative features
flood forecasts
to map floods
SAE combined with
BPNN. K-means Imbalance in data
SAE-BPNN - DC = 0.88 [66]
clustering used to distribution problem
improve the results
Weights calculated using
Success rate = A high prediction rate
BSA method for the
96.48% indicates a likelihood
BSA-SVM conditioning factors; use Malaysia [16]
Prediction rate = of having false
of SVM for flood
95.67% predictions
prediction
Table 3. Cont.
Tool/Tech Method Study Area Outcome Limitation Reference

The highest
8 machine learning performance
Machine learning
models and 7 ensembles achieved using the Accuracy affected by a
and statistical Haraz, Iran [50]
of machine learning and ensemble model change in input data
approaches
statistical methods Emmedian with
AUC = 0.976
ANN, decision forest, Bayesian Linear
Several standard Incomplete data and
Bayesian linear model, Pattani Basin, model
machine learning unknown variables [31]
boosted decision tree and Thailand demonstrated the
models used in experiments
linear regression model best performance
The researchers have used various metrics to assess the performance of their tech-
niques; the most frequent one is the accuracy, which is simply the percentage of correct
detections. Other measures include AUC, success rate and Deterministic coefficient (DC).
Most of the techniques have limitations arising from the data-based restrictions [73]. The
models using conditional factors needed to select these factors from a large pool of flood
data. This required careful feature selection and extraction, as the most influential factors,
which are contributing the most to the occurrence of floods, needed to be selected. Other
data-related problems include an imbalance in data distribution, the presence of unidenti-
fied variables in data and ambiguity in selecting parameters for the system. Hence, most
models are found to be highly dependent on the input parameters and data either to be
used in training, testing or just analysis and the major concerns of researchers about their
proposed system were most frequently related to the input data. One possible way to solve
this issue is to use deep learning methods, which have an inherent ability to cope with
unstructured data and perform feature extraction automatically. Additionally, the use of
deep learning to tackle the problem of flood management was found to be rare, despite
its increased usage in image classification and segmentation problems. This indicates the
need to investigate the models from this domain for flood detection and mapping tasks.
Some works have also been conducted on the generative adversarial network (GAN)
that enables to capture high-quality images and provide support in models for estimation
of water levels, analysing surface water, losses in wetlands and river winding. With the
application of GAN, the data sets can be improved, and the models could be trained well.
In the study carried out by [74], a repository was developed for the overhead river images
for training purposes. An augmentation was summarised, and Progressive Growing GAN
(PGGAN) was implemented to train small resolutions images and develop high-resolution
images. Some limitations have been observed with conventional GAN resulting in high
computational time and gradient issues that PGGAN overcomes. GAN is the primary
system for the generation of unsupervised data [68]. The network of a generator and
discriminator work in contrast to each other, where the generator creates realistic images
and fools the discriminator to not distinguish between the real and fake images. Thus, the
shortage of data was overcome with the application of GAN, and better outcomes of the
models were achieved.
Data mining and social sensing with the application of Natural Language Processing
(NLP) is an emerging technology to extract and assess social media data for any disaster
event [69–71]. Social media provides current information about the event and keep the
public up to date about the oncoming hazard. This data will facilitate the prediction of the
emergency scenario and understand human behaviour by assessing underline patterns of
media users. Social sensing has advantages over field surveys and interviews, as it gathers
data from the public, not directly from the disaster responders, provides real-time data of
the disaster scenario and facilitate in making a timely decision for mitigating the disaster
and informing the public about evacuation plans [75].
Another method of data collection and analysis is through crowdsourcing, which

is a cost-effective and time-efficient method. The performance of crowdsourcing can
be significantly enhanced with the application of AI and machine learning methods or
flood management, as it provides access to good quality structured data for training the
algorithms. Crowdsourcing relates to data collection and decision-making approach based
on the information gathered [76,77]. For disaster management, crowdsourcing aims to
collect and analyse the data. It facilitates gathering firsthand information about disaster
situations, sharing knowledge on online platforms. It processes data through image
labelling, putting coordinates, tagging and categorising, such as labelling of damaged
infrastructure on images collected through remote sensing. This results in the generation of
structured and precise data for input into machine learning models and making real-time
decisions [78–80].
4. Discussion
RQ-3. What are the existing gaps in the selected technologies for flood management?
The image processing technique has been widely applicable for flood monitoring,
identifying routes and landmarks. 3D geodetic data for flood analysis is essential for flood
management. A large number of geodetic, photogrammetric and remote sensing techniques
are available to collect 3D data as it provides more in-depth information and provides an
opportunity to extract digital terrain and surface models [78]. Advanced techniques such
as Laser scanning—LIDAR (Light Detection and Ranging) and UAV (Unmanned Aerial
Vehicle) have been investigated for conducting surveys. The gathered information can
be useful to analyse geodetic information on the exiting environment and the impacts of
potential disaster, its impacts on the area and the damage caused. These technologies help
to collect a large amount of data in a short time with high accuracy and can be used for
future analysis. These techniques allow higher data accuracy which is achieved through
high resolution of the collected data having higher data density. With the advancement in
technology, compact devices are being built with platforms that collect data. Affordable
prices make it more attractive to the end-user [78–81]. However, there is a certain limitation
of image processing that hinders the wider uptake of this technique and achievement of
the required outcomes. Often, the quality of the images is marginalised due to various
factors, and the obtained results are less accurate. These factors may include brightness,
contrast, environmental pollution, clouds and dust particles. Different correction features
such as radiometric, geometric corrections and bad line replacement are applied to obtain
desired results. It is often difficult to obtain consistent results and the required quality
of the image with each test image due to several interferences and limitations of this
technique. It is often observed that pre-defined algorithms or scripts may work fine for
a certain set of images while it may not be able to process other sets of images due to
inconsistencies that may be due to various factors [82,83]. To address these issues, various
AI and machine learning tools can be adopted. Higher accuracy and reliability could be
obtained by utilising large datasets for training a prediction model. Different sensors are
used to capture feature and mapping applications. A holistic approach could be carried
out to implement image processing along with other techniques so that the limitations are
overcome and better results could be obtained. For example, Munawar et al. [84] applied a
novel approach to image processing and machine learning for post-disaster management.
The researchers focused on identifying the floods using machine-based analysis of images.
The developed model used a holistic approach for incorporating image processing and
machine learning, which was computationally efficient and was able to speed up the
training process. The improved images were used by the classifier for training purposes
and updating core algorithms. The model was able to classify flooded and non-flooded
images with a timely response for providing the aid [84]. Furthermore, hyperspectral
imagery has been widely used instead of multispectral imagery to differentiate mixed
pixel images. Another technique of image fusion has also been used often to improve
classification instead of individual sensors, which may be inconsistent.

