CN116778334A - Quantitative large-scale space grassland mouse entrance density prediction method and system - Google Patents
Quantitative large-scale space grassland mouse entrance density prediction method and system Download PDFInfo
- Publication number
- CN116778334A CN116778334A CN202310776838.9A CN202310776838A CN116778334A CN 116778334 A CN116778334 A CN 116778334A CN 202310776838 A CN202310776838 A CN 202310776838A CN 116778334 A CN116778334 A CN 116778334A
- Authority
- CN
- China
- Prior art keywords
- area
- grassland
- density
- quantitative
- hole
- 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 30
- 241000699666 Mus <mouse, genus> Species 0.000 claims abstract description 52
- 241000699670 Mus sp. Species 0.000 claims abstract description 32
- 238000009826 distribution Methods 0.000 claims abstract description 30
- 230000007613 environmental effect Effects 0.000 claims abstract description 29
- 241000283973 Oryctolagus cuniculus Species 0.000 claims description 11
- 238000010586 diagram Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 8
- 238000011160 research Methods 0.000 claims description 8
- 241000894007 species Species 0.000 claims description 6
- 239000002352 surface water Substances 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000001308 synthesis method Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 241000700159 Rattus Species 0.000 abstract description 33
- 238000011835 investigation Methods 0.000 abstract description 12
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 230000002265 prevention Effects 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract description 4
- 239000000463 material Substances 0.000 abstract description 3
- 239000000284 extract Substances 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 10
- 239000002689 soil Substances 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 5
- 241001529936 Murinae Species 0.000 description 4
- 241000283984 Rodentia Species 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 102100033538 Clusterin-associated protein 1 Human genes 0.000 description 1
- 101000945057 Danio rerio Clusterin-associated protein 1 homolog Proteins 0.000 description 1
- 241000699694 Gerbillinae Species 0.000 description 1
- 101000945060 Homo sapiens Clusterin-associated protein 1 Proteins 0.000 description 1
- 241001180873 Saposhnikovia divaricata Species 0.000 description 1
- 241001481798 Stochomys longicaudatus Species 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification 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
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06V10/766—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a quantitative large-scale space grassland mouse entrance to a cave density prediction method, which specifically comprises the following steps: the unmanned aerial vehicle photographs and determines the density of the holes of the sample land, the satellite remote sensing extracts the environmental factor value, establishes an optimal relation model of the hole density and the environmental factor, obtains the predicted hole density value in each 30 m-by-30 m resolution area of the target area, inverts the predicted hole density value to a map of the target area, and realizes quantitative and visual damage of mice in the target area of the grassland. The method can greatly reduce the cost of manpower and material resources required by investigation of the damage degree of the rats in a large-scale space range, realize quantitative and efficient monitoring of the spatial distribution of the rats in the grassland, and provide data support for accurate prevention and control decisions of the rats in the grassland.
Description
Technical Field
The invention belongs to the technical field of grassland mouse pest control, and particularly relates to a method and a system for predicting the density of a grassland mouse hole in a quantitative large-scale space.
Background
The distribution of the damage degree of the grassland mice in the quantitative space can provide data support for scientific prevention and control decisions of the grassland mice. The current quantitative method for the occurrence number of grassland mice in large-scale space at home and abroad is generally as follows: and (3) manually randomly selecting sampling points, and investigating the number index value of the mice in a certain area of the sampling point by adopting a hole counting method, a hole coefficient method or a line clamping method and the like so as to represent the number (density) of the mice in a certain area. These methods require a lot of manpower and material resources, high time cost, low efficiency, and poor precision of investigation data with the surface (area) of the spot (pattern), and only achieve more than none of the targets.
In 1979, przybilla aerial a surface image of the ground 200m by 300m in area with a fixed-wing drone equipped with an optical camera at the model airport of the Hederangent, wistergren, germany. Technology for obtaining ground target information by unmanned aerial vehicle remote sensing is rapidly developed after that. However, the early unmanned aerial vehicle remote sensing image has poor precision, and the information interpretation technology of a useful target has high requirements and high cost. With the improvement of consumer unmanned aerial vehicle shooting technology and the reduction of price, the technology of monitoring the occurrence of mouse damage by unmanned aerial vehicle shooting has been developed gradually after 2013. The technology of investigating the space quantity of the harmful mice by using the rotor unmanned aerial vehicle is published at present, mainly by rapidly obtaining a certain area of sample (2 hm) with a larger sample size (20 min/sample) 2 ) The number of the harmful mice in the sample area is precisely and quickly quantified by developing artificial intelligent recognition technology. Compared with the traditional manual investigation, the technology can significantly improve the investigation sample size of the area (region) with the point (sample plot). However, due to the limitation of aerial photographing capacity of the unmanned aerial vehicle, large-scale full-area coverage photographing still cannot be realized to determine the number of mouse holes, so that the number space distribution condition in a large-scale target area and even in the whole target mouse seed distribution area is obtained.
