CN117115671A - Soil quality analysis method and device based on remote sensing and electronic equipment - Google Patents
Soil quality analysis method and device based on remote sensing and electronic equipment Download PDFInfo
- Publication number
- CN117115671A CN117115671A CN202310893678.6A CN202310893678A CN117115671A CN 117115671 A CN117115671 A CN 117115671A CN 202310893678 A CN202310893678 A CN 202310893678A CN 117115671 A CN117115671 A CN 117115671A
- Authority
- CN
- China
- Prior art keywords
- soil
- remote sensing
- soil quality
- land
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000002689 soil Substances 0.000 title claims abstract description 329
- 238000004458 analytical method Methods 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000005516 engineering process Methods 0.000 claims abstract description 16
- 239000002245 particle Substances 0.000 claims description 21
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 11
- 238000010801 machine learning Methods 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 5
- 238000011176 pooling Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000013441 quality evaluation Methods 0.000 abstract description 10
- 238000004891 communication Methods 0.000 description 6
- 230000002650 habitual effect Effects 0.000 description 4
- 238000003709 image segmentation Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000004016 soil organic matter Substances 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000004856 soil analysis Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
Abstract
The invention provides a soil quality analysis method and device based on remote sensing and electronic equipment, wherein the method comprises the following steps: acquiring satellite remote sensing data and DEM elevation data; acquiring a land structure image based on the satellite remote sensing data; dividing and identifying the land structure image based on an image processing technology, and determining land types of different land structure areas; carrying out soil level identification on each land type based on the DEM elevation data to obtain soil level depth; determining soil influence parameters based on the remote sensing data, and obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth; and determining a soil quality analysis result based on the soil quality parameter. The soil quality evaluation method can realize comprehensiveness and accuracy of soil quality evaluation.
Description
Technical Field
The invention relates to the technical field of remote sensing image processing, in particular to a soil quality analysis method and device based on remote sensing and electronic equipment.
Background
At present, most of technical schemes for soil analysis by using remote sensing data only pay attention to single soil parameter estimation, especially the water content is high, and factors such as different land structures, land types, soil layer depths and the like are not comprehensively analyzed. Furthermore, the prior art is still limited by spectral data, lacking a comprehensive assessment and grading of soil quality.
Therefore, how to realize the comprehensiveness and accuracy of soil quality evaluation is a technical problem which needs to be solved currently.
Disclosure of Invention
The invention provides the technical field of remote sensing image processing, in particular to a soil quality analysis method, a device and electronic equipment based on remote sensing, which are used for solving the defects existing in the prior art and realizing comprehensiveness and accuracy of soil quality assessment.
The invention provides a soil quality analysis method based on remote sensing, which comprises the following steps:
acquiring satellite remote sensing data and DEM elevation data;
acquiring a land structure image based on the satellite remote sensing data;
dividing and identifying the land structure image based on an image processing technology, and determining land types of different land structure areas;
carrying out soil level identification on each land type based on the DEM elevation data to obtain soil level depth;
determining soil influence parameters based on the remote sensing data, and obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth;
and determining a soil quality analysis result based on the soil quality parameter.
According to the soil quality analysis method based on remote sensing provided by the invention, the soil structure image is segmented and identified based on an image processing technology, and the soil types of different soil structure areas are determined, and the soil quality analysis method comprises the following steps:
performing image size adjustment, gray value balance and edge detection on the land structure image to obtain a preprocessed image;
convoluting, pooling and upsampling the preprocessed image based on a first convolutional neural network model to obtain image features of the preprocessed image, and determining different land structures based on the image features;
and identifying each land structure based on a second convolutional neural network model to obtain land types of the different land structure areas.
According to the soil quality analysis method based on remote sensing provided by the invention, the soil influence parameters comprise at least one of NDVI value, elevation, surface temperature and normalized water index.