RQ-4. How can the authorities improve the existing flood management operation with
cutting-edge technologies?
Based
processing of on thedatasets,
large extensiveand review,
trainit prediction
is suggestedmodels
that thewhich
authorities should adopt
can implement image
intelli-
processing
gence as per the techniques in tandem
training models. Thiswith machine
would give learning. Machineoflearning
higher accuracy will enable
the obtained resultsthe
processing
[82–84]. As perofthelarge datasets,
extensive and train
review prediction
carried out for models which
this study, can implement
numerous intelligence
technologies are
as per the
currently training
being used models.
involving This wouldintelligence
artificial give higher andaccuracy
machineof the obtainedhowever,
learning; results [82–84].
not
As per
much work theisextensive reviewout
being carried carried out for this
to integrate study, numerous
technologies technologies
for enhanced are currently
management of
being used involving artificial intelligence and machine learning; however,
floods. To improve the existing systems, the authorities can map the flooded region either not much work
is being
using aerialcarried
imagery out to integrate
through technologies
satellites or using UAVsfor enhanced
allocatedmanagement
to the affected of regions.
floods. To
improve the existing systems, the authorities can map the
The UAV route can be optimised to provide maximum area coverage of the area in mini-flooded region either using
aerial imagery through satellites or using UAVs allocated to
mum time and cost [83] (Figure 6). The UAV swarm will collect the images of the region the affected regions. The
andUAV routethe
provide cangathered
be optimised
data toto provide
the controlmaximum area coverage
centre [85–88]. Recently,of the area in
Albani et minimum
al. [85]
time and cost [83] (Figure 6). The UAV swarm will collect the
applied a macroscopic model for monitoring an area using UAVs. Parametriasition was images of the region and
provide the gathered data to the control centre [85–88]. Recently,
proposed for efficient allocation of the UAVs; abstract multiple-agent simulations were Albani et al. [85] applied
a macroscopic
conducted to deploymodelUAVsfor monitoring an areaand
in multiple areas, using UAVs. Parametriasition
simulation of UAV swarm was was carried
proposed
for efficient allocation of the UAVs; abstract multiple-agent simulations
out for mapping the areas. Similarly, Venturini et al. [86] proposed a Reinforcement Learn- were conducted
ingto(RL)
deploy UAVstoindeal
approach multiple areas,swarms
with large and simulation
allocatingoftoUAV swarm was
non-uniform carried outoffor
distributions
mapping the areas. Similarly, Venturini et al. [86] proposed
targets. It was found in the study that training the UAVs for specific scenario a Reinforcement Learning (RL)
assist in
approach to deal with large swarms allocating to non-uniform distributions of targets. It
adapting to any new scenario with the least amount of training. The real-time data col-
was found in the study that training the UAVs for specific scenario assist in adapting to
lected from drones during flood situations could be analysed using pre-processing meth-
any new scenario with the least amount of training. The real-time data collected from
ods. Also, with the application of edge detection, it could help extract the features and
drones during flood situations could be analysed using pre-processing methods. Also, with
label the images. The extracted images are fed into machine learning algorithms for train-
the application of edge detection, it could help extract the features and label the images.
ing the models. Shortage of data could be an obstacle for efficiently training the models.
The extracted images are fed into machine learning algorithms for training the models.
To overcome these issues, authorities can apply GAN [89–91]. The generative models can
Shortage of data could be an obstacle for efficiently training the models. To overcome these
be successfully applied for producing realistic images, thus assisting in generating more
issues, authorities can apply GAN [89–91]. The generative models can be successfully
data. The data set can then be processed to develop flood maps, evacuation plans and for
applied for producing realistic images, thus assisting in generating more data. The data set
delivering relief goods to the victims [92–98]. A framework is proposed based on image
can then be processed to develop flood maps, evacuation plans and for delivering relief
processing and artificial intelligence learning (Figure 7).
goods to the victims [92–98]. A framework is proposed based on image processing and
artificial intelligence learning (Figure 7).
Figure 6. UAV swarm capturing affected region and knowledge-sharing mechanism.
Figure 6. UAV swarm capturing affected region and knowledge-sharing mechanism.

Figure 7. A proposed framework based on an integrated approach.