Satellite remote sensing technology has long been used for monitoring the occurrence of grassland rats. At present, the application modes of monitoring the damage of the rats on the grasslands mainly comprise two modes: one is to use satellite remote sensing image data to obtain remote sensing index values (such as normalized vegetation index NDVI, enhanced vegetation index EVI, surface water content LSWI, etc.) reflecting some environmental characteristics in a target area, and combine the mouse density values (trapping rate or hole density) of ground investigation to determine main remote sensing index values affecting the change of the mouse density in a sample area, so as to infer main ground environmental factors possibly affecting the dynamics of a target mouse population (Andreo et al, 2019). And the other is to use the sample point data of whether the historical or field investigation target mouse species are distributed or not, combine satellite remote sensing data (such as normalized vegetation index NDVI, enhanced vegetation index EVI, surface water content LSWI, ground temperature and humidity value, terrain feature type, soil type and the like) corresponding to some environmental features of the sample points, establish a Maxnet model to predict the probability interval of occurrence of the corresponding mouse species in a large-scale area and obtain the large-scale adaptive area of the mouse species. For example, lu et al (2022) uses 7 satellite remote sensing geospatial data such as altitude, gradient, ground surface temperature, rainfall, vegetation type, normalized vegetation index NDVI, soil type, etc. and ground station monitoring data, and combines the murine occurrence survey record data to build a Maxnet spatial distribution model of the target murine, and predicts the possible suitable distribution range of 5 rodent genera (vole, yellow vole, zokor, rabbit, gerbil) in 3 provinces/autonomous regions of inner mongolia, xinjiang, gansu. The method only determines the relation between the density of the mice in the sample area or the index value thereof and a plurality of satellite remote sensing indexes, and does not predict the density value of the mice in other areas outside the sample area. The method for predicting the large-scale adaptive area of the mouse species by utilizing the sample point data of whether the target mouse species is distributed or not in the history or field investigation and combining satellite remote sensing data and ground monitoring station data corresponding to some environmental characteristics of the sample points is essentially qualitative evaluation of the target mouse species distribution area, and a distribution map of the target mouse species population quantity in the area cannot be obtained.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method and a system for predicting the hole density of a grassland mouse in a quantitative large-scale space, which can accurately quantify the target mouse species in the large-scale space on the grassland.
The main technical ideas provided by the invention are as follows:
the method comprises the steps of obtaining large-sample-amount sample area rat hole density data by using an unmanned aerial vehicle, combining increasingly abundant satellite remote sensing environmental characteristic numerical data, establishing a quantitative relation model between hole density and environmental characteristic index values according to ecological characteristics of target rats, and further predicting unit resolution in a large-scale area on a grasslandRate area (e.g. 30 m.30m=900 m 2 ) Number of target mouse openings in the interior. Obtaining a grassland mouse entrance number distribution map with corresponding surface resolution, and finally providing data support for scientific prevention and control decisions of grassland mouse damage.
More specifically, the first aspect of the invention provides a quantitative large-scale space grassland mouse entrance density prediction method, which comprises the following steps:
s1: obtaining visible light images of selected area sample areas in each sample point in a target area, and identifying and extracting the number of rat hole openings in the area sample areas;
s2: acquiring satellite remote sensing data of the current annual environmental characteristics of the target area to obtain an environmental factor characteristic value;
s3: establishing a quantitative relation prediction model between the number of rat hole openings in the area sample plot and the characteristic value of the environmental factor;
s4: predicting the number of rat hole openings of other area plots in the target area by using a quantitative relation prediction model, and inverting the number of rat hole openings to the whole target area;
s5: and determining the number of holes corresponding to the hazard grades of the target mice, and obtaining hole density distribution diagrams of different hazard grades of the target mice in a large-scale space and corresponding hazard areas.
As a preferred embodiment, the step S1 specifically includes:
s101: selecting the number of sample points and the area sample areas, and shooting visible light images of the area sample areas in each sample point by using an unmanned aerial vehicle;
s102: cutting the obtained visible light image into unit images;
s103: and visually or artificially intelligently identifying and extracting the number of rat hole openings in each unit image.