According to the soil quality analysis method based on remote sensing provided by the invention, the soil level identification is carried out on each land type based on the DEM elevation data to obtain the soil level depth, and the soil level depth comprises the following steps:
determining a starting thickness and spatial coordinates of the land type based on the DEM elevation data;
and obtaining the soil layer depth based on the initial thickness, the space coordinates and the calculation parameters through an expansion model, wherein the soil layer depth is shown in the following formula:
H (x,y) ＝H 0 +K 1 exp(-K 2 y)
H (x,y) depth of soil layer, H 0 To start thickness, K 1 And K 2 Is a parameter, y is a spatial coordinate;
wherein the calculated parameters are determined by fitting verification of the expansion model based on machine learning
According to the soil quality analysis method based on remote sensing provided by the invention, the soil quality parameters are obtained based on the soil influence parameters, the land type and the soil layer depth, and the soil quality parameters comprise:
analyzing the soil influence parameters, the land type and the soil layer depth based on a regression model to obtain the soil quality parameters, wherein the soil quality parameters are shown in the following formula:
M＝β 0 t 0 +β 1 t 1 +β 2 t 2 +β 3 t 3 +β 4 t 4 +β 5 t 5 +ε
wherein M is the soil quality parameter, t i Beta is any one of soil influence parameters, land type or soil level depth i For regression coefficients, i=0, 1, 2, 3, 4, 5, epsilon is the error term;
the regression coefficients and error terms are determined by performing a your fit verification on the regression model based on machine learning.
According to the soil quality analysis method based on remote sensing, the soil influence parameters comprise the average particle diameter of soil;
the method for determining the average particle diameter of the soil comprises the following steps:
determining the pixel area of a target image corresponding to the soil quality parameter analysis;
traversing a target parameter representing a diameter of soil particles in the soil quality parameter;
the soil average particle diameter is determined based on the target parameter and pixel area.
According to the soil quality analysis method based on remote sensing provided by the invention, the soil quality analysis result is determined based on the soil quality parameters, and the soil quality analysis method comprises the following steps:
converting the soil quality parameters into standardized scores, and determining target weights corresponding to the soil quality parameters;
and carrying out weighted average on the standardized scores and the target weights to obtain the soil quality analysis result.
The invention also provides a soil quality analysis device based on remote sensing, which comprises:
the data acquisition module is used for acquiring satellite remote sensing data and DEM elevation data;
the image acquisition module is used for acquiring a land structure image based on the satellite remote sensing data;
the segmentation and identification module is used for segmenting and identifying the land structure image based on an image processing technology and determining land types of different land structure areas;
the level recognition module is used for carrying out soil level recognition on each land type based on the DEM elevation data to obtain soil level depth;
the parameter determining module is used for determining soil influence parameters based on the remote sensing data and obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth;
and the quality analysis module is used for determining a soil quality analysis result based on the soil quality parameter.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the soil quality analysis method based on remote sensing when executing the program.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a remote sensing based soil quality analysis method as described in any of the above.
The invention also provides a computer program product comprising a computer program which when executed by a processor implements a remote sensing based soil quality analysis method as described in any of the above.
According to the soil quality analysis method and device based on remote sensing and the electronic equipment, satellite remote sensing data and DEM elevation data are acquired, and a soil structure image is acquired based on the satellite remote sensing data; dividing and identifying the land structure image based on an image processing technology, and determining land types of different land structure areas; carrying out soil level identification on each land type based on the DEM elevation data to obtain soil level depth; and determining soil influence parameters based on the remote sensing data, obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth, and finally determining a soil quality analysis result based on the soil quality parameters. The soil quality evaluation method can realize comprehensiveness and accuracy of soil quality evaluation.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a soil quality analysis method based on remote sensing provided by the invention;
FIG. 2 is a second schematic flow chart of the soil quality analysis method based on remote sensing provided by the invention;
FIG. 3 is a second schematic flow chart of the soil quality analysis method based on remote sensing provided by the invention;
fig. 4 is a schematic structural diagram of a soil quality analysis device based on remote sensing provided by the invention;
fig. 5 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the soil quality analysis method based on remote sensing provided by the invention comprises the following steps:
step 110, acquiring satellite remote sensing data and DEM elevation data;
step 120, acquiring a land structure image based on the satellite remote sensing data;
130, dividing and identifying the land structure image based on an image processing technology, and determining land types of different land structure areas;
step 140, carrying out soil level identification on each land type based on the DEM elevation data to obtain soil level depth;
step 150, determining soil influence parameters based on the remote sensing data, and obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth;
and 160, determining a soil quality analysis result based on the soil quality parameter.