Figure 7. A proposed framework based on an integrated approach.
The authorities can use integrated technologies such as cloud computing, image
processing and artificial
The authorities can use intelligence
integratedfor gathering real-time
technologies information
such as cloud computing, for finding
image routes
pro-
to reach the affected regions. These technologies have the potential
cessing and artificial intelligence for gathering real-time information for finding routes tofor improving the
response in real-time. With the help of images from the disaster site,
reach the affected regions. These technologies have the potential for improving the re- the authorities can
develop
sponse maps for the
in real-time. Withobstacles
the helpand of other
imageshurdles
from that are limiting
the disaster site,the
therelief operation
authorities canto
be carried out efficiently [99–105]. In Baldazo et al. [105], researchers
develop maps for the obstacles and other hurdles that are limiting the relief operation to monitored floods
beby applying
carried Deep Q-Networks
out efficiently [99–105]. In(DQN)
Baldazo asettheal. optimisation strategy
[105], researchers for thefloods
monitored trajectory
by
planning; agents were trained over simulated floods in procedurally generated terrain and
applying Deep Q-Networks (DQN) as the optimisation strategy for the trajectory plan-
demonstrated good performance with two different reward schemes. Similarly, Hildmann
ning; agents were trained over simulated floods in procedurally generated terrain and
et al. [106] investigated the use of UAVs as Mobile Sensing Platforms (MSPs) for Disaster
demonstrated good performance with two different reward schemes. Similarly,
Response, Civil Security and Public Safety. The wider application and uptake of the
Hildmann et al. [106] investigated the use of UAVs as Mobile Sensing Platforms (MSPs)
technology can be enhanced by addressing the challenges for individual UAVs and a swarm
for Disaster Response, Civil Security and Public Safety. The wider application and uptake
of UAVs. The increase in the application of UAVs will enhance the rise of UAV swarms.
of the technology can be enhanced by addressing the challenges for individual UAVs and
Furthermore, social media is a good platform to disseminate information and altering
a swarm of UAVs. The increase in the application of UAVs will enhance the rise of UAV
the community. With the use of smartphones, information dissemination has been acceler-
swarms.
ated. Instead of using traditional cloud computing-based disaster management methods,
Furthermore, social media is a good platform to disseminate information and altering
various AI-based techniques can help the authorities with data offloading and real-time
thedetection
community. With the use of smartphones, information dissemination has been accel-
of disasters. In an emergency, creating awareness among the community and
erated.
providing timelyusing
Instead of traditional
information cloud computing-based
is critical in saving the livesdisaster management
of people [107]. Thesemeth-
tech-
ods, various AI-based techniques can help the authorities with data offloading
nologies can help the authorities in disaster preparedness, planning and decision making. and real-
time
Flooddetection of disasters.
prediction In an emergency,
can be enhanced by using creating
infrared awareness among the
sensors assessing the movement
communityof
and providing timely information is critical in saving the lives
the individuals. The information gathered by the sensors can be analysed and of people [107]. These tech-
forwarded
nologies can help the authorities in disaster preparedness, planning and
to the concerned departments to take necessary actions. Optimising the route and floor decision making.
plan simulation can assist in finding the shortest route for escaping the emergency. The
developed models and sensors must be able to work in dynamic environments and handle
different crises or be complementary to each other [107]. The inclusion of artificial intelli-
gence will capture human intelligence and behaviours in conditions that have not been
considered before. In a disaster response, AI can assist in collecting real-time data from
social media or public platforms and analyse the data based on algorithms using different
classification methods. This can classify informative and non-informative data during a
disaster event. Authorities can apply the shortest path algorithm to come up with the best
evacuation plan and guide their relief teams. Methods have been developed for working in
a static environment with no requirement to manage automatic congestion [108]. Moreover,
the use of big data can accelerate response time and save human lives. The escape route
patterns during a disaster event can be explored using spatiotemporal analytics of social
media, thus providing useful real-time information, as survey data may not be accessible
during a crisis. A deep learning approach can be used by the relief department to analyse
mobility patterns, and with the help of a simulator, human behaviours can be predicted
as per the situation. Furthermore, algorithms with GPUs can predict traffic patterns and
can effectively manage traffic using real-time data. Hence, there are different technologies,
algorithms and models which work in dynamic environments, assess the risk and help
in decision making. A better understanding and application of these technologies by the
emergency departments can fasten up the relief operations.
5. Conclusions
Advanced technologies are essential for maintaining communication, finding the
safest route and providing services to stranded people in a flood event. Comparative
analysis of different technologies is essential to understand the shortcomings of each and
how to address them using an integrative approach. Important resources are required
by the victims to survive during the disaster, and time is critical. With the application
of the latest tools, the safest routes for evacuation can be determined in advance for
regions where the probabilities of exceedance of the flood hazard are anticipated. Image
processing data can provide useful information about the extent of the damage to the
roads, bridges and locate a possible route to reach the victims. It can also help to detect
damage to buildings and infrastructure. Detection of significant landmarks from images
is another method being used to analyse various features from the images to determine
whether a region is flooded or not. Furthermore, AI methods are frequently used to deal
