CN112861658A - Identification method for desertification control key area based on multi-source data - Google Patents
Identification method for desertification control key area based on multi-source data Download PDFInfo
- Publication number
- CN112861658A CN112861658A CN202110085437.XA CN202110085437A CN112861658A CN 112861658 A CN112861658 A CN 112861658A CN 202110085437 A CN202110085437 A CN 202110085437A CN 112861658 A CN112861658 A CN 112861658A
- Authority
- CN
- China
- Prior art keywords
- desertification
- vegetation
- aerial vehicle
- unmanned aerial
- area
- 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
- 238000000034 method Methods 0.000 title claims abstract description 65
- 239000002689 soil Substances 0.000 claims abstract description 74
- 239000004576 sand Substances 0.000 claims abstract description 71
- 230000003628 erosive effect Effects 0.000 claims abstract description 11
- 238000011160 research Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 239000002028 Biomass Substances 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 238000011946 reduction process Methods 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000011835 investigation Methods 0.000 abstract description 4
- 239000000126 substance Substances 0.000 abstract description 3
- 238000003556 assay Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 235000015784 Artemisia rupestris Nutrition 0.000 description 2
- 241001670235 Artemisia rupestris Species 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 235000015759 Artemisia selengensis Nutrition 0.000 description 1
- 241001168877 Artemisia selengensis Species 0.000 description 1
- 244000025254 Cannabis sativa Species 0.000 description 1
- 241000223025 Caragana microphylla Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 241001520921 Leersia virginica Species 0.000 description 1
- 241001210452 Medicago ruthenica Species 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a desertification control key area identification method based on multi-source data, which comprises the following steps: the method comprises the following steps: the method comprises the following steps of firstly, dividing a desert into regions, and collecting and shooting vegetation in the desert of each divided region by using an unmanned aerial vehicle with a collecting function and a shooting function; step two: the unmanned aerial vehicle recovers the vegetation and the soil in a plurality of areas after collecting the vegetation and the soil; step three: scanning and analyzing vegetation and soil collected by the unmanned aerial vehicle by using an analyzer, and displaying the condition of the desert area; through using unmanned aerial vehicle to gather the vegetation in the desert area, retrieve the vegetation that unmanned aerial vehicle gathered and carry out chemical examination and processing to unmanned aerial vehicle after, through the simplification that the assay machine and use microscope observation vegetation constitute, and the coarsening that native soil is buried and arouses by wind erosion or sand, through using vegetation and the soil in unmanned aerial vehicle gathering desert, practiced thrift the time of artifical investigation desert, effectively improved staff's work efficiency.
Description
Technical Field
The invention relates to the technical field of area identification, in particular to a desertification control key area identification method based on multi-source data.
Background
Desertification is a natural (unnatural) phenomenon in which the productivity of large pieces of soil is reduced or lost due to factors such as drought, rain, vegetation damage, strong wind erosion, running water erosion, soil salinization and the like. It has a narrow and broad meaning, originated in the late 60 and early 70 of the 20 th century, and in the sub-saharan areas of africa, with severe drought in successive years, leading to unprecedented disasters, and the term "desertification" has come into play. The final result of desertification is mostly desertification, and the research on the interrelation of desertification and natural and human activity factors is one of the main core problems of the current desertification research. Particularly on a regional scale, how to scientifically and accurately describe desertification is the most critical. Because natural factors (such as wind, precipitation, temperature, vegetation coverage, etc.) and human activity intensity (such as population density, reclamation index, stock carrying capacity, artificial forest and grass area, etc.) are often expressed in the form of quantitative quantities, the quantification of desertification on a regional scale is relatively confused in past studies. The main points are as follows: the expression definition of the desertification degree and the desertification process is unclear; the regional desertification features are described by the total area of desertified (or desertified) land by the changes of a moving dune, a semi-fixed dune and a fixed dune respectively, and the heterogeneity of the desertified (desertified) land is ignored:
firstly, in the existing desertification control key area identification method, mostly, the desert environment is investigated manually, and the investigation result is analyzed to judge the environmental desertification degree;
in addition, the existing desertification control key area identification method needs more time and wastes time and labor for investigation due to larger environment area;
and finally, the existing desertification control key area identification method judges the desertification degree only through analysis of workers and comparison of some data, the comparison data is not comprehensive enough, and the accuracy of the data result is not high.
Disclosure of Invention
The invention aims to provide a desertification control key area identification method based on multi-source data, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a desertification control key area identification method based on multi-source data comprises the following steps:
the method comprises the following steps: the method comprises the following steps of firstly, dividing a desert into regions, and collecting and shooting vegetation in the desert of each divided region by using an unmanned aerial vehicle with a collecting function and a shooting function;
step two: the unmanned aerial vehicle recovers the vegetation and the soil in a plurality of areas after collecting the vegetation and the soil;
step three: scanning and analyzing vegetation and soil collected by the unmanned aerial vehicle by using an analyzer, and displaying the condition of the desert area;
step four: and classifying the images according to the characteristic parameters, and calculating the area to be treated according to the classification result.
As a further scheme of the invention: the unmanned aerial vehicle of step one is controlled through the staff, descends near the vegetation of desert area and gathers to place the vegetation and the soil of gathering in special holding box.