The above steps are described in detail below.
In the above steps 110 and 120, satellite remote sensing data and DEM elevation data are acquired, and then a land structure image is acquired from the satellite remote sensing data. The satellite remote sensing data is high-resolution remote sensing data, and the high-resolution satellite remote sensing data generally refers to data with finer space details and more accurate ground object information. The resolution is defined as the size of the unit ground area corresponding to the sensor pixels, and the resolution of the high-resolution satellite remote sensing data can be several meters to tens of centimeters.
DEM (Digital Elevation Model) elevation data is a digital model in the Geographic Information System (GIS) that describes the elevation of a surface, representing elevation or elevation information of the surface in a grid or vector form. DEM elevation data is also acquired by measurement or remote sensing techniques to provide detailed description and quantitative analysis of the topographical surface. DEM elevation data records elevation values, typically in meters, for each location on the earth's surface. DEM data may be used in a number of application fields including terrain analysis, hydrologic modeling, land use planning, three-dimensional visualization, and the like.
And then, performing type recognition and hierarchical depth recognition on the obtained land structure image through the steps 130 and 140.
The process of carrying out type identification on the land structure image can be realized by utilizing a convolutional neural network model, namely, the land structure image is subjected to operations such as feature extraction, feature segmentation and the like, so that the land structure image is segmented into different land structures such as soil, deserts, grasslands, roads, buildings and the like.
The process of carrying out hierarchical depth identification on the land structure image can utilize the expansion model to carry out soil hierarchical analysis through habitual thickness differences, and the dividing principle is to divide according to habitual thickness differences of different soil layers, so that the soil hierarchical depths of different horizontal planes of the land structure image are determined.
Further, through the above step 150, according to the obtained land type and the soil layer depth, comprehensive analysis is performed in combination with the soil influence parameters, so as to obtain the quality parameters of the soil.
Optionally, the soil influencing parameter comprises at least one of NDVI value, elevation, surface temperature, normalized water index.
It will be appreciated that the above-mentioned soil influencing parameters, such as NDVI value, elevation, surface temperature, normalized water index, may be directly obtained according to the remote sensing data, and then the soil quality parameters including, but not limited to, soil organic matter content, PH value, water content, average granularity diameter, etc. may be determined by combining the soil type and soil level depth obtained in the above-mentioned steps 130 and 140.
And finally, according to the obtained soil quality parameters and the weight data of the parameters, obtaining a final soil quality evaluation result.
According to the soil quality analysis method based on remote sensing, satellite remote sensing data and DEM elevation data are obtained, and a land structure image is obtained based on the satellite remote sensing data; dividing and identifying the land structure image based on an image processing technology, and determining land types of different land structure areas; carrying out soil level identification on each land type based on the DEM elevation data to obtain soil level depth; and determining soil influence parameters based on the remote sensing data, obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth, and finally determining a soil quality analysis result based on the soil quality parameters. The soil quality evaluation method can realize comprehensiveness and accuracy of soil quality evaluation.
Referring to fig. 2, in some alternative embodiments, the segmenting and identifying the land structure image based on the image processing technology, determining land types of different land structure areas includes:
step 210, performing image size adjustment, gray value balance and edge detection on the land structure image to obtain a preprocessed image;
step 220, convoluting, pooling and up-sampling the preprocessed image based on a first convolutional neural network model to obtain image characteristics of the preprocessed image, and determining different land structures based on the image characteristics;
and 230, identifying each land structure based on the second convolutional neural network model to obtain land types of the different land structure areas.