As a preferred embodiment, the ground resolution of the cropped unit image is 30m×30m.
As a preferred embodiment, the step S2 specifically includes:
s201: using a satellite image dataset with the spatial resolution of 30m in a Google Earth Engine geographic cloud data processing platform;
s202: and acquiring satellite remote sensing data of the current annual environmental characteristics of the whole target area by using a mean synthesis method.
As a preferred embodiment, the satellite remote sensing data of the environmental characteristic includes normalized vegetation index NDVI, enhanced vegetation index EVI, surface moisture content LSWI, and ground temperature and humidity values.
As a preferred embodiment, the step S5 specifically includes:
s501: determining the number of holes corresponding to the hazard level of the target mouse species according to the industry standard or the scientific research publication result;
s502: and obtaining a hole density grading distribution diagram of the species of the target species in the target region, extracting areas for obtaining hole densities of different levels, and finally obtaining hole density distribution diagrams of different hazard levels of the species of the target species in a large-scale space and corresponding hazard areas.
More specifically, a second aspect of the present invention provides a quantitative large scale space grassland mousehole mouth density prediction system, the system comprising:
the device comprises a hole number acquisition module, a mouse hole number extraction module and a mouse hole number extraction module, wherein the hole number acquisition module is used for acquiring visible light images of area sample areas selected from all sample points in a target area, and identifying and extracting the number of mouse holes in the area sample areas;
the environment characteristic recognition and extraction module is used for acquiring satellite remote sensing data of the current annual environment characteristic of the target area to obtain an environment factor characteristic value;
the model building module is used for building a quantitative relation prediction model according to the number of rat hole openings in the area sample plot and the characteristic value of the environmental factor;
the calculation module predicts the number of rat hole openings of the area sample plot in the target area by using the quantitative relation prediction model and inverts the number of rat hole openings to the whole target area;
and the prediction module is used for obtaining a hole density grading distribution diagram of the mouse species in the target area according to the hole data of the whole area obtained by the calculation module, and extracting areas for obtaining hole densities of different grades.
More specifically, the third aspect of the present invention provides an electronic device, including a processor and a memory, wherein the memory stores computer instructions, and the processor is configured to execute the computer instructions stored in the memory, so as to implement the steps of the method for predicting the density of the holes of the grassland mice in the quantitative large-scale space.
More specifically, a fourth aspect of the present invention provides a computer readable storage medium storing computer instructions for causing the computer to perform a quantitative large scale space grassland mouse entrance density prediction method as described above.
In summary, the invention has the following advantages:
the invention can accurately quantify the large scale space on the grassland (for example, the existing research covers 3000km 2 Region) target mice were grown every 30m×30m=900 m 2 The number of the rat holes in the resolution area is further used for drawing a spatial distribution prediction graph of the number of the rat holes with the resolution of 30m by 30m. And obtaining a hole density grading distribution diagram of the target mouse species in the target area according to the number of holes corresponding to the target mouse species hazard level determined by the industry standard or the scientific research publication result. The defect that the density space distribution of the grassland mice is determined by using points (plots) instead of areas in the traditional manual investigation or the reported unmanned aerial vehicle investigation is poor in accuracy is overcome.
Drawings
FIG. 1 is a technical route for obtaining spatial distribution diagrams of different hazard class hole densities of mice and rats in Merler town, north Qinghai province.
Fig. 2 is a plot of a mersler town geographic location and an aerial sample of a drone in an embodiment.
Fig. 3 is a graph showing a linear relationship between the number of holes of the mice and rats and the actual value (visual interpretation value) in the image area (n=131) of the prediction verification unit of the optimal prediction model in the embodiment.
Fig. 4 is a graph of 5 hazard class distributions of muzzle densities of merle plateau mice predicted using unmanned aerial vehicle and satellite remote sensing techniques in an example.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but 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.
1. Terminology related to the inventive technique
Unmanned aerial vehicle remote sensing (Unmanned aerial vehicle remote sensing): the method for acquiring the ground target space data information efficiently by analyzing the image information by utilizing the ground related information image obtained by the unmanned aerial vehicle carried sensor.
Satellite remote sensing (Satellite remote sensing): the method comprises the steps of obtaining various ground feature radiation, reflection and refraction electromagnetic wave signals by using a satellite-mounted sensor, and returning the signals to a ground station for analysis and interpretation so as to obtain various ground feature data information. The earth surface information obtained by satellite remote sensing has the advantages of large scale, synchronism and repeated observation, and can continuously update the information of the fixed area target according to time sequence, such as the change of environmental parameters and the like.