As a still further scheme of the invention: and after the unmanned aerial vehicle in the second step collects one area, the unmanned aerial vehicle is controlled by the staff again to go to the next area, and after all the vegetations and soil in all the divided areas are collected by the unmanned aerial vehicle, the unmanned aerial vehicle is recovered.
As a still further scheme of the invention: in the third step, the vegetation and the soil in the special storage box in the unmanned aerial vehicle are placed on an analyzer for analyzing the attributes and analyzing the change of the soil and the vegetation, and for the primary soil and the vegetation in a certain area, the process of coarsening the soil, the simplification of vegetation composition and the reduction process of aboveground biomass caused by wind erosion or sand burying are the desertification process.
As a still further scheme of the invention: in the third step, the pictures shot by the unmanned aerial vehicle are analyzed, and the land desertification stage is classified as follows: a potential desertification stage, a mild desertification stage, a moderate desertification stage, and a severe desertification stage.
As a still further scheme of the invention: and the analyzer in the fourth step arranges the analyzed information out to be displayed on a display, so that the information can be conveniently watched by the staff.
As a still further scheme of the invention: a training unit is arranged in the analyzer in the third step and is used for comparing pictures shot by the unmanned aerial vehicle, dividing the pictures and comparing classifiers of different types of pictures by using an SVM classifier, a KNN classifier, a RandomForest classifier or a Bayesian classifier;
and the identification unit is used for distinguishing the desert images, comparing the distinguishing results of the classifiers of the desert images of different types, and then sorting and dividing the desert conditions in all the areas.
As a still further scheme of the invention: the unmanned aerial vehicle in the first step comprises;
a picture transmission unit; the system is used for transmitting the collected pictures to the staff;
a feature extraction unit; and obtaining the local characteristics of the vegetation sampling points.
As a still further scheme of the invention: calculating the desertification degree of different areas by using an analysis machine, wherein the desertification degree is defined as: DG ═ (M; + h, SM; + k, F;)/Ai, where DG; the degree of desertification in the research area; m; the area of a sand dune flowing in a research area; SM, semi-fixed dune area; f; the area of the sand dune is fixed; ai is the total area of the zone; i is a certain time period; k and k are undetermined weight factors; the value of DG is changed between 0 and 1, namely: no sand dune-like type M exists in a certain region; SM; and F are both o, the desertification degree of the area is 0; if the sand dune types in the region are all moving sand dunes, then Ai is equal to M; SM, and F; if the value is o, the desertification degree is 1;
the definition has two characteristics, one is that the weight of the moving dune F is determined to be 1, and the other is that the weight of the semi-fixed dune SM and the fixed dune F are undetermined; the third is the calculated range of k-O and h-k 2-1.
As a still further scheme of the invention: the case of F ═ SM is almost impossible to occur in practical desertification studies, but it is a special case in the h-value curve; when the areas of the fixed sand dune land and the semi-fixed sand dune land are equal, the k value curve change trends of the F and the SM are completely consistent; meanwhile, it is also obvious that the k value curve when k is 0.6 is higher than the h value curve when k is 0.3, which indicates that the two curves have the same trend but different degrees; and step four, calculating the area to be treated according to the results of the analysis machine.
Compared with the prior art, the invention has the beneficial effects that:
1. through using unmanned aerial vehicle to gather the vegetation in the desert area, retrieve the vegetation that unmanned aerial vehicle gathered and carry out chemical examination and processing to unmanned aerial vehicle after, through the simplification that the assay machine and use microscope observation vegetation constitute, and the coarsening that native soil is buried and arouses by wind erosion or sand, through using vegetation and the soil in unmanned aerial vehicle gathering desert, practiced thrift the time of artifical investigation desert, effectively improved staff's work efficiency.
2. Through using unmanned aerial vehicle to shoot the desert picture, and give the analysis machine for the picture, the analysis machine divides the picture, with SVM classifier, KNN classifier, random forest classifier or Bayesian classifier to the different grade type picture contrast, calculate the desertification area of different degrees, later form the proportion again and feed back the staff with the information, through chemical examination to vegetation inside composition content in the desert and use the analysis machine analysis to shoot the picture, the accuracy of data has effectively been strengthened.
3. The pictures shot by the unmanned aerial vehicle are processed by the analysis machine, the desertification degree is calculated, the k value is calculated, the image of the k value is drawn, the k value curve reflects the desertification degree, and therefore the k value is influenced to be determined possibly, wherein SM is greater than F, SM, F is greater than SM, and SM is less than F. Assuming that the areas of the land occupied by the fixed sand dune land, the semi-fixed sand dune land and the mobile sand dune land in a certain area are 0.262, 0.102 and 0.303 respectively, the weights of the fixed sand dune land and the semi-fixed sand dune land are k 1-0.6 and k 2-0.3 respectively, the k-value curve has the characteristics that the areas of the fixed sand dune and the semi-fixed sand dune are equal, the area of the semi-fixed sand dune is larger than that of the fixed sand dune or the area of the fixed sand dune is larger than that of the semi-fixed sand dune.
4. By analyzing the pictures with the analyzer, the situation of F ═ SM in the actual desertification study is almost impossible to occur, but it is k: a particular example of a value curve is given by F SM 0.233. The result shows that the h value curve change trends of F and SM are completely consistent under the condition that the areas of the fixed sand dune land and the semi-fixed sand dune land are equal; it is also clear that the k value curve is higher when k is 0.6 than when k is constant, indicating that the two curves have the same trend but different degrees.