with several flood-related problems, including flood prediction, flood hazard analysis,
flood detection, mapping flood-prone regions and assessing the damage of infrastructure
components after the flood. AI-based algorithms can optimise various functions and
minimise computational time to obtain the desired outcome under any crisis. The images
captured from the disaster site can be feed into the AI algorithms to develop maps for
identifying any obstacles and hurdles that are limiting the relief operation to be carried
out efficiently. AI-based techniques can help the authorities with data offloading and
real-time detection of natural events. Futuristic communities can be imagined with the
use of AI-based sensors gathering information and giving early warning to minimise
the damage. The application of these technologies should be carried out at a large scale
considering any unforeseeable events. These technologies could be extended for advising
developmental initiatives, improving the existing capacity for flood management and
minimising the adverse effects of disasters. Thus, integration of emerging technologies,
networks, services and applications can enhance risk reduction and prepare the community
for any situation. Application of these technologies at different phases of disaster and
keeping dynamicity in consideration can assist in preparing for any oncoming disaster
such as bushfires, earthquakes, etc. Real-time data acquisition can help in evacuation
plans and simulating enhanced evacuation models, thus helping the authorities in disaster
preparedness, planning and decision making.
Author Contributions: Conceptualization, H.S.M., A.W.A.H., M.J.T. and S.T.W.; methodology, H.S.M.
and A.W.A.H.; investigation, H.S.M., A.W.A.H., M.J.T., A.S. and S.T.W.; writing—original draft
preparation, H.S.M. and A.W.A.H.; writing—review and editing, A.W.A.H. and M.J.T.; supervision,
A.W.A.H., M.J.T., A.S. and S.T.W. All authors have read and agreed to the published version of the
manuscript.
Funding: This research received no external funding.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: No new data were created or analyzed in this study. Data sharing is
not applicable to this article.
Conflicts of Interest: The authors declare no conflict of interest.
References
1. Tsai, M.-H.; Yang, C.-H.; Chen, J.Y.; Kang, S.-C. Four-Stage Framework for Implementing a Chatbot System in Disaster Emergency
Operation Data Management: A Flood Disaster Management Case Study. KSCE J. Civ. Eng. 2021, 25, 503–515. [CrossRef]
2. Anbarasan, M.; Muthu, B.; Sivaparthipan, C.B.; Sundarasekar, R.; Kadry, S.; Krishnamoorthy, S.; Dasel, A.A. Detection of flood
disaster system based on IoT, big data and convolutional deep neural network. Comput. Commun. 2020, 150, 150–157. [CrossRef]
3. Gupta, K. Challenges in developing urban flood resilience in India. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 2020, 378,
20190211. [CrossRef]
4. Sintha, E.O.M.; Suryadi, B.; Syafari, M.R. Performance Assessment of Local Government Organizations on Flood Disaster
Prevention and Preparedness in Gunung Mas Regency. Sch. Int. J. Law Crime Justice 2020, 3, 458–462. [CrossRef]
5. Kankanamge, N.; Yigitcanlar, T.; Goonetilleke, A. Kamruzzaman Determining disaster severity through social media analysis:
Testing the methodology with South East Queensland Flood tweets. Int. J. Dis. Risk Reduct. 2020, 42, 101360. [CrossRef]
6. Wu, Z.; Shen, Y.; Wang, H.; Wu, M. Urban flood disaster risk evaluation based on ontology and Bayesian Network. J. Hydrol.
2020, 583, 124596. [CrossRef]
7. Karunarathne, A.Y.; Lee, G. The geographies of the dynamic evolution of social networks for the flood disaster response and
recovery. Appl. Geogr. 2020, 125, 102274. [CrossRef]
8. Oktari, R.S.; Munadi, K.; Idroes, R.; Sofyan, H. Knowledge management practices in disaster management: Systematic review. Int.
J. Dis. Risk Reduct. 2020, 51, 101881. [CrossRef]
9. Wu, Z.; Shen, Y.; Wang, H.; Wu, M. An ontology-based framework for heterogeneous data management and its application for
urban flood disasters. Earth Sci. Inform. 2020, 13, 377–390. [CrossRef]
10. Gautam, A.; Sit, M.; Demir, I. Realistic River Image Synthesis using Deep Generative Adversarial Networks. arXiv 2020,
arXiv:2003.00826.
11. Zhang, J.; Zhou, C.; Xu, K.; Watanabe, M. Flood disaster monitoring and evaluation in China. Glob. Environ. Chang. Part B Environ.
Hazards 2002, 4, 33–43. [CrossRef]
12. Iqbal, U.; Perez, P.; Li, W.; Barthelemy, J. How computer vision can facilitate flood management: A systematic review. Int. J. Dis.
Risk Reduct. 2021, 53, 102030. [CrossRef]
13. Matgen, P.; Schumann, G.; Henry, J.-B.; Hoffmann, L.; Pfister, L. Integration of SAR-derived river inundation areas, high-precision
topographic data and a river flow model toward near real-time flood management. Int. J. Appl. Earth Obs. Geoinf. 2007, 9, 247–263.
[CrossRef]
14. Chen, J.; Li, Q.; Wang, H.; Deng, M. A Machine Learning Ensemble Approach Based on Random Forest and Radial Basis Function
Neural Network for Risk Evaluation of Regional Flood Disaster: A Case Study of the Yangtze River Delta, China. Int. J. Environ.
Res. Public Health 2019, 17, 49. [CrossRef] [PubMed]
15. Elhag, M.; Abdurahman, S.G. Advanced remote sensing techniques in flash flood delineation in Tabuk City, Saudi Arabia. Nat.
16. Tehrany, M.S.; Pradhan, B.; Jebur, M.N. Flood susceptibility analysis and its verification using a novel ensemble support vector
machine and frequency ratio method. Stoch. Environ. Res. Risk Assess. 2015, 29, 1149–1165. [CrossRef]
17. Dawson, D.A.; Vercruysse, K.; Wright, N. A spatial framework to explore needs and opportunities for interoperable urban flood
management. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 2020, 378, 20190205. [CrossRef]
18. Pouyanfar, S.; Tao, Y.; Sadiq, S.; Tian, H.; Tu, Y.; Wang, T.; Shyu, M.L. Unconstrained flood event detection using adversarial data
augmentation. In Proceedings of the International Conference on Image Processing (ICIP), Taipei, Taiwan, 22–25 September 2019;
pp. 155–159.
19. Saravi, S.; Kalawsky, R.; Joannou, D.; Rivas-Casado, M.; Fu, G.; Meng, F. Use of Artificial Intelligence to Improve Resilience and
Preparedness Against Adverse Flood Events. Water 2019, 11, 973. [CrossRef]
20. Hong, H.; Tsangaratos, P.; Ilia, I.; Liu, J.; Zhu, A.-X.; Chen, W. Application of fuzzy weight of evidence and data mining techniques
in construction of flood susceptibility map of Poyang County, China. Sci. Total Environ. 2018, 625, 575–588. [CrossRef]
21. Lütjens, B.; Leshchinskiy, B.; Requena-Mesa, C.; Chishtie, F.; Díaz-Rodriguez, N.; Boulais, O.; Piña, A.; Newman, D.; Lavin, A.;