Grassland mousehole density (Burrow density of rodent in grassland): number of mouseholes per unit area on grasslands. Which reflects the relative density of the corresponding murine population.
Portal density inversion model (Inversion model of rodent burrow density): obtaining a certain surface resolution area (30 m×30m=900 m) of a grassland sample area by using an unmanned aerial vehicle remote sensing image 2 ) The data of the number of mouse holes in the large-scale target area is obtained by utilizing satellite remote sensing images (for example, 30m is 30 m=900 m) 2 ) And (3) establishing quantitative relation models between the number of rat holes in the sample land and corresponding characteristic values of factors such as climate, vegetation, soil and the like according to the environmental data such as climate, vegetation, soil characteristics and the like.
Spatial representation of the hole density inversion model (Spatial expression of the inversion model for rodent burrow density): according to the hole density inversion model, converting corresponding weather, vegetation and soil characteristic data in a specific surface resolution area extracted from the large-scale target area satellite remote sensing image into corresponding hole quantity, and projecting the corresponding hole quantity onto a target area map to obtain a grassland rat hole quantity distribution map with corresponding surface resolution.
Hole density grading distribution map (Distribution map of different grade burrow density): and determining the hole density corresponding to different hazard grades (generally classified into 5 grades) of the target mouse species according to local or national industry standards or scientific research publication results, and endowing the surface resolution unit area within the range of the hole density on a map with the same color to obtain a hole density classification distribution diagram of the target mouse species in the target region.
2. The technical proposal related to the invention
(1) And obtaining a visible light image of the unmanned aerial vehicle. Selecting a certain number of sample points in a target area, taking an aerial image of a certain area of sample plot of each sample point by using an unmanned aerial vehicle, cutting the aerial image into unit images with the ground resolution of 30m and 30m, and visually reading or identifying the number of rat holes in each unit image of a sampling place by artificial intelligence.
(2) Satellite data acquisition, namely acquiring satellite remote sensing data (such as normalized vegetation index NDVI, enhanced vegetation index EVI, surface water content LSWI, ground temperature, humidity value and the like) of the current annual environmental characteristics of the whole target area by using a satellite image data set with the spatial resolution of 30m in a Google Earth Engine geographic cloud data processing platform and using a mean synthesis method.
(3) And establishing a multiple linear regression relation between the number of rat hole openings in the aerial photography sample area unit image area of the unmanned aerial vehicle and the characteristic value of the environmental factor of the current annual satellite remote sensing to obtain an optimal model for predicting the number of the rat hole openings.
(4) And predicting the number of mouse holes in the unit image ground with the area of 30m and 30m in the whole target area by using a quantitative relation model between the hole density and the environmental characteristic index, and inverting the number of mouse holes to the whole target area. And obtaining a hole density grading distribution map of the mouse species in the target area according to the number of holes corresponding to the target mouse species hazard level determined by the industry standard or the scientific research publication result, and extracting areas for obtaining hole densities of different levels. Finally, obtaining the density distribution map of the target mice with different hazard grades and the corresponding hazard areas on a large scale space.
Examples: predicting hole densities of different hazard grades of rats and rabbits in Merr town, qilin county, qinghai province, and referring to FIG. 1 for implementation steps
28 sample spots (figure 2) in the administrative area are shot by using a Royal 2Pro unmanned aerial vehicle in the middle 8 th 2022, 3555 visible light images of the unmanned aerial vehicle are obtained altogether, and the original images of the unmanned aerial vehicle are spliced by using Aigsoft Metashape 1.8.0 according to the following steps: the unmanned aerial vehicle photo is imported into software, a research sample orthographic image is obtained through splicing according to the steps of aligning the photo, establishing dense point cloud, generating grid, generating texture, establishing orthographic image and establishing DEM in a workflow, and finally an orthographic image geographic coordinate system is set as a WGS 84 coordinate system and exported in a TIFF format. Clipping the orthographic images of 28 samples into a ground resolution area of 30m×30m=900 m 2 A total of 436 unit images are obtained. And recording the geographical coordinates of the central points of the images of all the unit images, and manually and visually interpreting the number of the mouseholes in each unit image to obtain the mousehole mouth density of each unit image.