It can be understood that this embodiment is a specific manner of land type identification, and the specific flow is as follows:
image preprocessing: firstly, image preprocessing is needed, including image size adjustment, gray value balance, edge detection and other operations, so that better image quality is obtained, and subsequent image segmentation and recognition are facilitated.
Image segmentation: the deep learning segmentation algorithm automatically extracts image features by means of a first convolutional neural network model, such as a U-Net convolutional neural network model, through operations of multiple convolutions, pooling, up-sampling and the like, and achieves image segmentation to segment different land structures of soil, deserts, grasslands, roads, buildings and the like.
Identification algorithm: after the land structure area is obtained, a deep learning algorithm is adopted, and land types such as cultivated land, woodland, grassland, urban area, mountain body, desert and the like are identified by taking the land structure in the second step as input through a second convolutional neural network model such as an AlexNet convolutional neural network model.
According to the soil quality analysis method based on remote sensing, the image segmentation and the type recognition are carried out on the remotely-sensed image through the convolutional neural network model, so that the remotely-sensed land structure image can be accurately divided into various different types, and the soil quality analysis is conveniently carried out on the various types of land structure images, so that the comprehensiveness and the accuracy of the soil quality analysis are realized.
In some optional embodiments, the performing soil level recognition on each land type based on the DEM elevation data to obtain a soil level depth includes:
determining a starting thickness and spatial coordinates of the land type based on the DEM elevation data;
and obtaining the soil layer depth based on the initial thickness, the space coordinates and the calculation parameters through an expansion model, wherein the soil layer depth is shown in the following formula:
H (x,y) ＝H 0 +K 1 exp(-K 2 y)
H (x,y) depth of soil layer, H 0 To start thickness, K 1 And K 2 Is a parameter, y is a spatial coordinate;
wherein the calculated parameters are determined based on machine learning by fitting verification of the expansion model.
It will be appreciated that this embodiment is a process of acquiring soil level depth.
Based on elevation data, an expansion model is adopted, soil layer analysis is carried out through habitual thickness differences, the division principle is to divide according to habitual thickness differences of different soil layers, and the method is as follows:
H (x,y) ＝H 0 +K 1 exp(-K 2 y)
wherein H is (x,y) The soil layer thickness, i.e., the soil layer depth, H, representing the position y from the ground level 0 Represents the initial thickness, K 1 And K 2 Is a parameter and y is a spatial coordinate.
By actually sampling and sounding different soil types, machine learning is performed by using the expansion model, and the parameter K is calculated 1 And K 2 And performing fitting verification, and finally, taking the fitting verification as a calculation parameter of the depth of different soil types and layers of the whole area.
According to the soil quality analysis method based on remote sensing, the initial thickness and the space coordinates of the soil structure image are obtained through the DEM elevation data, and the relevant parameters are obtained through fitting verification, so that the soil layer depth of the soil structure image is obtained, and the soil quality analysis is conveniently carried out according to the soil layer depth, so that the comprehensiveness and the accuracy of the soil quality analysis are realized.
In some optional embodiments, the obtaining the soil quality parameter based on the soil influence parameter, the soil type, and the soil level depth includes:
analyzing the soil influence parameters, the land type and the soil layer depth based on a regression model to obtain the soil quality parameters, wherein the soil quality parameters are shown in the following formula:
M＝β 0 t 0 +β 1 t 1 +β 2 t 2 +β 3 t 3 +β 4 t 4 +β 5 t 5 +ε
wherein M is the soil quality parameter, t i Beta is any one of soil influence parameters, land type or soil level depth i For regression coefficients, i=0, 1, 2, 3, 4, 5, epsilon is the error term;
the regression coefficients and error terms are determined by performing a your fit verification on the regression model based on machine learning.
It will be appreciated that this embodiment is a process for determining soil quality parameters.