Gal, Y.; et al. Physics-informed GANs for coastal flood visualization. arXiv 2020, arXiv:2010.08103.
22. Ahmad, D.; Afzal, M. Household vulnerability and resilience in flood hazards from disaster-prone areas of Punjab, Pakistan. Nat.
23. Syifa, M.; Park, S.J.; Achmad, A.R.; Lee, C.-W.; Eom, J. Flood Mapping Using Remote Sensing Imagery and Artificial Intelligence
Techniques: A Case Study in Brumadinho, Brazil. J. Coast. Res. 2019, 90, 197–204. [CrossRef]
24. Chapi, K.; Singh, V.P.; Shirzadi, A.; Shahabi, H.; Bui, D.T.; Pham, B.T.; Khosravi, K. A novel hybrid artificial intelligence approach
for flood susceptibility assessment. Environ. Model. Softw. 2017, 95, 229–245. [CrossRef]
25. Chiba, Y.; Shaw, R.; Prabhakar, S. Climate change-related non-economic loss and damage in Bangladesh and Japan. Int. J. Clim.
Chang. Strat. Manag. 2017, 9, 166–183. [CrossRef]
26. Handayani, W.; Chigbu, U.E.; Rudiarto, I.; Putri, I.H.S. Urbanization and Increasing Flood Risk in the Northern Coast of Central
Java—Indonesia: An Assessment towards Better Land Use Policy and Flood Management. Land 2020, 9, 343. [CrossRef]
27. Vidal, S.; Richaud, B.; Hansen, F.; Courtigne, J. Flood Forecast Tool to Help Dam Management from France to Thailand. In
Advances in Hydroinformatics; Springer: Singapore, 2020; pp. 427–435.
28. Tseng, C.-H.; Chen, L.-C.; Wu, J.-H.; Lin, F.-P.; Sheu, R.-K. An automated image dehazing method for flood detection to improve
flood alert monitoring system. J. Natl. Sci. Found. Sri Lanka 2018, 46, 329. [CrossRef]
29. Munawar, H.S.; Zhang, J.; Li, H.; Mo, D.; Chang, L. Mining multispectral aerial images for automatic detection of strategic bridge
locations for disaster relief missions. In Proceedings of the 23rd Pacific-Asia Conference on Knowledge Discovery and Data
Mining, Macau, China, 14–17 April 2019; Springer: Cham, Switzerland, 2019; pp. 189–200.
30. Shafizadeh-Moghadam, H.; Valavi, R.; Shahabi, H.; Chapi, K.; Shirzadi, A. Novel forecasting approaches using combination of
machine learning and statistical models for flood susceptibility mapping. J. Environ. Manag. 2018, 217, 1–11. [CrossRef]
31. Widiasari, I.R.; Nugroho, L.E. Deep learning multilayer perceptron (MLP) for flood prediction model using wireless sensor
network based hydrology time series data mining. In Proceedings of the 2017 International Conference on Innovative and
Creative Information Technology (ICITech), Salatiga, Indonesia, 2–4 November 2017; pp. 1–5.
32. Gold, C.; Sollich, P. Model selection for support vector machine classification. Neurocomputing 2003, 55, 221–249. [CrossRef]
33. Anusha, N.; Bharathi, B. Flood detection and flood mapping using multi-temporal synthetic aperture radar and optical data.
Egypt. J. Remote Sens. Space Sci. 2020, 23, 207–219. [CrossRef]
34. Gimenez-Maranges, M.; Breuste, J.; Hof, A. Sustainable Drainage Systems for transitioning to sustainable urban flood management
in the European Union: A review. J. Clean. Prod. 2020, 255, 120191. [CrossRef]
35. Donratanapat, N.; Samadi, S.; Vidal, J.M.; Tabas, S.S. A national scale big data analytics pipeline to assess the potential impacts of
flooding on critical infrastructures and communities. Environ. Model. Softw. 2020, 133, 104828. [CrossRef]
36. Cao, C.; Xu, M.; Kamsing, P.; Boonprong, S.; Yomwan, P.; Saokarn, A. Flooding Identification by Vegetation Index. In Environmental
Remote Sensing in Flooding Areas; Springer: Singapore, 2021; pp. 29–44.
37. Mohanty, M.P.; Nithya, S.; Nair, A.S.; Indu, J.; Ghosh, S.; Bhatt, C.M.; Rao, G.S.; Karmakar, S. Sensitivity of various topographic
data in flood management: Implications on inundation mapping over large data-scarce regions. J. Hydrol. 2020, 590, 125523.
[CrossRef]
38. Mishra, A.; Arya, D.S. Development of Decision Support System (DSS) for Urban Flood Management: A Review of Methodologies
and Results. In World Environmental and Water Resources Congress 2020: Water, Wastewater, and Stormwater and Water Desalination
and Reuse; American Society of Civil Engineers: Reston, VA, USA, 2020; pp. 60–72.
39. Singh, G.; Pandey, A. Mapping Punjab Flood using Multi-temporal Open-Access Synthetic Aperture Radar Data in Google Earth
Engine. In Hydrological Extremes; Springer: Cham, Switzerland, 2021; pp. 75–85.
40. Dai, R.; Fan, Z.; Pan, Z. A Virtual Reality Training System for Flood Security. In Transactions on Edutainment XVI; Springer:
Berlin/Heidelberg, Germany, 2020; pp. 126–134.
41. Pradeep, R.M.M.; Wijesekera, N.T.S. Incorporating stakeholder concerns in Land Information Systems for urban flood manage-
ment. Array 2020, 8, 100037. [CrossRef]
42. Bhadra, T.; Chouhan, A.; Chutia, D.; Bhowmick, A.; Raju, P.L.N. Flood Detection Using Multispectral Images and SAR Data. In
International Conference on Machine Learning, Image Processing, Network Security and Data Sciences; Springer: Singapore, 2020; pp.
294–303.
43. Gan, J.L.; Zailah, W. Water Level Classification for Flood Monitoring System Using Convolutional Neural Network. In Proceedings
of the 11th National Technical Seminar on Unmanned System Technology 2019, Kuantan, Malaysia, 2–3 December 2019; Springer:
Singapore, 2021; pp. 299–318.
44. Wing, O.E.J.; Pinter, N.; Bates, P.D.; Kousky, C. New insights into US flood vulnerability revealed from flood insurance big data.
Nat. Commun. 2020, 11, 1444. [CrossRef]
45. Juan, A.; Gori, A.; Sebastian, A. Comparing floodplain evolution in channelized and unchannelized urban watersheds in Houston,
Texas. J. Flood Risk Manag. 2020, 13, e12604. [CrossRef]
46. Gaya, C.O. Application of GIS and Remote Sensing in Flood Management in the Lake Victoria Basin. Ph.D. Thesis, JKUAT-
COETEC, Jomo Kenyatta University of Agriculture and Technology, University in Juja, Juja, Kenya, 2020.
47. Yeum, C.M.; Choi, J.; Dyke, S.J. Automated region-of-interest localization and classification for vision-based visual assessment of
civil infrastructure. Struct. Health Monit. 2018, 18, 675–689. [CrossRef]
48. Supriyanti, R.; Suwitno, S.; Ramadhani, Y.; Widodo, H.B.; Rosanti, T.I. Brightness and Contrast Modification in Ultrasonography
Images Using Edge Detection Results. TELKOMNIKA Telecommun. Comput. Electron. Control 2016, 14, 1090. [CrossRef]
49. Smith, K.; Berry, R.; Clarke, L.E. Exploring the potential of Google Earth as a communication and engagement tool in collaborative
Natural Flood Management planning. Geogr. J. 2019, 186, 171–185. [CrossRef]
50. Lioi, B.; Gioia, A.; Totaro, V.; Balacco, G.; Iacobellis, V.; Chiaia, G. Coupled Use of Hydrologic-Hydraulic Model and Geomorpho-