From a Google Earth Engine geographic cloud data platform, selecting a LANDSAT/LC08/C02/T1_L2 satellite remote sensing image dataset with the ground resolution of 30m, wherein remote sensing data in the dataset is subjected to pretreatment such as radiation calibration, orthographic correction and atmospheric correction. The 90 Merler remote sensing image data without cloud coverage in 2022 are filtered and reserved. Obtaining remote sensing index images such as annual normalized vegetation index (Normalized difference vegetation index, NDVI), enhanced vegetation index (Enhanced vegetation index, EVI), humidity index (WET), surface moisture content index (Land surface water index, LSWI), normalized bare soil index (Normalized difference bare soil index, NDBSI) and the like by using a mean synthesis method; a satellite image data set of MODIS/006/MOD11A2 is selected to obtain a land surface temperature (Land surface temperature, LST) image with a land resolution of 1km corresponding to the target area. And (3) importing the processed satellite index images into an ArcGIS, and extracting satellite remote sensing index values corresponding to each unit image of the unmanned aerial vehicle shooting sample plot according to the geographic coordinate points of each unit image in the research sample plot by using a space analysis/extraction analysis/multi-value extraction to point tool.
And randomly selecting a rat hole opening density value of 70% unmanned aerial vehicle aerial photography unit images (305) in the sample area and corresponding satellite remote sensing index values, and establishing a multiple linear regression model between the rat hole opening density and satellite remote sensing index data values, wherein the rest 30% data (131 unit images) are used as a data set for verifying the accuracy of the model. The optimal prediction model for predicting the number of the rabbit holes of the merrill plateau mice is obtained by multiple collinearity examination and AICc criterion screening: ln (Y) =2.1802+0.1434x1-7.544x2+11.3084x3. Wherein: y is the number of the rabbit holes of the plateau mice in the unit image area of the sample land, x1 is the land surface temperature LST of the current year, x2 is the normalized vegetation index NDVI of the current year, and x3 is the humidity index WET of the current year. Visual interpretation verifies that the mean value of the number of holes of 131 unit images in the data set is 81.40 +/-5.09, the mean value predicted by using the optimal prediction model is 91.05 +/-7.30, and a significant linear correlation is formed between a predicted value and a true value (R 2 ＝0.56,p<0.0001 (fig. 3).
And calculating the predicted value of the number of the rabbit holes of the plateau mice in each 30m unit image of the whole merle town according to the optimal prediction model. The density of the holes of the mice and rabbits on the plateau is 0 to 500 per hectare, so that the mice and rabbits are harmless; 500-1000 per hectare is a grade I hazard; 1000-2000 per hectare is a grade ii hazard; 2000-3000 per hectare grade iii hazard; 3000 per hectare the grade IV hazard criteria were rated for the high altitude murine rabbit hazard. Carrying out space expression on each unit image of the whole area by using a space analysis tool/mathematical analysis tool in the ArcGIS according to the hazard level standard (figure 4), and counting the area of each hazard level to finally obtain the area 99772.92 hectare of the whole Merr town rateless hazard area, wherein the area is 32.47%; grade I hazard zone 78965.48 hectares, 25.69%; grade ii hazard zone 71586.04 hectares, 23.29%; grade III hazard zone 37106.10 hectares, 12.07% duty cycle; grade iv hazard area 19924.72 hectares, 6.48% duty cycle (table 1). Table 1: siler town plateau mouse-rabbit portal density 5 hazard class total area predicted by unmanned aerial vehicle and satellite remote sensing technology
The above schemes and examples can be summarized as follows:
the invention provides a set of grassland rat hole numbers in a large-scale space range, wherein the grassland rat hole numbers are accurately quantified and visualized in a 30 m-by-30 m area by using unmanned aerial vehicle remote sensing images and satellite remote sensing images. The defect of poor accuracy in determining the density space distribution of the grassland mice by using points (plots) instead of areas in the traditional manual investigation or the reported unmanned aerial vehicle investigation is overcome. The method can greatly reduce the cost of manpower and material resources required by investigation of the damage degree of the rats in a large-scale space range, realize quantitative and efficient monitoring of the spatial distribution of the rats in the grassland, and provide data support for accurate prevention and control decisions of the rats in the grassland.
The implementation scheme flow of accurately quantifying the number of rat holes in a resolution area of 30m by 30m of target rat species in a large-scale space on a grassland comprises the following steps: the unmanned aerial vehicle photographs and determines the density of the holes in the sample land, the satellite remote sensing extracts the environmental factor value, and establishes an optimal relation model of the density of the holes and the environmental factor, the obtained target area predicts the density value of the holes in a resolution area of 30m x 30m and inverts the predicted density value to a map of the target area, so that the quantitative and visual damage of the mice in the target area of the grassland is realized.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Reference to the literature
Pistil, hua Li Min, ma Sujie, wang Ting, chu Bin, zhou Rui, ji Chengpeng. A method for monitoring the damage of highland zokor and highland rabbit based on micro unmanned plane technology [ P ]. Gansu: CN108537130a,2018-09-14.