In this embodiment, for example, the NDVI value, elevation, surface temperature, normalized water index, land type, and soil level depth are respectively denoted as t 0 、t 1 、t 2 、t 3 、t 4 、t 5 The regression coefficients corresponding to the above are respectively marked as beta 0 、β 1 、β 2 、β 3 、β 4 、β 5 。
According to the formula, the soil quality parameters obtained by utilizing the soil influence parameters, the land types or the soil layer depths are calculated.
Further, the soil influencing parameter comprises a soil average particle diameter;
the method for determining the average particle diameter of the soil comprises the following steps:
determining the pixel area of a target image corresponding to the soil quality parameter analysis;
traversing a target parameter representing a diameter of soil particles in the soil quality parameter;
the soil average particle diameter is determined based on the target parameter and pixel area.
The soil quality parameters comprise soil organic matter content, pH value, water content, average granularity diameter and the like.
Among them, the present example mainly determines the average particle diameter of soil.
First, a pixel area of a target image in a land type recognition process of a land structure image is determined. Then traversing all soil particle diameters in the target image, and finally determining the average soil particle diameter through summation average, wherein a specific formula can be expressed as follows:
where Di represents the diameter of the ith particle and Ai is its pixel area. By traversing the entire land classification cut image, the average particle diameter at the different cut images can be obtained.
In some alternative embodiments, the determining the soil quality analysis result based on the soil quality parameter includes:
converting the soil quality parameters into standardized scores, and determining target weights corresponding to the soil quality parameters;
and carrying out weighted average on the standardized scores and the target weights to obtain the soil quality analysis result.
It will be appreciated that this embodiment is an analytical process for soil quality.
Firstly, the soil quality parameters are converted into standardized scores, and the values are scaled to 0 to the upper range1. Then, according to the weighted average method, for n soil parameters, assume that the normalized score of the ith parameter is S i The corresponding weight is W i Then comprehensive score S tat The calculation formula of (2) is as follows:
in the actual implementation process, the soil quality can be graded as a whole according to the score interval, and the soil quality is optimized: [0.8,1.0); good: [0.6,0.8); in (a): [0.4,0.6); the difference is: [0.2, 0.4); extremely bad: [0.0,0.2).
According to the soil quality analysis method based on remote sensing, the soil quality parameters are subjected to standardized score conversion, and the weighting coefficients are used for weighting and summing, so that the final comprehensive score of the soil quality is obtained, and the comprehensiveness and the accuracy of the soil quality analysis are realized.
The soil quality analysis device based on remote sensing provided by the invention is described below, and the soil quality analysis device based on remote sensing described below and the soil quality analysis method based on remote sensing described above can be correspondingly referred to each other.
Referring to fig. 4, the soil quality analysis device based on remote sensing provided by the invention comprises the following modules:
the data acquisition module 410 is configured to acquire satellite remote sensing data and DEM elevation data;
an image acquisition module 420, configured to acquire a land structure image based on the satellite remote sensing data;
a segmentation and identification module 430, configured to segment and identify the land structure image based on an image processing technology, and determine land types of different land structure areas;
the level recognition module 440 is configured to perform soil level recognition on each land type based on the DEM elevation data, so as to obtain a soil level depth;
the parameter determining module 450 is configured to determine a soil influence parameter based on the remote sensing data, and obtain a soil quality parameter based on the soil influence parameter, the land type and the soil layer depth;
a quality analysis module 460 for determining a soil quality analysis result based on the soil quality parameter.
According to the soil quality analysis device based on remote sensing, satellite remote sensing data and DEM elevation data are acquired, and a land structure image is acquired based on the satellite remote sensing data; dividing and identifying the land structure image based on an image processing technology, and determining land types of different land structure areas; carrying out soil level identification on each land type based on the DEM elevation data to obtain soil level depth; and determining soil influence parameters based on the remote sensing data, obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth, and finally determining a soil quality analysis result based on the soil quality parameters. The soil quality evaluation method can realize comprehensiveness and accuracy of soil quality evaluation.