5. The result of analyzing the soil is compared with the results of other areas through the analyzer, and then the result is changed into data to be fed back to the working personnel, and the working personnel can effectively know the key area of the desert needing to be controlled by comparing the data of analyzing the soil in the desert with the data of the content in the vegetation with global big data.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a desertification control key area identification method based on multi-source data, which comprises the following steps:
the method comprises the following steps: the method comprises the following steps of firstly, dividing a desert into regions, and collecting and shooting vegetation in the desert of each divided region by using an unmanned aerial vehicle with a collecting function and a shooting function;
step two: the unmanned aerial vehicle recovers the vegetation and the soil in a plurality of areas after collecting the vegetation and the soil;
step three: scanning and analyzing vegetation and soil collected by the unmanned aerial vehicle by using an analyzer, and displaying the condition of the desert area;
step four: and classifying the images according to the characteristic parameters, and calculating the area to be treated according to the classification result.
Preferably, the unmanned aerial vehicle of step one is controlled through the staff, descends to near the vegetation of desert area and gathers to place the special case of preserving in vegetation and the soil that will gather.
Preferably, after the unmanned aerial vehicle in the second step collects one area, the unmanned aerial vehicle is controlled by the staff again to go to the next area, and after all the vegetation and the soil in all the divided areas are collected by the unmanned aerial vehicle, the unmanned aerial vehicle is recovered.
Preferably, in the third step, the vegetation and the soil in the special storage box in the unmanned aerial vehicle are placed on an analyzer for analyzing the attributes and analyzing the change of the soil and the vegetation, and for the native soil and the vegetation in a certain area, the process of coarsening the soil, the simplification of the vegetation composition and the reduction process of the aboveground biomass caused by wind erosion or sand burying are the desertification process.
Preferably, in the third step, the images shot by the unmanned aerial vehicle are analyzed, and the land desertification stage is classified as: a potential desertification stage, a mild desertification stage, a moderate desertification stage, and a severe desertification stage.
Preferably, the analyzer in the fourth step sorts out the analyzed information and displays the information on a display, so that the information is convenient for the staff to watch.
Preferably, a training unit is arranged in the analyzer in the third step and is used for comparing pictures shot by the unmanned aerial vehicle, dividing the pictures, and comparing classifiers of different types of pictures by using an SVM classifier, a KNN classifier, a RandomForest classifier or a Bayesian classifier;
and the identification unit is used for distinguishing the desert images, comparing the distinguishing results of the classifiers of the desert images of different types, and then sorting and dividing the desert conditions in all the areas.
Preferably, the first step is performed without a robot;
a picture transmission unit; the system is used for transmitting the collected pictures to the staff;
a feature extraction unit; and obtaining the local characteristics of the vegetation sampling points.
Preferably, the degree of desertification of the different regions is calculated by using an analyzer, and the degree of desertification is defined as: DG ═ (M; + h, SM; + k, F;)/Ai, where DG; the degree of desertification in the research area; m; the area of a sand dune flowing in a research area; SM, semi-fixed dune area; f; the area of the sand dune is fixed; ai is the total area of the zone; i is a certain time period; k and k are undetermined weight factors; the value of DG is changed between 0 and 1, namely: no sand dune-like type M exists in a certain region; SM; and F are both o, the desertification degree of the area is 0; if the sand dune types in the region are all moving sand dunes, then Ai is equal to M; SM, and F; if the value is o, the desertification degree is 1;
the definition has two characteristics, one is that the weight of the moving dune F is determined to be 1, and the other is that the weight of the semi-fixed dune SM and the fixed dune F are undetermined; the third is the calculated range of k-O and h-k 2-1.
Preferably, the case of F ═ SM is almost impossible to occur in actual desertification studies, but it is a special case in the h-value curve; when the areas of the fixed sand dune land and the semi-fixed sand dune land are equal, the k value curve change trends of the F and the SM are completely consistent; it is also clear that the k-value curve is higher when k is 0.6 than when k is 0.3, indicating that the two curves have the same trend but different degrees.
Preferably, the area to be treated is calculated according to the result of the analysis machine example in the fourth step.
Example 1
A desertification control key area identification method based on multi-source data comprises the following steps:
the method comprises the following steps: the method comprises the following steps of firstly, dividing a desert into regions, and collecting and shooting vegetation in the desert of each divided region by using an unmanned aerial vehicle with a collecting function and a shooting function;
step two: the unmanned aerial vehicle recovers the vegetation and the soil in a plurality of areas after collecting the vegetation and the soil;
step three: scanning and analyzing vegetation and soil collected by the unmanned aerial vehicle by using an analyzer, and displaying the condition of the desert area;
step four: and classifying the images according to the characteristic parameters, and calculating the area to be treated according to the classification result.
Preferably, the unmanned aerial vehicle of step one is controlled through the staff, descends to near the vegetation of desert area and gathers to place the special case of preserving in vegetation and the soil that will gather.
Preferably, after the unmanned aerial vehicle in the second step collects one area, the unmanned aerial vehicle is controlled by the staff again to go to the next area, and after all the vegetation and the soil in all the divided areas are collected by the unmanned aerial vehicle, the unmanned aerial vehicle is recovered.