Dong G,Xian W,Shao H,Shao Q,Qi J.2023.Performance of multiple models for estimating rodent activity intensity in Alpine grassland using remote sensing.Remote Sensing.15(5):1404.
Wu Y,Ma Y,Liu W,Zhang W.2019.Modeling the spatial distribution of plateau pika (Ochotona curzoniae)in the Qinghai Lake Basin,China[J].Animals.9(10):843.Andreo V,Belgiu M,Hoyos D B,Osei F,Provensal C,Stein A.2019.Rodents and satellites:
Predicting mice abundance and distribution with Sentinel-2data[J].Ecological informatics.51:157-167.
Lu L,Sun Z,Qimuge E,Ye H,Huang W,Nie C,Wang K,Zhou Y.2022Using remote sensing data and species–environmental matching model to predict the potential distribution of grassland rodents in the Northern China.Remote Sensing.14(9):2168。
Claims (10)
1. A method for predicting quantitative large-scale space grassland mouse entrance density, which is characterized by comprising the following steps:
s1: obtaining visible light images of selected area patterns in each pattern point in a target area, and identifying and extracting the number of rat hole openings in the area patterns;
s2: acquiring satellite remote sensing data of the current annual environmental characteristics of the target area to obtain an environmental factor characteristic value;
s3: establishing a quantitative relation prediction model between the number of rat hole openings in the area sample plot and the characteristic value of the environmental factor;
s4: predicting the number of rat hole openings of the area sample land in the whole target area by using a quantitative relation prediction model, and inverting the number of the rat hole openings to the target area;
s5: and determining the number of holes corresponding to the hazard grades of the target mice, and obtaining hole density distribution diagrams of different hazard grades of the target mice in a large-scale space and corresponding hazard areas.
2. The method for predicting the quantitative large-scale space grassland mouse entrance density according to claim 1, wherein the step S1 specifically comprises:
s101: selecting the number of sample points and the area sample areas, and shooting visible light images of the area sample areas in each sample point by using an unmanned aerial vehicle;
s102: cutting the obtained visible light image into unit images;
s103: and visually or artificially intelligently identifying and extracting the number of rat hole openings in each unit image.
3. The method for predicting the quantitative large-scale space grassland mouse entrance density according to claim 1, wherein the step S2 specifically comprises:
s201: using a satellite image dataset with the spatial resolution of 30m in a Google Earth Engine geographic cloud data processing platform;
s202: and acquiring satellite remote sensing data of the current annual environmental characteristics of the whole target area by using a mean synthesis method.
4. A method for predicting the quantitative large-scale space grassland mouse entrance density according to claim 3, wherein the satellite remote sensing data of the environmental features comprise normalized vegetation index NDVI, enhanced vegetation index EVI, surface water content LSWI, and ground temperature and humidity values.
5. The method for predicting the quantitative large-scale space grassland mouse entrance density according to claim 4, wherein the quantitative relation prediction model is as follows:
ln(Y)＝a+f(x1)+f(x2)+…+f(xn)；
wherein Y is the number of the holes of the mice and rabbits of the plateau in the unit image area of the sample area, a is a constant, and X1, X2 … Xn are the characteristic values of environmental factors of satellite remote sensing in the current year.
6. The method for predicting the quantitative large-scale space grassland mouse entrance density according to claim 1, wherein the step S5 specifically comprises:
s501: determining the number of holes corresponding to the hazard level of the target mouse species according to the industry standard or the scientific research publication result;
s502: and obtaining a hole density grading distribution diagram of the species of the mice in the target area, extracting areas for obtaining hole densities of different levels, and finally obtaining hole density distribution diagrams of different hazard levels of the species of the target mice in the target area and corresponding hazard areas.
7. A quantitative large-scale spatial grassland mousehole density prediction system, characterized in that the system comprises:
the device comprises a hole number acquisition module, a mouse hole number extraction module and a mouse hole number extraction module, wherein the hole number acquisition module is used for acquiring visible light images of area sample areas selected from all sample points in a target area, and identifying and extracting the number of mouse holes in the area sample areas;
the environment characteristic recognition and extraction module is used for acquiring satellite remote sensing data of the current annual environment characteristic of the target area to obtain an annual environment factor characteristic value;
the model building module is used for building a quantitative relation prediction model according to the number of rat hole openings in the area sample plot and the characteristic value of the annual average environmental factor;
the calculation module predicts the number of rat hole openings of the area sample plot in the target area by using the quantitative relation prediction model and inverts the number of rat hole openings to the whole target area;
and the prediction module is used for obtaining a hole density grading distribution diagram of the mouse species in the target area according to the hole data of the whole area obtained by the calculation module, and extracting areas for obtaining hole densities of different grades.