In some optional embodiments, the segmenting and identifying the land structure image based on the image processing technology, determining land types of different land structure areas includes:
performing image size adjustment, gray value balance and edge detection on the land structure image to obtain a preprocessed image;
convoluting, pooling and upsampling the preprocessed image based on a first convolutional neural network model to obtain image features of the preprocessed image, and determining different land structures based on the image features;
and identifying each land structure based on a second convolutional neural network model to obtain land types of the different land structure areas.
In some alternative embodiments, the soil influencing parameter comprises at least one of NDVI value, elevation, surface temperature, normalized water index.
In some optional embodiments, the performing soil level recognition on each land type based on the DEM elevation data to obtain a soil level depth includes:
determining a starting thickness and spatial coordinates of the land type based on the DEM elevation data;
and obtaining the soil layer depth based on the initial thickness, the space coordinates and the calculation parameters through an expansion model, wherein the soil layer depth is shown in the following formula:
H (x,y) ＝H 0 +K 1 exp(-K 2 y)
H (x,y) depth of soil layer, H 0 To start thickness, K 1 And K 2 Is a parameter and y is a spatial coordinate.
Wherein the calculated parameters are determined by fitting verification of the expansion model based on machine learning
In some optional embodiments, the obtaining the soil quality parameter based on the soil influence parameter, the soil type, and the soil level depth includes:
analyzing the soil influence parameters, the land type and the soil layer depth based on a regression model to obtain the soil quality parameters, wherein the soil quality parameters are shown in the following formula:
M＝β 0 t 0 +β 1 t 1 +β 2 t 2 +β 3 t 3 +β 4 t 4 +β 5 t 5 +ε
wherein M is the soil quality parameter, t i Beta is any one of soil influence parameters, land type or soil level depth i For regression coefficients, i=0, 1, 2, 3, 4, 5, epsilon is the error term;
the regression coefficients and error terms are determined by performing a your fit verification on the regression model based on machine learning.
In some alternative embodiments, the soil quality parameter comprises a soil average particle diameter;
the method for determining the average particle diameter of the soil comprises the following steps:
determining the pixel area of a target image corresponding to the soil quality parameter analysis;
traversing a target parameter representing a diameter of soil particles in the soil quality parameter;
the soil average particle diameter is determined based on the target parameter and pixel area.
In some alternative embodiments, the determining the soil quality analysis result based on the soil quality parameter includes:
converting the soil quality parameters into standardized scores, and determining target weights corresponding to the soil quality parameters;
and carrying out weighted average on the standardized scores and the target weights to obtain the soil quality analysis result.
Fig. 5 illustrates a physical schematic diagram of an electronic device, as shown in fig. 5, which may include: processor 510, communication interface (Communications Interface) 520, memory 530, and communication bus 540, wherein processor 510, communication interface 520, memory 530 complete communication with each other through communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a telemetry-based soil quality analysis method comprising:
acquiring satellite remote sensing data and DEM elevation data;
acquiring a land structure image based on the satellite remote sensing data;
dividing and identifying the land structure image based on an image processing technology, and determining land types of different land structure areas;
carrying out soil level identification on each land type based on the DEM elevation data to obtain soil level depth;
determining soil influence parameters based on the remote sensing data, and obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth;
and determining a soil quality analysis result based on the soil quality parameter.
Further, the logic instructions in the memory 530 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of performing the remote sensing-based soil quality analysis method provided by the above methods, the method comprising:
acquiring satellite remote sensing data and DEM elevation data;
acquiring a land structure image based on the satellite remote sensing data;
dividing and identifying the land structure image based on an image processing technology, and determining land types of different land structure areas;
carrying out soil level identification on each land type based on the DEM elevation data to obtain soil level depth;
determining soil influence parameters based on the remote sensing data, and obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth;
and determining a soil quality analysis result based on the soil quality parameter.