Preferably, in the third step, the vegetation and the soil in the special storage box in the unmanned aerial vehicle are placed on an analyzer for analyzing the attributes and analyzing the change of the soil and the vegetation, and for the native soil and the vegetation in a certain area, the process of coarsening the soil, the simplification of the vegetation composition and the reduction process of the aboveground biomass caused by wind erosion or sand burying are the desertification process.
Preferably, in the third step, the images shot by the unmanned aerial vehicle are analyzed, and the land desertification stage is classified as: a potential desertification stage, a mild desertification stage, a moderate desertification stage, and a severe desertification stage.
Preferably, the analyzer in the fourth step sorts out the analyzed information and displays the information on a display, so that the information is convenient for the staff to watch.
Preferably, a training unit is arranged in the analyzer in the third step and is used for comparing pictures shot by the unmanned aerial vehicle, dividing the pictures, and comparing classifiers of different types of pictures by using an SVM classifier, a KNN classifier, a RandomForest classifier or a Bayesian classifier;
and the identification unit is used for distinguishing the desert images, comparing the distinguishing results of the classifiers of the desert images of different types, and then sorting and dividing the desert conditions in all the areas.
Preferably, the first step is performed without a robot;
a picture transmission unit; the system is used for transmitting the collected pictures to the staff;
a feature extraction unit; and obtaining the local characteristics of the vegetation sampling points.
Preferably, the degree of desertification of the different regions is calculated by using an analyzer, and the degree of desertification is defined as: DG ═ (M; + h, SM; + k, F;)/Ai, where DG; the degree of desertification in the research area; m; the area of a sand dune flowing in a research area; SM, semi-fixed dune area; f; the area of the sand dune is fixed; ai is the total area of the zone; i is a certain time period; k and k are undetermined weight factors; the value of DG is changed between 0 and 1, namely: no sand dune-like type M exists in a certain region; SM; and F are both o, the desertification degree of the area is 0; if the sand dune types in the region are all moving sand dunes, then Ai is equal to M; SM, and F; if the value is o, the desertification degree is 1;
the definition has two characteristics, one is that the weight of the moving dune F is determined to be 1, and the other is that the weight of the semi-fixed dune SM and the fixed dune F are undetermined; the third is the calculated range of k-O and h-k 2-1.
Preferably, the case of F ═ SM is almost impossible to occur in actual desertification studies, but it is a special case in the h-value curve; when the areas of the fixed sand dune land and the semi-fixed sand dune land are equal, the k value curve change trends of the F and the SM are completely consistent; it is also clear that the k-value curve is higher when k is 0.6 than when k is 0.3, indicating that the two curves have the same trend but different degrees.
Preferably, the area to be treated is calculated according to the result of the analysis machine example in the step four, when the measured vegetation coverage accounts for 50% -99% of the desertification degree, the land is a potential desertification stage, and caragana microphylla, cryptospermum japonicum and artemisia selengensis can be planted for treatment.
Example 2
A desertification control key area identification method based on multi-source data comprises the following steps:
the method comprises the following steps: the method comprises the following steps of firstly, dividing a desert into regions, and collecting and shooting vegetation in the desert of each divided region by using an unmanned aerial vehicle with a collecting function and a shooting function;
step two: the unmanned aerial vehicle recovers the vegetation and the soil in a plurality of areas after collecting the vegetation and the soil;
step three: scanning and analyzing vegetation and soil collected by the unmanned aerial vehicle by using an analyzer, and displaying the condition of the desert area;
step four: and classifying the images according to the characteristic parameters, and calculating the area to be treated according to the classification result.
Preferably, the unmanned aerial vehicle of step one is controlled through the staff, descends to near the vegetation of desert area and gathers to place the special case of preserving in vegetation and the soil that will gather.
Preferably, after the unmanned aerial vehicle in the second step collects one area, the unmanned aerial vehicle is controlled by the staff again to go to the next area, and after all the vegetation and the soil in all the divided areas are collected by the unmanned aerial vehicle, the unmanned aerial vehicle is recovered.
Preferably, in the third step, the vegetation and the soil in the special storage box in the unmanned aerial vehicle are placed on an analyzer for analyzing the attributes and analyzing the change of the soil and the vegetation, and for the native soil and the vegetation in a certain area, the process of coarsening the soil, the simplification of the vegetation composition and the reduction process of the aboveground biomass caused by wind erosion or sand burying are the desertification process.
Preferably, in the third step, the images shot by the unmanned aerial vehicle are analyzed, and the land desertification stage is classified as: a potential desertification stage, a mild desertification stage, a moderate desertification stage, and a severe desertification stage.
Preferably, the analyzer in the fourth step sorts out the analyzed information and displays the information on a display, so that the information is convenient for the staff to watch.
Preferably, a training unit is arranged in the analyzer in the third step and is used for comparing pictures shot by the unmanned aerial vehicle, dividing the pictures, and comparing classifiers of different types of pictures by using an SVM classifier, a KNN classifier, a RandomForest classifier or a Bayesian classifier;
and the identification unit is used for distinguishing the desert images, comparing the distinguishing results of the classifiers of the desert images of different types, and then sorting and dividing the desert conditions in all the areas.
Preferably, the first step is performed without a robot;
a picture transmission unit; the system is used for transmitting the collected pictures to the staff;
a feature extraction unit; and obtaining the local characteristics of the vegetation sampling points.