logical Descriptors for Flood-Prone Areas Evaluation: A Case Study of Lama Lamasinata. In Proceedings of the International
Conference on Computational Science and Its Applications, Cagliari, Italy, 1–4 July 2020; Springer: Cham, Switzerland, 2020;
pp. 607–619.
51. Munawar, H.S.; Maqsood, A. Isotropic surround suppression based linear target detection using hough transform. Int. J. Adv.
Appl. Sci. 2017, 4, 37–42. [CrossRef]
52. Kornfeld, J.; Svara, F.; Wanner, A.A. Image processing for volume electron microscopy. In Volume Microscopy; Humana: New York,
NY, USA, 2020; pp. 245–262.
53. Wu, J.H.; Tseng, C.H.; Chen, L.C.; Lo, S.W.; Lin, F.P. Automated image identification method for flood disaster monitoring in
riverine environments: A case study in Taiwan. In Proceedings of the AASRI International Conference on Industrial Electronics
and Applications (IEA 2015), London, UK, 27–28 June 2015; pp. 27–28.
54. Jacinth, J.; Saravanan, S.; Abijith, D. Integration of SAR and multi-spectral imagery in flood inundation mapping–a case study on
Kerala floods 2018. ISH J. Hydraul. Eng. 2020, 1–11. [CrossRef]
55. Puno, G.R.; Puno, R.C.; Maghuyop, I.V. Two-dimensional flood model for risk exposure analysis of land use/land cover in a
watershed. Glob. J. Environ. Sci. Manag. 2021, 7, 225–238.
56. Wagenaar, D.; Curran, A.; Balbi, M.; Bhardwaj, A.; Soden, R.; Hartato, E.; Sarica, G.M.; Ruangpan, L.; Molinario, G.; Lallemant, D.
Invited perspectives: How machine learning will change flood risk and impact assessment. Nat. Hazards Earth Syst. Sci. 2020, 20,
1149–1161. [CrossRef]
57. Said, A.; Shaat, O.; Su, P.H.; Bogden, P.; Kraig, R.; Bosch, M. Understanding Flooding Detection Using Overhead Imagery-Lessons
Learned. In International Symposium on Visual Computing; Springer: Cham, Switzerland, 2020; pp. 696–706.
58. Karamuz, E.; Romanowicz, R.J.; Doroszkiewicz, J. The use of unmanned aerial vehicles in flood hazard assessment. J. Flood Risk
Manag. 2020, 13, 12622. [CrossRef]
59. Bahrawi, J.; Ewea, H.; Kamis, A.; Elhag, M. Potential flood risk due to urbanization expansion in arid environments, Saudi Arabia.
Nat. Hazards 2020, 104, 795–809. [CrossRef]
60. Ezequiel, C.A.F.; Cua, M.; Libatique, N.C.; Tangonan, G.L.; Alampay, R.; Labuguen, R.T.; Favila, C.M.; Honrado, J.L.E.; Canos, V.;
Devaney, C.; et al. UAV aerial imaging applications for post-disaster assessment, environmental management and infrastructure
development. In Proceedings of the 2014 International Conference on Unmanned Aircraft Systems (ICUAS), Orlando, FL, USA,
27–30 May 2014; pp. 274–283.
61. Esteban, J.; McRoberts, R.E.; Fernández-Landa, A.; Tomé, J.L.; Nӕsset, E. Estimating Forest Volume and Biomass and Their
Changes Using Random Forests and Remotely Sensed Data. Remote Sens. 2019, 11, 1944. [CrossRef]
62. Stylianidis, E.; Akca, D.; Poli, D.; Hofer, M.; Gruen, A.; Sánchez Martín, V. Forsat: A 3D forest monitoring system for cover
mapping and volumetric 3D change detection. Int. J. Digit. Earth 2020, 13, 854–885. [CrossRef]
63. Xu, C.; Manley, B.; Morgenroth, J. Evaluation of modelling approaches in predicting forest volume and stand age for small-scale
plantation forests in New Zealand with RapidEye and LiDAR. Int. J. Appl. Earth Obs. Geoinf. 2018, 73, 386–396. [CrossRef]
64. Dos Reis, A.A.; Franklin, S.E.; de Mello, J.M.; Acerbi, F.W., Jr. Volume estimation in a Eucalyptus plantation using multi-source
remote sensing and digital terrain data: A case study in Minas Gerais State, Brazil. Int. J. Remote Sens. 2019, 40, 2683–2702.
[CrossRef]
65. Akay, S.S.; Özcan, O.; Şanlı, F.B. Quantification and visualization of flood-induced morphological changes in meander structures
by UAV-based monitoring. Eng. Sci. Technol. Int. J. 2021. [CrossRef]
66. Tamminga, A.D.; Eaton, B.C.; Hugenholtz, C.H. UAS-based remote sensing of fluvial change following an extreme flood event.
Earth Surf. Process. Landf. 2015, 40, 1464–1476. [CrossRef]
67. Miřijovský, J.; Langhammer, J. Multitemporal Monitoring of the Morphodynamics of a Mid-Mountain Stream Using UAS
Photogrammetry. Remote Sens. 2015, 7, 8586–8609. [CrossRef]
68. Akay, S.S.; Ozcan, O.; Sen, O.L. Modeling morphodynamic processes in a meandering river with unmanned aerial vehicle-based
measurements. J. Appl. Remote Sens. 2019, 13, 044523. [CrossRef]
69. Liu, Q.; Hu, X.; Ye, M.; Cheng, X.; Li, F. Gas Recognition under Sensor Drift by Using Deep Learning. Int. J. Intell. Syst. 2015, 30,
907–922. [CrossRef]
70. Casado, M.R.; Leinster, P. Towards more effective strategies to reduce property level flood risk: Standardising the use of
Unmanned Aerial Vehicles. J. Water Supply Res. Technol. 2020, 69, 807–818. [CrossRef]
71. Albano, R.; Samela, C.; Crăciun, I.; Manfreda, S.; Adamowski, J.; Sole, A.; Sivertun, Å.; Ozunu, A. Large Scale Flood Risk Mapping
in Data Scarce Environments: An Application for Romania. Water 2020, 12, 1834. [CrossRef]
72. Wu, W.; Emerton, R.; Duan, Q.; Wood, A.W.; Wetterhall, F.; Robertson, D.E. Ensemble flood forecasting: Current status and future
opportunities. Wiley Interdiscip. Rev. Water 2020, 7, 1432. [CrossRef]
73. Riza, H.; Santoso, E.W.; Tejakusuma, I.G.; Prawiradisastra, F.; Prihartanto, P. Utilization of artificial intelligence to improve flood
disaster mitigation. J. Sains Teknol. Mitigasi Bencana 2020, 15, 1–11. [CrossRef]
74. Sun, W.; Bocchini, P.; Davison, B.D. Applications of artificial intelligence for disaster management. Nat. Hazards 2020, 103,
2631–2689. [CrossRef]
75. Guikema, S. Artificial Intelligence for Natural Hazards Risk Analysis: Potential, Challenges, and Research Needs. Risk Anal. 2020,
40, 1117–1123. [CrossRef]
76. Xiang, X.; Li, Q.; Khan, S.; Khalaf, O.I. Urban water resource management for sustainable environment planning using artificial
intelligence techniques. Environ. Impact Assess. Rev. 2021, 86, 106515. [CrossRef]
77. Kuzmić, T.; Ninkov, Т.; Bulatović, V.; Vasić, D.; Davidović, M. Modern Geodetic Methods with Application in the Environmental
Management and its Protection. In Book of Proceedings; University of Belgrade: Belgrade, Serbia, 2017; p. 59.
78. Bakuła, K.; Wziatek,
˛ D.Z.; Weintrit, B.; J˛edryka, M.; Ryfa, T.; Pilarska, M.; Kurczyński, Z. Multi-sourced, remote sensing data in
levees monitoring: Case study of safedam project. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2018, W4, 101–108. [CrossRef]
79. Schumann, G.; Matgen, P.; Cutler, M.; Black, A.; Hoffmann, L.; Pfister, L. Comparison of remotely sensed water stages from
LiDAR, topographic contours and SRTM. ISPRS J. Photogramm. Remote Sens. 2008, 63, 283–296. [CrossRef]
80. Langhammer, J.; Janský, B.; Kocum, J.; Minařík, R. 3-D reconstruction of an abandoned montane reservoir using UAV photogram-