In yet another aspect, the present invention provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the remote sensing-based soil quality analysis method provided by the above methods, the method comprising:
acquiring satellite remote sensing data and DEM elevation data;
acquiring a land structure image based on the satellite remote sensing data;
dividing and identifying the land structure image based on an image processing technology, and determining land types of different land structure areas;
carrying out soil level identification on each land type based on the DEM elevation data to obtain soil level depth;
determining soil influence parameters based on the remote sensing data, and obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth;
and determining a soil quality analysis result based on the soil quality parameter.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A soil quality analysis method based on remote sensing, comprising:
acquiring satellite remote sensing data and DEM elevation data;
acquiring a land structure image based on the satellite remote sensing data;
dividing and identifying the land structure image based on an image processing technology, and determining land types of different land structure areas;
carrying out soil level identification on each land type based on the DEM elevation data to obtain soil level depth;
determining soil influence parameters based on the remote sensing data, and obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth;
and determining a soil quality analysis result based on the soil quality parameter.
2. The remote sensing-based soil quality analysis method according to claim 1, wherein the performing soil level identification on each land type based on the DEM elevation data to obtain a soil level depth comprises:
determining a starting thickness and spatial coordinates of the land type based on the DEM elevation data;
and obtaining the soil layer depth based on the initial thickness, the space coordinates and the calculation parameters through an expansion model, wherein the soil layer depth is shown in the following formula:
H (x,y) ＝H 0 +K 1 exp(-K 2 y)
H (x,y) depth of soil layer, H 0 To start thickness, K 1 And K 2 Is a parameter, y is a spatial coordinate;
wherein the calculated parameters are determined based on machine learning by fitting verification of the expansion model.
3. The remote sensing-based soil quality analysis method according to claim 1, wherein the obtaining the soil quality parameter based on the soil influence parameter, the land type and the soil layer depth comprises:
analyzing the soil influence parameters, the land type and the soil layer depth based on a regression model to obtain the soil quality parameters, wherein the soil quality parameters are shown in the following formula:
M＝β 0 t 0 +β 1 t 1 +β 2 t 2 +β 3 t 3 +β 4 t 4 +β 5 t 5 +ε
wherein M is the soil quality parameter, t i Beta is any one of soil influence parameters, land type or soil level depth i For regression coefficients, i=0, 1, 2, 3, 4, 5, epsilon is the error term;
the regression coefficients and error terms are determined by performing a your fit verification on the regression model based on machine learning.
4. The remote sensing-based soil quality analysis method of claim 1, wherein the soil influencing parameter comprises a soil average particle diameter;
the method for determining the average particle diameter of the soil comprises the following steps:
determining the pixel area of a target image corresponding to the soil quality parameter analysis;
traversing a target parameter representing a diameter of soil particles in the soil quality parameter;
the soil average particle diameter is determined based on the target parameter and pixel area.
5. The remote sensing-based soil quality analysis method of claim 1, wherein said determining a soil quality analysis result based on said soil quality parameter comprises:
converting the soil quality parameters into standardized scores, and determining target weights corresponding to the soil quality parameters;
and carrying out weighted average on the standardized scores and the target weights to obtain the soil quality analysis result.
6. The remote sensing-based soil quality analysis method of claim 1, wherein the segmenting and recognizing the land structure image based on the image processing technique, determining land types of different land structure areas, comprises:
performing image size adjustment, gray value balance and edge detection on the land structure image to obtain a preprocessed image;
convoluting, pooling and upsampling the preprocessed image based on a first convolutional neural network model to obtain image features of the preprocessed image, and determining different land structures based on the image features;
and identifying each land structure based on a second convolutional neural network model to obtain land types of the different land structure areas.
7. The remote sensing-based soil quality analysis method of any of claims 1-6, wherein said soil influencing parameter comprises at least one of NDVI value, elevation, surface temperature, normalized water index.