Preferably, the degree of desertification of the different regions is calculated by using an analyzer, and the degree of desertification is defined as: DG ═ (M; + h, SM; + k, F;)/Ai, where DG; the degree of desertification in the research area; m; the area of a sand dune flowing in a research area; SM, semi-fixed dune area; f; the area of the sand dune is fixed; ai is the total area of the zone; i is a certain time period; k and k are undetermined weight factors; the value of DG is changed between 0 and 1, namely: no sand dune-like type M exists in a certain region; SM; and F are both o, the desertification degree of the area is 0; if the sand dune types in the region are all moving sand dunes, then Ai is equal to M; SM, and F; if the value is o, the desertification degree is 1;
the definition has two characteristics, one is that the weight of the moving dune F is determined to be 1, and the other is that the weight of the semi-fixed dune SM and the fixed dune F are undetermined; the third is the calculated range of k-O and h-k 2-1.
Preferably, the case of F ═ SM is almost impossible to occur in actual desertification studies, but it is a special case in the h-value curve; when the areas of the fixed sand dune land and the semi-fixed sand dune land are equal, the k value curve change trends of the F and the SM are completely consistent; it is also clear that the k-value curve is higher when k is 0.6 than when k is 0.3, indicating that the two curves have the same trend but different degrees.
Preferably, the area to be treated is calculated according to the result of the analysis machine example in the fourth step, when the measured vegetation coverage accounts for 30-50% of the desertification degree, the land is in a light desertification stage and can be treated by planting Melissitus ruthenicus seeds and artemisia rupestris.
Example 3
A desertification control key area identification method based on multi-source data comprises the following steps:
the method comprises the following steps: the method comprises the following steps of firstly, dividing a desert into regions, and collecting and shooting vegetation in the desert of each divided region by using an unmanned aerial vehicle with a collecting function and a shooting function;
step two: the unmanned aerial vehicle recovers the vegetation and the soil in a plurality of areas after collecting the vegetation and the soil;
step three: scanning and analyzing vegetation and soil collected by the unmanned aerial vehicle by using an analyzer, and displaying the condition of the desert area;
step four: and classifying the images according to the characteristic parameters, and calculating the area to be treated according to the classification result.
Preferably, the unmanned aerial vehicle of step one is controlled through the staff, descends to near the vegetation of desert area and gathers to place the special case of preserving in vegetation and the soil that will gather.
Preferably, after the unmanned aerial vehicle in the second step collects one area, the unmanned aerial vehicle is controlled by the staff again to go to the next area, and after all the vegetation and the soil in all the divided areas are collected by the unmanned aerial vehicle, the unmanned aerial vehicle is recovered.
Preferably, in the third step, the vegetation and the soil in the special storage box in the unmanned aerial vehicle are placed on an analyzer for analyzing the attributes and analyzing the change of the soil and the vegetation, and for the native soil and the vegetation in a certain area, the process of coarsening the soil, the simplification of the vegetation composition and the reduction process of the aboveground biomass caused by wind erosion or sand burying are the desertification process.
Preferably, in the third step, the images shot by the unmanned aerial vehicle are analyzed, and the land desertification stage is classified as: a potential desertification stage, a mild desertification stage, a moderate desertification stage, and a severe desertification stage.
Preferably, the analyzer in the fourth step sorts out the analyzed information and displays the information on a display, so that the information is convenient for the staff to watch.
Preferably, a training unit is arranged in the analyzer in the third step and is used for comparing pictures shot by the unmanned aerial vehicle, dividing the pictures, and comparing classifiers of different types of pictures by using an SVM classifier, a KNN classifier, a RandomForest classifier or a Bayesian classifier;
and the identification unit is used for distinguishing the desert images, comparing the distinguishing results of the classifiers of the desert images of different types, and then sorting and dividing the desert conditions in all the areas.
Preferably, the first step is performed without a robot;
a picture transmission unit; the system is used for transmitting the collected pictures to the staff;
a feature extraction unit; and obtaining the local characteristics of the vegetation sampling points.
Preferably, the degree of desertification of the different regions is calculated by using an analyzer, and the degree of desertification is defined as: DG ═ (M; + h, SM; + k, F;)/Ai, where DG; the degree of desertification in the research area; m; the area of a sand dune flowing in a research area; SM, semi-fixed dune area; f; the area of the sand dune is fixed; ai is the total area of the zone; i is a certain time period; k and k are undetermined weight factors; the value of DG is changed between 0 and 1, namely: no sand dune-like type M exists in a certain region; SM; and F are both o, the desertification degree of the area is 0; if the sand dune types in the region are all moving sand dunes, then Ai is equal to M; SM, and F; if the value is o, the desertification degree is 1;
the definition has two characteristics, one is that the weight of the moving dune F is determined to be 1, and the other is that the weight of the semi-fixed dune SM and the fixed dune F are undetermined; the third is the calculated range of k-O and h-k 2-1.
Preferably, the case of F ═ SM is almost impossible to occur in actual desertification studies, but it is a special case in the h-value curve; when the areas of the fixed sand dune land and the semi-fixed sand dune land are equal, the k value curve change trends of the F and the SM are completely consistent; it is also clear that the k-value curve is higher when k is 0.6 than when k is 0.3, indicating that the two curves have the same trend but different degrees.