metry, aerial LiDAR and field survey. Appl. Geogr. 2018, 98, 9–21. [CrossRef]
81. Yigitcanlar, T.; DeSouza, K.C.; Butler, L.; Roozkhosh, F. Contributions and Risks of Artificial Intelligence (AI) in Building Smarter
Cities: Insights from a Systematic Review of the Literature. Energies 2020, 13, 1473. [CrossRef]
82. Yigitcanlar, T.; Kankanamge, N.; Regona, M.; Maldonado, A.; Rowan, B.; Ryu, A.; DeSouza, K.C.; Corchado, J.M.; Mehmood, R.;
Li, R.Y.M. Artificial Intelligence Technologies and Related Urban Planning and Development Concepts: How Are They Perceived
and Utilized in Australia? J. Open Innov. Technol. Mark. Complex. 2020, 6, 187. [CrossRef]
83. Montasari, R.; Carroll, F.; Macdonald, S.; Jahankhani, H.; Hosseinian-Far, A.; Daneshkhah, A. Application of Artificial Intelligence
and Machine Learning in Producing Actionable Cyber Threat Intelligence. In Digital Forensic Investigation of Internet of Things (IoT)
Devices; Springer: Cham, Switzerland, 2021; pp. 47–64.
84. Albani, D.; Manoni, T.; Nardi, D.; Trianni, V. Dynamic UAV swarm deployment for non-uniform coverage. In Proceedings
of the 17th International Conference on Autonomous Agents and Multi-Agent Systems, Stockholm, Sweden, 10–15 July 2018;
pp. 523–531.
85. Venturini, F.; Mason, F.; Pase, F.; Chiariotti, F.; Testolin, A.; Zanella, A.; Zorzi, M. Distributed reinforcement learning for flexible
UAV swarm control with transfer learning capabilities. In Proceedings of the 6th ACM Workshop on Micro Aerial Vehicle
Networks, Systems, and Applications, Toronto, ON, Canada, 15 June 2020; pp. 1–6.
86. Erdelj, M.; Król, M.; Natalizio, E. Wireless Sensor Networks and Multi-UAV systems for natural disaster management. Comput.
Netw. 2017, 124, 72–86. [CrossRef]
87. Abdelkader, M.; Shaqura, M.; Ghommem, M.; Collier, N.; Calo, V.; Claudel, C. Optimal multi-agent path planning for fast inverse
modeling in UAV-based flood sensing applications. In Proceedings of the 2014 International Conference on Unmanned Aircraft
Systems (ICUAS), Orlando, FL, USA, 27–30 May 2014; pp. 64–71.
88. Ortiz, B.; Kahn, L.; Bosch, M.; Bogden, P.; Pavon-Harr, V.; Savas, O.; McCulloh, I. Improving Community Resiliency and
Emergency Response With Artificial Intelligence. arXiv 2020, arXiv:2005.14212.
89. Chang, D.-L.; Yang, S.-H.; Hsieh, S.-L.; Wang, H.-J.; Yeh, K.-C. Artificial Intelligence Methodologies Applied to Prompt Pluvial
Flood Estimation and Prediction. Water 2020, 12, 3552. [CrossRef]
90. Razali, N.; Ismail, S.; Mustapha, A. Machine learning approach for flood risks prediction. IAES Int. J. Artif. Intell. 2020, 9, 73–80.
[CrossRef]
91. Munawar, H.S. Flood Disaster Management: Risks, Technologies, and Future Directions. Mach. Vis. Insp. Syst. 2020, 1, 115–146.
92. Khalilpourazari, S.; Pasandideh, S.H.R. Designing emergency flood evacuation plans using robust optimization and artificial
intelligence. J. Comb. Optim. 2021, 41, 640–677. [CrossRef]
93. Webster, C.; Ivanov, S. Robotics, artificial intelligence, and the evolving nature of work. In Digital Transformation in Business and
Society; Palgrave Macmillan: Cham, Switzerland, 2020; pp. 127–143.
94. Ofli, F.; Imran, M.; Alam, F. Using Artificial Intelligence and Social Media for Disaster Response and Management: An Overview.
In AI and Robotics in Disaster Studies; Springer: Berlin/Heidelberg, Germany, 2020; pp. 63–81.
95. Chang, F.-J.; Guo, S. Advances in Hydrologic Forecasts and Water Resources Management. Water 2020, 12, 1819. [CrossRef]
96. Fu, G.; Meng, F.; Casado, M.R.; Kalawsky, R.S. Towards Integrated Flood Risk and Resilience Management. Water 2020, 12, 1789.
[CrossRef]
97. Pham, B.T.; Luu, C.; Van Phong, T.; Nguyen, H.D.; Van Le, H.; Tran, T.Q.; Ta, H.T.; Prakash, I. Flood risk assessment using hybrid
artificial intelligence models integrated with multi-criteria decision analysis in Quang Nam Province, Vietnam. J. Hydrol. 2021,
592, 125815. [CrossRef]
98. Shahabi, H.; Shirzadi, A.; Ghaderi, K.; Omidvar, E.; Al-Ansari, N.; Clague, J.J.; Geertsema, M.; Khosravi, K.; Amini, A.; Bahrami,
S.; et al. Flood Detection and Susceptibility Mapping Using Sentinel-1 Remote Sensing Data and a Machine Learning Approach:
Hybrid Intelligence of Bagging Ensemble Based on K-Nearest Neighbor Classifier. Remote Sens. 2020, 12, 266. [CrossRef]
99. Hong, H.; Panahi, M.; Shirzadi, A.; Ma, T.; Liu, J.; Zhu, A.-X.; Chen, W.; Kougias, I.; Kazakis, N. Flood susceptibility assessment
in Hengfeng area coupling adaptive neuro-fuzzy inference system with genetic algorithm and differential evolution. Sci. Total
Environ. 2018, 621, 1124–1141. [CrossRef] [PubMed]
100. Khosravi, K.; Shahabi, H.; Pham, B.T.; Adamowski, J.; Shirzadi, A.; Pradhan, B.; Prakash, I. A comparative assessment of flood
susceptibility modeling using multi-criteria decision-making analysis and machine learning methods. J. Hydrol. 2019, 573,
311–323. [CrossRef]
101. Wang, Z.; Lai, C.; Chen, X.; Yang, B.; Zhao, S.; Bai, X. Flood hazard risk assessment model based on random forest. J. Hydrol. 2015,
527, 1130–1141. [CrossRef]
102. Ullah, K.; Zhang, J. GIS-based flood hazard mapping using relative frequency ratio method: A case study of Panjkora River Basin,
eastern Hindu Kush, Pakistan. PLoS ONE 2020, 15, e0229153. [CrossRef] [PubMed]
103. Jahangir, M.H.; Reineh, S.M.M.; Abolghasemi, M. Spatial predication of flood zonation mapping in Kan River Basin, Iran, using
artificial neural network algorithm. Weather Clim. Extrem. 2019, 25, 100215. [CrossRef]
104. Baldazo, D.; Parras, J.; Zazo, S. Decentralized multi-agent deep reinforcement learning in swarms of drones for flood monitoring.
In Proceedings of the 27th European Signal Processing Conference (EUSIPCO), A Coruna, Spain, 2–6 September 2019; pp. 1–5.
105. Hildmann, H.; Kovacs, E. Using unmanned aerial vehicles (UAVs) as mobile sensing platforms (MSPs) for disaster response, civil
security and public safety. Drones 2019, 3, 59. [CrossRef]
106. Qadir, Z.; Ullah, F.; Munawar, H.S.; Al-Turjman, F. Addressing disasters in smart cities through UAVs path planning and 5G
communications: A systematic review. Comput. Commun. 2021, 168, 114–135. [CrossRef]
107. Dhara, S.; Dang, T.; Parial, K.; Lu, X.X. Accounting for Uncertainty and Reconstruction of Flooding Patterns Based on Multi-
Satellite Imagery and Support Vector Machine Technique: A Case Study of Can Tho City, Vietnam. Water 2020, 12, 1543.
[CrossRef]
108. Sermet, Y.; Demir, I. Towards an information centric flood ontology for information management and communication. Earth Sci.
Inform. 2019, 12, 541–551. [CrossRef]
View publication stats