8. The quantitative large scale space grassland mouse hole density prediction system according to claim 7, wherein the quantitative relation prediction model is:
ln(Y)＝a+f(x1)+f(x2)+…+f(xn)；
wherein Y is the number of the holes of the mice and rabbits of the plateau in the unit image area of the sample area, a is a constant, and X1, X2 … Xn are the characteristic values of environmental factors of satellite remote sensing in the current year.
9. An electronic device comprising a processor and a memory, wherein the memory has stored thereon computer instructions, the processor being configured to execute the computer instructions stored on the memory to implement the steps of a method for predicting a quantitative large scale space grassland mouse portal density as claimed in any one of claims 1 to 5.
10. A computer readable storage medium storing computer instructions for causing the computer to perform a method of quantifying large scale space grassland mouse entrance density prediction according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310776838.9A CN116778334A (en) | 2023-06-28 | 2023-06-28 | Quantitative large-scale space grassland mouse entrance density prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310776838.9A CN116778334A (en) | 2023-06-28 | 2023-06-28 | Quantitative large-scale space grassland mouse entrance density prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116778334A true CN116778334A (en) | 2023-09-19 |
Family
ID=88013098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310776838.9A Pending CN116778334A (en) | 2023-06-28 | 2023-06-28 | Quantitative large-scale space grassland mouse entrance density prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116778334A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102651094A (en) * | 2011-02-28 | 2012-08-29 | 中国科学院遥感应用研究所 | Plague natural epidemic focus space distribution forecasting method |
| CN108537130A (en) * | 2018-03-15 | 2018-09-14 | 甘肃农业大学 | A kind of Myospalax baileyi and Ochotona curzoniae based on miniature drone technology endanger monitoring method |
| CN109257575A (en) * | 2018-11-09 | 2019-01-22 | 广东佰得威病媒生物监测评估有限公司 | A kind of density of rodents monitoring method and monitoring system |
| CN111881728A (en) * | 2020-06-16 | 2020-11-03 | 四川师范大学 | Grassland mouse damage monitoring method based on low-altitude remote sensing |
| CN113378700A (en) * | 2021-06-08 | 2021-09-10 | 四川农业大学 | Grassland rat damage dynamic monitoring method based on unmanned aerial vehicle aerial image |
| CN115311343A (en) * | 2022-04-22 | 2022-11-08 | 花立民 | Grassland pest occurrence area investigation method based on multi-stage sampling |
| CN115527130A (en) * | 2022-09-20 | 2022-12-27 | 中国农业科学院农业信息研究所 | Grassland pest mouse density investigation method and intelligent evaluation system |
-
2023
- 2023-06-28 CN CN202310776838.9A patent/CN116778334A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102651094A (en) * | 2011-02-28 | 2012-08-29 | 中国科学院遥感应用研究所 | Plague natural epidemic focus space distribution forecasting method |
| CN108537130A (en) * | 2018-03-15 | 2018-09-14 | 甘肃农业大学 | A kind of Myospalax baileyi and Ochotona curzoniae based on miniature drone technology endanger monitoring method |
| CN109257575A (en) * | 2018-11-09 | 2019-01-22 | 广东佰得威病媒生物监测评估有限公司 | A kind of density of rodents monitoring method and monitoring system |
| CN111881728A (en) * | 2020-06-16 | 2020-11-03 | 四川师范大学 | Grassland mouse damage monitoring method based on low-altitude remote sensing |
| CN113378700A (en) * | 2021-06-08 | 2021-09-10 | 四川农业大学 | Grassland rat damage dynamic monitoring method based on unmanned aerial vehicle aerial image |
| CN115311343A (en) * | 2022-04-22 | 2022-11-08 | 花立民 | Grassland pest occurrence area investigation method based on multi-stage sampling |
| CN115527130A (en) * | 2022-09-20 | 2022-12-27 | 中国农业科学院农业信息研究所 | Grassland pest mouse density investigation method and intelligent evaluation system |
Non-Patent Citations (7)
| Title |
|---|
| DAVIS J.CHIDODO等: "Application of normalized difference vegetation index (NDVI) to forecast rodent population abundance in smallholder agro-ecosystems in semi-arid areas in Tanzania", 《MAMMALIA》, vol. 84, no. 02, 31 July 2019 (2019-07-31), pages 136 - 143 * |
| HAIYANG SHI等: "Analysis of the Impacts of Environmental Factors on Rat Hole Density in the Northern Slope of the Tienshan Mountains with Satellite Remote Sensing Data", 《REMOTE SENSING》, 21 November 2021 (2021-11-21), pages 1 - 17 * |
| 潘群等: "基于Cubist模型的天山北坡草地鼠群密度时空分布特征", 《干旱区地理》, vol. 45, no. 04, 31 July 2022 (2022-07-31), pages 1 - 3 * |
| 甄磊等: "基于无人机可见光图像估算甘肃鼢鼠对马铃薯的为害量", 《植物保护学报》, vol. 49, no. 06, 15 December 2022 (2022-12-15), pages 1697 - 1704 * |
| 花蕊等: "基于无人机遥感的天然草原鼠害发生面积调查方法研究", 《草业学报》, vol. 32, no. 05, 13 February 2023 (2023-02-13), pages 71 - 82 * |
| 连欢欢等: "利用无人机开展草原鼠害调查监测的研究", 《青海草业》, vol. 30, no. 04, 21 December 2021 (2021-12-21), pages 38 - 43 * |
| 郭新磊等: "基于无人机的青藏高原鼠兔潜在栖息地环境初步研究", 《草业科学》, vol. 34, no. 06, 15 June 2017 (2017-06-15), pages 1307 - 1308 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lau et al. | Quantifying branch architecture of tropical trees using terrestrial LiDAR and 3D modelling | |
| D'Urban Jackson et al. | Three-dimensional digital mapping of ecosystems: a new era in spatial ecology | |
| Swatantran et al. | Rapid, high-resolution forest structure and terrain mapping over large areas using single photon lidar | |
| Maltamo et al. | Combining ALS and NFI training data for forest management planning: a case study in Kuortane, Western Finland | |
| Vandaele et al. | Deep learning for automated river-level monitoring through river-camera images: an approach based on water segmentation and transfer learning | |
| Zeybek | Classification of UAV point clouds by random forest machine learning algorithm | |
| Jeswani et al. | Evaluation of the consistency of DMSP-OLS and SNPP-VIIRS Night-time Light Datasets | |
| CN110110025B (en) | Regional population density simulation method based on feature vector space filtering value | |
| CN112445241A (en) | Ground surface vegetation identification method and system based on unmanned aerial vehicle remote sensing technology and readable storage medium | |
| Solvin et al. | Use of UAV photogrammetric data in forest genetic trials: measuring tree height, growth, and phenology in Norway spruce (Picea abies L. Karst.) | |
| Liu et al. | Estimating maize seedling number with UAV RGB images and advanced image processing methods | |
| CN115630567A (en) | Coastal zone soil organic carbon reserve simulation and prediction method | |
| Gervasoni et al. | Convolutional neural networks for disaggregated population mapping using open data | |
| CN114241332A (en) | Deep learning-based solid waste field identification method and device and storage medium | |
| Tao et al. | Mapping tropical forest trees across large areas with lightweight cost-effective terrestrial laser scanning | |
| Zhang et al. | A 250 m annual alpine grassland AGB dataset over the Qinghai–Tibet Plateau (2000–2019) in China based on in situ measurements, UAV photos, and MODIS data | |
| CN117408495B (en) | Data analysis method and system based on comprehensive management of land resources | |
| Greco et al. | Methodology for measuring dendrometric parameters in a mediterranean forest with UAVs flying inside forest | |
| CN110321528B (en) | Hyperspectral image soil heavy metal concentration assessment method based on semi-supervised geospatial regression analysis | |
| CN112101168A (en) | Satellite and unmanned aerial vehicle linkage-based commonweal litigation auxiliary evidence obtaining system and method | |
| CN117011759A (en) | Method and system for analyzing multi-element geological information of surrounding rock of tunnel face by drilling and blasting method | |
| CN116778334A (en) | Quantitative large-scale space grassland mouse entrance density prediction method and system | |
| Roussel et al. | Classification of high-voltage power line structures in low density ALS data acquired over broad non-urban areas | |
| Cömert et al. | Object based building extraction and building period estimation from unmanned aerial vehicle data | |
| Anttila | Assessment of manual and automated methods for updating stand-level forest inventories based on aerial photography |
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 |