Preferably, the area to be treated is calculated according to the result of the example of the analyzer in the fourth step, and when the measured vegetation coverage accounts for 10-30% of the desertification degree, the land is in a moderate desertification stage and can be treated by artemisia rupestris and white grass.
Example 4
A desertification control key area identification method based on multi-source data comprises the following steps:
the method comprises the following steps: the method comprises the following steps of firstly, dividing a desert into regions, and collecting and shooting vegetation in the desert of each divided region by using an unmanned aerial vehicle with a collecting function and a shooting function;
step two: the unmanned aerial vehicle recovers the vegetation and the soil in a plurality of areas after collecting the vegetation and the soil;
step three: scanning and analyzing vegetation and soil collected by the unmanned aerial vehicle by using an analyzer, and displaying the condition of the desert area;
step four: and classifying the images according to the characteristic parameters, and calculating the area to be treated according to the classification result.
Preferably, the unmanned aerial vehicle of step one is controlled through the staff, descends to near the vegetation of desert area and gathers to place the special case of preserving in vegetation and the soil that will gather.
Preferably, after the unmanned aerial vehicle in the second step collects one area, the unmanned aerial vehicle is controlled by the staff again to go to the next area, and after all the vegetation and the soil in all the divided areas are collected by the unmanned aerial vehicle, the unmanned aerial vehicle is recovered.
Preferably, in the third step, the vegetation and the soil in the special storage box in the unmanned aerial vehicle are placed on an analyzer for analyzing the attributes and analyzing the change of the soil and the vegetation, and for the native soil and the vegetation in a certain area, the process of coarsening the soil, the simplification of the vegetation composition and the reduction process of the aboveground biomass caused by wind erosion or sand burying are the desertification process.
Preferably, in the third step, the images shot by the unmanned aerial vehicle are analyzed, and the land desertification stage is classified as: a potential desertification stage, a mild desertification stage, a moderate desertification stage, and a severe desertification stage.
Preferably, the analyzer in the fourth step sorts out the analyzed information and displays the information on a display, so that the information is convenient for the staff to watch.
Preferably, a training unit is arranged in the analyzer in the third step and is used for comparing pictures shot by the unmanned aerial vehicle, dividing the pictures, and comparing classifiers of different types of pictures by using an SVM classifier, a KNN classifier, a RandomForest classifier or a Bayesian classifier;
and the identification unit is used for distinguishing the desert images, comparing the distinguishing results of the classifiers of the desert images of different types, and then sorting and dividing the desert conditions in all the areas.
Preferably, the first step is performed without a robot;
a picture transmission unit; the system is used for transmitting the collected pictures to the staff;
a feature extraction unit; and obtaining the local characteristics of the vegetation sampling points.
Preferably, the degree of desertification of the different regions is calculated by using an analyzer, and the degree of desertification is defined as: DG ═ (M; + h, SM; + k, F;)/Ai, where DG; the degree of desertification in the research area; m; the area of a sand dune flowing in a research area; SM, semi-fixed dune area; f; the area of the sand dune is fixed; ai is the total area of the zone; i is a certain time period; k and k are undetermined weight factors; the value of DG is changed between 0 and 1, namely: no sand dune-like type M exists in a certain region; SM; and F are both o, the desertification degree of the area is 0; if the sand dune types in the region are all moving sand dunes, then Ai is equal to M; SM, and F; if the value is o, the desertification degree is 1;
the definition has two characteristics, one is that the weight of the moving dune F is determined to be 1, and the other is that the weight of the semi-fixed dune SM and the fixed dune F are undetermined; the third is the calculated range of k-O and h-k 2-1.
Preferably, the case of F ═ SM is almost impossible to occur in actual desertification studies, but it is a special case in the h-value curve; when the areas of the fixed sand dune land and the semi-fixed sand dune land are equal, the k value curve change trends of the F and the SM are completely consistent; it is also clear that the k-value curve is higher when k is 0.6 than when k is 0.3, indicating that the two curves have the same trend but different degrees.
Preferably, the area to be treated is calculated according to the result of the example of the analyzer in the fourth step, and when the measured vegetation coverage accounts for less than 10% of the desertification degree, the land is in a severe desertification stage and can be treated by planting husked rice.
According to the measuring result; the vegetation coverage determines the land desertification degree, and the potential desertification stage is that the vegetation coverage is more than 50 percent; the vegetation coverage is between 30 and 50 percent, and is in a mild desertification stage; the vegetation coverage is in a moderate desertification stage between 10% and 30%; when the vegetation coverage is less than 10%, the vegetation coverage is in a severe desertification stage, and different dominant plant species can be planted to have different desertification degrees to improve the vegetation coverage.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that various changes in the embodiments and/or modifications of the invention can be made, and equivalents and modifications of some features of the invention can be made without departing from the spirit and scope of the invention.
Claims (10)
1. A desertification control key area identification method based on multi-source data is characterized in that: the method comprises the following steps:
the method comprises the following steps: the method comprises the following steps of firstly, dividing a desert into regions, and collecting and shooting vegetation in the desert of each divided region by using an unmanned aerial vehicle with a collecting function and a shooting function;
step two: the unmanned aerial vehicle recovers the vegetation and the soil in a plurality of areas after collecting the vegetation and the soil;
step three: scanning and analyzing vegetation and soil collected by the unmanned aerial vehicle by using an analyzer, and displaying the condition of the desert area;
step four: and classifying the images according to the characteristic parameters, and calculating the area to be treated according to the classification result.