8. A soil quality analysis device based on remote sensing, comprising:
the data acquisition module is used for acquiring satellite remote sensing data and DEM elevation data;
the image acquisition module is used for acquiring a land structure image based on the satellite remote sensing data;
the segmentation and identification module is used for segmenting and identifying the land structure image based on an image processing technology and determining land types of different land structure areas;
the level recognition module is used for carrying out soil level recognition on each land type based on the DEM elevation data to obtain soil level depth;
the parameter determining module is used for determining soil influence parameters based on the remote sensing data and obtaining soil quality parameters based on the soil influence parameters, the land type and the soil layer depth;
and the quality analysis module is used for determining a soil quality analysis result based on the soil quality parameter.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the remote sensing based soil quality analysis method of any one of claims 1 to 7 when the program is executed by the processor.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the remote sensing based soil quality analysis method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310893678.6A CN117115671A (en) | 2023-07-19 | 2023-07-19 | Soil quality analysis method and device based on remote sensing and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310893678.6A CN117115671A (en) | 2023-07-19 | 2023-07-19 | Soil quality analysis method and device based on remote sensing and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117115671A true CN117115671A (en) | 2023-11-24 |
Family
ID=88806382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310893678.6A Pending CN117115671A (en) | 2023-07-19 | 2023-07-19 | Soil quality analysis method and device based on remote sensing and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117115671A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118521182A (en) * | 2024-07-18 | 2024-08-20 | 烟台大学 | Homeland planning adjustment auxiliary system based on remote sensing data |
-
2023
- 2023-07-19 CN CN202310893678.6A patent/CN117115671A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118521182A (en) * | 2024-07-18 | 2024-08-20 | 烟台大学 | Homeland planning adjustment auxiliary system based on remote sensing data |
| CN118521182B (en) * | 2024-07-18 | 2024-10-18 | 烟台大学 | Homeland planning adjustment auxiliary system based on remote sensing data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111986099B (en) | Tillage monitoring method and system based on convolutional neural network with residual error correction fused | |
| Li et al. | A 30-year (1984–2013) record of annual urban dynamics of Beijing City derived from Landsat data | |
| CN110298211B (en) | River network extraction method based on deep learning and high-resolution remote sensing image | |
| Chen et al. | The application of the tasseled cap transformation and feature knowledge for the extraction of coastline information from remote sensing images | |
| CN103871039B (en) | Generation method for difference chart in SAR (Synthetic Aperture Radar) image change detection | |
| CN110991430B (en) | Ground feature identification and coverage rate calculation method and system based on remote sensing image | |
| CN113610070A (en) | Landslide disaster identification method based on multi-source data fusion | |
| CN115471467A (en) | High-resolution optical remote sensing image building change detection method | |
| Wang et al. | Hybrid model for estimating forest canopy heights using fused multimodal spaceborne LiDAR data and optical imagery | |
| CN117115671A (en) | Soil quality analysis method and device based on remote sensing and electronic equipment | |
| CN112765556A (en) | Method for evaluating tree age of new-born mangrove forest based on intensive time remote sensing data | |
| CN110991285B (en) | Method and device for extracting lake ice climate information based on MODIS optical data | |
| CN117422619A (en) | Training method of image reconstruction model, image reconstruction method, device and equipment | |
| CN116258956A (en) | Unmanned aerial vehicle tree recognition method, unmanned aerial vehicle tree recognition equipment, storage medium and unmanned aerial vehicle tree recognition device | |
| CN116612383A (en) | Landslide identification method and device based on generation of countermeasure network data expansion strategy | |
| CN107463944A (en) | A kind of road information extracting method using multidate High Resolution SAR Images | |
| CN114067205A (en) | Light-weight arbitrary-scale double-time-phase image change detection method | |
| Sui et al. | Processing of multitemporal data and change detection | |
| CN115147726B (en) | City form map generation method and device, electronic equipment and readable storage medium | |
| CN116563427A (en) | Construction year drawing method and system based on Landsat time sequence | |
| CN106339423A (en) | Method and device for dynamically updating sugarcane planting information | |
| CN116310881B (en) | Soil organic matter content estimation method and device, electronic equipment and storage medium | |
| CN117690029B (en) | Lithology recognition method, platform and medium based on automatically generated samples | |
| Chen et al. | Integrating topographic features and patch matching into point cloud restoration for terrain modelling | |
| CN115995046B (en) | Rural road remote sensing extraction method and device under shadow shielding state |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |