CN116403125B - Grassland caterpillar suitable living area dividing method, system and terminal based on unmanned aerial vehicle aerial photography - Google Patents
Grassland caterpillar suitable living area dividing method, system and terminal based on unmanned aerial vehicle aerial photography Download PDFInfo
- Publication number
- CN116403125B CN116403125B CN202211640504.0A CN202211640504A CN116403125B CN 116403125 B CN116403125 B CN 116403125B CN 202211640504 A CN202211640504 A CN 202211640504A CN 116403125 B CN116403125 B CN 116403125B
- Authority
- CN
- China
- Prior art keywords
- grassland
- caterpillars
- caterpillar
- observation sample
- data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000009826 distribution Methods 0.000 claims abstract description 40
- 230000007613 environmental effect Effects 0.000 claims abstract description 36
- 238000012216 screening Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims description 27
- 239000002689 soil Substances 0.000 claims description 20
- 238000001556 precipitation Methods 0.000 claims description 12
- 230000005855 radiation Effects 0.000 claims description 12
- 230000035945 sensitivity Effects 0.000 claims description 11
- 238000004088 simulation Methods 0.000 claims description 9
- 239000004576 sand Substances 0.000 claims description 8
- 238000010220 Pearson correlation analysis Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 239000002344 surface layer Substances 0.000 claims description 3
- 238000012876 topography Methods 0.000 claims description 3
- 230000004083 survival effect Effects 0.000 claims 1
- 238000011160 research Methods 0.000 abstract description 31
- 241000607479 Yersinia pestis Species 0.000 abstract description 12
- 241000238631 Hexapoda Species 0.000 abstract description 10
- 230000002265 prevention Effects 0.000 abstract description 3
- 238000011835 investigation Methods 0.000 description 11
- 102100033538 Clusterin-associated protein 1 Human genes 0.000 description 9
- 101000945057 Danio rerio Clusterin-associated protein 1 homolog Proteins 0.000 description 9
- 101000945060 Homo sapiens Clusterin-associated protein 1 Proteins 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 206010054949 Metaplasia Diseases 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000004069 differentiation Effects 0.000 description 4
- 230000015689 metaplastic ossification Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 244000025254 Cannabis sativa Species 0.000 description 3
- 241000486464 Gynaephora Species 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 241000592183 Eidolon Species 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000004927 clay Substances 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 244000144972 livestock Species 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 231100000572 poisoning Toxicity 0.000 description 2
- 230000000607 poisoning effect Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 241001290610 Abildgaardia Species 0.000 description 1
- 241000223600 Alternaria Species 0.000 description 1
- 239000002028 Biomass Substances 0.000 description 1
- 241000283690 Bos taurus Species 0.000 description 1
- 235000008744 Brassica perviridis Nutrition 0.000 description 1
- 241000712024 Brassica rapa var. perviridis Species 0.000 description 1
- 241000234642 Festuca Species 0.000 description 1
- 241000255777 Lepidoptera Species 0.000 description 1
- 241001124557 Lymantriidae Species 0.000 description 1
- 241000253075 Pulicaria vulgaris Species 0.000 description 1
- 235000013559 Schnittsellerie Nutrition 0.000 description 1
- 244000169997 Schnittsellerie Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000021050 feed intake Nutrition 0.000 description 1
- 244000144980 herd Species 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000000361 pesticidal effect Effects 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000019617 pupation Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 239000003053 toxin Substances 0.000 description 1
- 231100000765 toxin Toxicity 0.000 description 1
- 108700012359 toxins Proteins 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 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
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Remote Sensing (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a grassland caterpillar suitable living area dividing method, a grassland caterpillar suitable living area dividing system and a grassland caterpillar suitable living area dividing terminal based on unmanned aerial vehicle aerial photography, which comprise the following steps: setting an observation sample point, and acquiring grassland caterpillar data of the observation sample point by using unmanned aerial vehicle aerial photography; acquiring environmental factors corresponding to the observation sample points; based on BIOMOD simulation software, constructing an ecological niche model by using grassland caterpillar data and environmental factors; evaluating the ecological niche model according to three indexes of Kappa, TSS and AUC, and screening out an optimal ecological niche model; and predicting the spatial distribution probability of the grassland caterpillars by using the optimal ecological niche model, and dividing the grassland caterpillars suitable living areas according to the spatial distribution probability. The invention provides basic data of spatial distribution research of grassland caterpillars based on unmanned aerial vehicle aerial technology, and combines BIOMOD and environmental factors corresponding to observation sample points to divide grassland insect pest suitable living areas, thereby providing theoretical and practical basis for further quantitatively knowing ecological status of grassland caterpillars and making insect pest early warning and prevention measures.