2. The method for identifying the desertification control key area based on the multi-source data as claimed in claim 1, wherein the method comprises the following steps: the unmanned aerial vehicle of step one is controlled through the staff, descends near the vegetation of desert area and gathers to place the vegetation and the soil of gathering in special holding box.
3. The method for identifying the desertification control key area based on the multi-source data as claimed in claim 1, wherein the method comprises the following steps: and after the unmanned aerial vehicle in the second step collects one area, the unmanned aerial vehicle is controlled by the staff again to go to the next area, and after all the vegetations and soil in all the divided areas are collected by the unmanned aerial vehicle, the unmanned aerial vehicle is recovered.
4. The method for identifying the desertification control key area based on the multi-source data as claimed in claim 1, wherein the method comprises the following steps: in the third step, the vegetation and the soil in the special storage box in the unmanned aerial vehicle are placed on an analyzer for analyzing the attributes and analyzing the change of the soil and the vegetation, and for the primary soil and the vegetation in a certain area, the process of coarsening the soil, the simplification of vegetation composition and the reduction process of aboveground biomass caused by wind erosion or sand burying are the desertification process.
5. The method for identifying the desertification control key area based on the multi-source data as claimed in claim 1, wherein the method comprises the following steps: in the third step, the pictures shot by the unmanned aerial vehicle are analyzed, and the land desertification stage is classified as follows: a potential desertification stage, a mild desertification stage, a moderate desertification stage, and a severe desertification stage.
6. The method for identifying the desertification control key area based on the multi-source data as claimed in claim 1, wherein the method comprises the following steps: and the analyzer in the fourth step arranges the analyzed information out to be displayed on a display, so that the information can be conveniently watched by the staff.
7. The method for identifying the desertification control key area based on the multi-source data as claimed in claim 1, wherein the method comprises the following steps: a training unit is arranged in the analyzer in the third step and is used for comparing pictures shot by the unmanned aerial vehicle, dividing the pictures and comparing classifiers of different types of pictures by using an SVM classifier, a KNN classifier, a RandomForest classifier or a Bayesian classifier;
and the identification unit is used for distinguishing the desert images, comparing the distinguishing results of the classifiers of the desert images of different types, and then sorting and dividing the desert conditions in all the areas.
8. The method for identifying the desertification control key area based on the multi-source data as claimed in claim 1, wherein the method comprises the following steps: the unmanned aerial vehicle in the first step comprises;
a picture transmission unit; the system is used for transmitting the collected pictures to the staff;
a feature extraction unit; and obtaining the local characteristics of the vegetation sampling points.
9. The method for identifying the desertification control key area based on the multi-source data as claimed in claim 1, wherein the method comprises the following steps: calculating the desertification degree of different areas by using an analysis machine, wherein the desertification degree is defined as: DG ═ (M; + h, SM; + k, F;)/Ai, where DG; the degree of desertification in the research area; m; the area of a sand dune flowing in a research area; SM, semi-fixed dune area; f; the area of the sand dune is fixed; ai is the total area of the zone; i is a certain time period; k and k are undetermined weight factors; the value of DG is changed between 0 and 1, namely: no sand dune-like type M exists in a certain region; SM; and F are both o, the desertification degree of the area is 0; if the sand dune types in the region are all moving sand dunes, then Ai is equal to M; SM, and F; if the value is o, the desertification degree is 1;
the definition has two characteristics, one is that the weight of the moving dune F is determined to be 1, and the other is that the weight of the semi-fixed dune SM and the fixed dune F are undetermined; the third is the calculated range of k-O and h-k 2-1.
10. The method for identifying the desertification control key area based on the multi-source data according to claim 9, wherein the method comprises the following steps: the case of F ═ SM is almost impossible to occur in practical desertification studies, but it is a special case in the h-value curve; when the areas of the fixed sand dune land and the semi-fixed sand dune land are equal, the k value curve change trends of the F and the SM are completely consistent; meanwhile, it is also obvious that the k value curve when k is 0.6 is higher than the h value curve when k is 0.3, which indicates that the two curves have the same trend but different degrees; and step four, calculating the area to be treated according to the results of the analysis machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110085437.XA CN112861658A (en) | 2021-01-14 | 2021-01-14 | Identification method for desertification control key area based on multi-source data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110085437.XA CN112861658A (en) | 2021-01-14 | 2021-01-14 | Identification method for desertification control key area based on multi-source data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112861658A true CN112861658A (en) | 2021-05-28 |
Family