Sustainability 13 07925

Uploaded by

Copyright:

Available Formats

Sustainability 13 07925

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Sustainability 13 07925

Uploaded by

Copyright:

Available Formats

See discussions, stats, and author profiles for this publication at: https://www.researchgate.

An Integrated Approach for Post-Disaster Flood Management Via the Use of

Article in Sustainability · July 2021

Steven Travis Waller Muhammad Jamaluddin Thaheem

SEE PROFILE SEE PROFILE

The user has requested enhancement of the downloaded file.

Academic Editor: Chunjiang An

Sustainability 2021, 13, 7925. https://doi.org/10.3390/su13147925 https://www.mdpi.com/journal/sustainability

2. Materials and Methods

Sustainability 2021, 13, 7925 5 of 22

3.1. Image Processing

Sustainability 2021, 13, 7925 6 of 22

Figure Input image

3.1.3. Post-Disaster Assessment Using UAV

Table 2. Comparison of image processing methods for flood management.

Technique Method Imaging Device Outcome Limitation Authors

3.2. Artificial Intelligence (AI)

In Equation (1), Ym denotes the normalised values of ym . The minimum value of yj is

Table 3. Comparison of AI techniques for flood management.

Tool/Tech Method Study Area Outcome Limitation Reference

Tool/Tech Method Study Area Outcome Limitation Reference

Another method of data collection and analysis is through crowdsourcing, which

Sustainability 2021, 13, x FOR PEER REVIEW 15 of 22

Figure 6. UAV swarm capturing affected region and knowledge-sharing mechanism.

Figure 6. UAV swarm capturing affected region and knowledge-sharing mechanism.

Figure 7. A proposed framework based on an integrated approach.

View publication stats

You might also like