Description
Technical Field
The invention relates to the technical field of biological ecological distribution, in particular to a grassland caterpillar suitable-living area dividing method, system and terminal based on unmanned aerial vehicle aerial photography.
Background
The grassland caterpillar (Gynaephora alpheraki) is an alias of the genus Heterocarpa (Lepidotera) and the genus Heterocarpa (Gynaephora), belonging to the family Lepidoptera (Lepidotera) and the family Podopteraceae (LYMANTRIIDAE). The alpine grasslands of the Qinghai-Tibet plateau in China are one of the main distribution areas. Grassland caterpillars show strong feeding preference for sedge and grass plants such as small-fleabane grass, short-fleabane grass, fescue, elvan spica, etc., and feed is fed to the basal part by the leaf tips, and tender green leaves of vegetation are fed preferentially. In recent years, the occurrence of the caterpillars in the Qinghai-Tibet plateau is frequent and the outbreak of the caterpillars is a disaster under the dual influence of global climate change and human activity disturbance. After the grassland caterpillar disasters burst, more than five hundred grassland vegetation can be achieved per square meter, the severely destroyed grassland vegetation is difficult to recover within two years, and the grassland production capacity and the livestock carrying capacity per unit area are greatly reduced. In addition, grassland caterpillars are rich in toxins, poisoning can be caused after livestock feed intake, and poisoning can be caused if protective measures are not adopted or cleaning is not timely carried out after herd contact. Grassland caterpillars cause great harm to alpine grasslands in Qinghai-Tibet plateau in China. Since the 60 s of the 20 th century, a great deal of manpower, material resources and financial resources are invested in the country each year to control grassland caterpillars, and particularly, great research is conducted on pesticide effects and development of novel biological pesticides. But still fail to control the pest hazard fundamentally and effectively.
The environment to which the insect pest is adaptive is known, and the biological characteristics, occurrence rules and quantity changes of the insect pest are known, so that the insect pest is a main theoretical basis and basis for monitoring, forecasting and preventing. At present, the investigation and research of the grassland caterpillars is still based on the traditional sample prescription investigation at the site scale, such as the research on the feeding characteristics, the growth and development, the space distribution pattern influence factors and the like of the grassland caterpillars. Sample methods generally require a lot of time, labor and capital investment in large scale investigation, and it is difficult to conduct investigation work in a large area in a limited time. While the larvae of the grassland caterpillars are smaller, the satellite telesensitivity resolution is limited, and the larvae cannot be identified and measured. In addition, the survey sites and observers of the conventional method are not fixed and the measurement standards are not uniform, resulting in limited space-time representativeness and comparability of the obtained samples. Limited by limited observation means, the information such as the spatial diversity characteristics and the distribution of the metaplasia areas of the regional scale grassland caterpillars is not clear at present.
Disclosure of Invention
The invention aims to solve the problems that the space distribution of the grassland caterpillars is unclear and inaccurate by the existing observation means, and provides a grassland caterpillars suitable-living division method, system and terminal based on unmanned aerial vehicle aerial photography.
The aim of the invention is realized by the following technical scheme:
in a first aspect, a method for dividing a grassland caterpillar habitat based on unmanned aerial vehicle aerial photography is provided, the method comprising:
setting an observation sample point, and acquiring grassland caterpillar data of the observation sample point by using unmanned aerial vehicle aerial photography;
Acquiring environmental factors corresponding to the observation sample points;
Based on BIOMOD simulation software, constructing an ecological niche model by utilizing the grassland caterpillar data and the environmental factors;
evaluating the ecological niche model according to three indexes of Kappa, TSS and AUC, and screening out an optimal ecological niche model;
and predicting the spatial distribution probability of the grassland caterpillars by using the optimal ecological niche model, and dividing the grassland caterpillars suitable living areas according to the spatial distribution probability.
As a preferred option, the grassland caterpillars are preferably distinguished based on unmanned aerial vehicle aerial photography, the size of the observation sample points is 250m multiplied by 250m, and each observation sample point is provided with a Grid flight route of 200m multiplied by 200m and 3 Belt flight routes of 40m multiplied by 40 m.
As a preferred option, a method for dividing grassland caterpillars into regions suitable for growth based on unmanned aerial vehicle aerial photography, wherein the method for obtaining grassland caterpillars data of the observation sample point by unmanned aerial vehicle aerial photography comprises the following steps:
Uploading aerial photos, waypoints and route information of each flight through FragMAP;
And positioning and analyzing the grassland caterpillar data in time based on the collaborative analysis platform, wherein different analysts simultaneously perform the caterpillar number extraction work, and compare the grassland caterpillar analysis results of different personnel.
As a preferred option, the method for distinguishing the grassland caterpillars from each other based on unmanned aerial vehicle aerial photography comprises the steps of meteorological, soil, remote sensing vegetation index and topography.
As a preferred option, the method for distinguishing the grassland caterpillars from each other based on unmanned aerial vehicle aerial photography, wherein the constructing of the ecological niche model by using the grassland caterpillars data and the environmental factors comprises the following steps:
and screening all the environmental factors by combining the Pearson correlation coefficient and the factor Importance index Importance.
As a preferred option, a grassland caterpillar habitat division method based on unmanned aerial vehicle aerial photography is used for evaluating the consistency of the predicted result by Kappa, and the TSS is calculated according to the following formula:
TSS＝Sensitivity+Specificity-1＝TPR-FPR
Wherein Sensitivity is Sensitivity, SPECIFICITY is specificity, TPR (true positive rate) true positive rate, FPR (falsepositive rate) false positive rate, and the TSS value range is (0, 1); the AUC is defined as the area enclosed by the coordinate axis under the ROC curve, and the value range of the AUC is (0.5, 1).
As a preferred option, a method for dividing grassland caterpillars into regions suitable for growth based on unmanned aerial vehicle aerial photography, the dividing the regions suitable for growth of grassland caterpillars according to the spatial distribution probability comprises:
the grassland caterpillars are divided into different grades according to the size of the spatial distribution probability.
As a preferred option, a grassland caterpillar habitat distinguishing method based on unmanned aerial vehicle aerial photography, wherein the method for evaluating the ecological niche model according to three indexes of Kappa, TSS and AUC, screening out the optimal ecological niche model comprises the following steps:
The RF model has the highest simulation precision on the grassland caterpillar ecological niche.
In a second aspect, there is provided a grassland caterpillars metaplasia division system based on unmanned aerial vehicle aerial photography, the system comprising:
The grassland caterpillar data acquisition module is used for setting an observation sample point and acquiring grassland caterpillar data of the observation sample point by unmanned aerial vehicle aerial photography;
the environment factor acquisition module is used for acquiring environment factors corresponding to the observation sample points;
the ecological niche model building module is used for building an ecological niche model by utilizing the grassland caterpillar data and the environmental factors based on BIOMOD simulation software;
The ecological niche model screening module is used for evaluating the ecological niche model according to three indexes of Kappa, TSS and AUC and screening out an optimal ecological niche model;
And the grassland caterpillar suitable living area dividing module predicts the spatial distribution probability of the grassland caterpillar by utilizing the optimal ecological niche model and divides the grassland caterpillar suitable living area according to the spatial distribution probability.
In a third aspect, a terminal is provided, including a memory and a processor, where the memory stores computer instructions executable on the processor, and where the processor executes the computer instructions to perform the steps associated with any one of the grassland caterpillar beneficial differentiation methods.
It should be further noted that the technical features corresponding to the above options may be combined with each other or replaced to form a new technical scheme without collision.
Compared with the prior art, the invention has the beneficial effects that:
(1) According to the invention, the field grassland caterpillars are observed by adopting unmanned aerial vehicle aerial photo acquisition, the unmanned aerial vehicle is high in efficiency, convenient to operate and high in photo resolution, so that a plurality of difficulties in traditional sample investigation are overcome, a large amount of manpower and material resources are saved, and the range and the number of sample points of the grassland caterpillars are increased. And a large amount of real and reliable field observation data can be provided for grassland caterpillar suitable living area research. Compared with the traditional habitat division method, the method utilizes the ecological level model to estimate the grassland caterpillar pest area, further quantitatively analyzes the habitat index of each ecological factor, and reduces the systematic error caused by the random selection of the sample party in the traditional division analysis. The method has the advantages that the plot of the suitable living area of the grassland caterpillar in the research area is accurately obtained, so that an efficient and accurate method is provided for basic researches such as the habit of the grassland caterpillar and the like and the prediction of the insect damage of the alpine grassland, and theoretical and practical bases are provided for further quantitatively knowing the ecological status of the grassland caterpillar and the formulation of insect damage prevention and control strategies and measures.
(2) In one example, all environmental factors are screened in combination with Pearson correlation coefficients and factor Importance index Importance, so that the influence of inter-factor autocorrelation and information redundancy on the running speed and simulation accuracy of the model is reduced.
Drawings
FIG. 1 is a flow chart of a grassland caterpillar habitat division method based on unmanned aerial vehicle aerial photography, according to an embodiment of the invention;
FIG. 2 is a schematic view of an observation sample point setup according to an embodiment of the present invention;
FIG. 3 is a schematic diagram showing a process of analyzing the number of the grassland caterpillars according to the embodiment of the present invention;
FIG. 4 is a graph showing the results of an environment variable autocorrelation analysis in accordance with an embodiment of the present invention;
FIG. 5 illustrates the importance values and relative contribution rates of environmental variables (environmental factors) in accordance with an embodiment of the present invention;
FIG. 6 is a statistical result of the occurrence probability space-time dynamic change of the grassland caterpillars according to the embodiment of the invention;
FIG. 7 is a schematic representation of the spatiotemporal dynamics of a grassland caterpillar pest area shown in an embodiment of the invention;
FIG. 8 is a plot of the accumulation of grassland caterpillars as pest areas in accordance with an embodiment of the present invention;
FIG. 9 is a schematic diagram showing the grassland caterpillar habitat division according to the embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully understood from the accompanying drawings, in which some, but not all embodiments of the invention are shown. 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.
In addition, the technical features of the different embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
According to the invention, a FragMAP unmanned aerial vehicle aerial photographing system is adopted to observe the space diversity characteristics of the grassland caterpillars in the Qinghai patch area of the Qilin mountain country family, and factors such as grassland vegetation, soil, climate, topography and the like corresponding to the BIOMOD ecological niche model and the observation sample plot are combined to obtain the grassland caterpillars ecological niche of the Alternaria patch area of the Qilin mountain country family, and the grassland insect-attack suitable areas are divided according to the space diversity characteristics. Provides a high-efficiency and accurate method for basic researches such as the habit of the grassland caterpillars and the like and the prediction of the insect damage of the alpine grassland, and simultaneously provides theoretical and practical basis for the quantitative understanding of the ecological status of the grassland caterpillars and the formulation of insect damage prevention and control strategies and measures.