ID=76007705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110085437.XA Pending CN112861658A (en) | 2021-01-14 | 2021-01-14 | Identification method for desertification control key area based on multi-source data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112861658A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116468311A (en) * | 2023-03-30 | 2023-07-21 | 中国科学院西北生态环境资源研究院 | Method for monitoring and evaluating desertification by using earth arthropod |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106403904A (en) * | 2016-10-19 | 2017-02-15 | 中国林业科学研究院 | Landscape-scale vegetation coverage calculation method and system based on unmanned aerial vehicle |
| CN108053072A (en) * | 2017-12-22 | 2018-05-18 | 中国科学院地理科学与资源研究所 | The structure of desertification dynamic simulation model and application |
| CN108152071A (en) * | 2017-12-15 | 2018-06-12 | 佛山市神风航空科技有限公司 | A kind of unmanned plane desert and Gobi soil sampling system |
| US20180364157A1 (en) * | 2017-06-19 | 2018-12-20 | Dinamica Generale S.P.A. | Self-propelled apparatus for optimally analysing and managing fields intended for agricultural cultivation |
| AU2020101054A4 (en) * | 2020-06-19 | 2020-07-30 | Guizhou Institute Of Pratacultural | A Multi-source Remote Sensing Data Classification Method Based On the Classification Sample Points Extracted By the UAV |
-
2021
- 2021-01-14 CN CN202110085437.XA patent/CN112861658A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106403904A (en) * | 2016-10-19 | 2017-02-15 | 中国林业科学研究院 | Landscape-scale vegetation coverage calculation method and system based on unmanned aerial vehicle |
| US20180364157A1 (en) * | 2017-06-19 | 2018-12-20 | Dinamica Generale S.P.A. | Self-propelled apparatus for optimally analysing and managing fields intended for agricultural cultivation |
| CN108152071A (en) * | 2017-12-15 | 2018-06-12 | 佛山市神风航空科技有限公司 | A kind of unmanned plane desert and Gobi soil sampling system |
| CN108053072A (en) * | 2017-12-22 | 2018-05-18 | 中国科学院地理科学与资源研究所 | The structure of desertification dynamic simulation model and application |
| AU2020101054A4 (en) * | 2020-06-19 | 2020-07-30 | Guizhou Institute Of Pratacultural | A Multi-source Remote Sensing Data Classification Method Based On the Classification Sample Points Extracted By the UAV |
Non-Patent Citations (3)
| Title |
|---|
| DANIEL SOLAZZO ET AL.: "Mapping and measuring aeolian sand dunes with photogrammetry and LiDAR from unmanned aerial vehicles (UAV) and multispectral satellite imagery on the Paria Plateau, AZ, USA", GEOMORPHOLOGY, 15 October 2018 (2018-10-15) * |
| DUANFANG XU ET AL.: "Multi‐scenario simulation of desertification in North China for 2030", WILEY, 15 August 2020 (2020-08-15) * |
| 陈昂: ""基于Google Earth Engine与无人机影像的沙漠化信息提取--以内蒙古正蓝旗为例"", 万方数据库, 6 November 2020 (2020-11-06), pages 1 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116468311A (en) * | 2023-03-30 | 2023-07-21 | 中国科学院西北生态环境资源研究院 | Method for monitoring and evaluating desertification by using earth arthropod |
| CN116468311B (en) * | 2023-03-30 | 2024-02-27 | 中国科学院西北生态环境资源研究院 | Method for monitoring and evaluating desertification by using earth arthropod |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | A remote sensing and GIS integrated study on urbanization with its impact on arable lands: Fuqing City, Fujian Province, China | |
| Pausas et al. | Modelling habitat quality for arboreal marsupials in the south coastal forests of New South Wales, Australia | |
| Bonneau et al. | Using satellite images to classify and analyze the health of hemlock forests infested by the hemlock woolly adelgid | |
| CN107464035A (en) | Chinese medicine performance rating method and system | |
| Seydack et al. | An unconventional approach to timber yield regulation for multi-aged, multispecies forests. II. Application to a South African forest | |
| CN113192026A (en) | Walnut maturity detection and prediction method based on visible light image | |
| Dos Santos et al. | Estimating babassu palm density using automatic palm tree detection with very high spatial resolution satellite images | |
| Aplin et al. | Predicting missing field boundaries to increase per-field classification accuracy | |
| CN115456476B (en) | Homeland space planning data acquisition and analysis system based on machine vision | |
| CN115965812B (en) | Evaluation method for classification of unmanned aerial vehicle images on wetland vegetation species and land features | |
| CN112861658A (en) | Identification method for desertification control key area based on multi-source data | |
| CN116129262A (en) | Cultivated land suitability evaluation method and system for suitable mechanized transformation | |
| Kamal et al. | A preliminary study on machine learning and google earth engine for mangrove mapping | |
| Abah et al. | Crop suitability mapping for rice, cassava, and yam in North Central Nigeria | |
| CN110807604A (en) | Method for evaluating soil fertility of greenhouse | |
| CN111476434B (en) | GIS-based soil heavy metal fractal dimension spatial variation analysis method | |
| Chen et al. | Soil sampling depth matters in assessing the impact of shrubification on soil organic carbon storage in grazed alpine meadows | |
| Willson et al. | Three-dimensional light structure of an upland Quercus stand post-tornado disturbance | |
| Udin et al. | Land use and land cover detection by different classification systems using remotely sensed data of Kuala Tiga, Tanah Merah Kelantan, Malaysia | |
| Cui et al. | Phenotypic characteristics of ramie (Boehmeria nivea L) germplasm resources based on UAV remote sensing | |
| Nasron et al. | Soil suitability assessment for harumanis mango cultivation in UiTM Arau, Perlis | |
| Chen et al. | Windbreak and sand fixation of sand plants based on intelligent image processing and plant landscape design | |
| Man et al. | Analysis on temporal and spatial characteristics of drought in North China from 1998 to 2017 | |
| CN109241866A (en) | A kind of crops automatic classification method and device based on history crop pattern map | |
| CN116843533B (en) | Mining area vegetation reconstruction method based on vegetation classification and land type division |
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 |