In an exemplary embodiment, a method for dividing a grassland caterpillar habitat based on unmanned aerial vehicle (unmanned aerial vehicle) is provided, and referring to fig. 1, the method includes:
setting an observation sample point, and acquiring grassland caterpillar data of the observation sample point by using unmanned aerial vehicle aerial photography;
Acquiring environmental factors corresponding to the observation sample points;
Based on BIOMOD simulation software, constructing an ecological niche model by utilizing the grassland caterpillar data and the environmental factors;
evaluating the ecological niche model according to three indexes of Kappa, TSS and AUC, and screening out an optimal ecological niche model;
and predicting the spatial distribution probability of the grassland caterpillars by using the optimal ecological niche model, and dividing the grassland caterpillars suitable living areas according to the spatial distribution probability.
The northeast part of Qinghai province at the park of Qili mountain is the juncture of Gansu province and Qinghai province, and the total area is 5.02 ten thousand square kilometers. The invention takes the grasslands of Qinghai tablet areas of Qilian mountain country families as research objects (mainly comprising 5 city counties such as German Haw City, tianjun counties, qilian counties, just-examined counties, and Ganyuan counties). The annual average precipitation amount in the research area is 232.4mm, the annual precipitation amount is distributed northwest-southeast, and the precipitation amount in the middle and eastern areas is larger. The annual average air temperature is lower (4 ℃), the spatial distribution form is more stable, the annual change is small, the air temperature contour line is basically consistent with the topographic profile, and the grassland is the most main land utilization type of the research area and accounts for 67.19 percent of the total area of the whole research area. Mainly comprises grassland types such as alpine meadow, mountain meadow, low-land meadow, warm meadow, alpine desert meadow, warm desert, alpine desert and the like. The area is also an important ecological safety barrier in the western part of China, and an important water source area of the yellow river and a priority area for biodiversity protection.
In one example, a grassland caterpillar habitat distinguishing method based on unmanned aerial vehicle aerial photography is provided, the size of the observation sample points is 250m×250m, and a Grid flight route of 200m×200m and 3 Belt flight routes of 40m×40m are arranged in each observation sample point. Specifically, an unmanned aerial vehicle aerial photography analysis system FragMAP which is independently developed by a team is utilized, a large number of field observation sample points with the size of 250m multiplied by 250m are arranged in a research area according to the vegetation type of the grasslands and the space representativeness, each observation sample point is provided with 4 airlines to represent the vegetation information of the grasslands in the range of 250m multiplied by 250m as shown in figure 2, 16 aerial photography points are uniformly distributed in the observation range of each flight airlines mode, and each aerial photography point lens takes a photo of the grasslands vertically downwards. Each route is set and stored in FRAGMAP SETTER for later invocation for fixed point repeated observation. The Grid flight mode uses a large-scale 'eidolon' series unmanned plane, and the flight height is 20m (the picture resolution is less than 1cm, and the coverage range is 26m multiplied by 35 m); the Belt flight mode uses a large-scale 2zoom version unmanned aerial vehicle with a flight height of 2m (resolution 0.09cm, coverage 3.43m×2.57 m). The Dajiang 'eidolon' series unmanned aerial vehicle is used for selecting a grassland growth condition which is relatively uniform, and has a representative MODIS pixel scale observation pattern. Grassland caterpillar data are obtained through field observation aerial photographs of a Royal 2zoom version unmanned aerial vehicle Mavic and a rotor unmanned aerial vehicle. The field observation is carried out before the pupation period of the grassland caterpillars in 2021 (at the end of 7 months to the beginning of 8 months), and the arrangement of observation sample points (also called observation sample plots) considers the occurrence and distribution rules of the grassland caterpillars on one hand; on the other hand, in order to obtain the spatial distribution of the grassland caterpillars as comprehensively as possible, when the field observation sample plot is set, the observation sample plot is set as much as possible at intervals of about 10km along the main traffic road and the human reachable area. 229 fixed monitoring points are arranged in the national park, and the number of observation sample areas is approximately 10000; and obtaining 1-thousand aerial photos for qualitative and quantitative detection of the late grassland caterpillars.
In one example, a method for identifying a grassland caterpillar suitable for living based on unmanned aerial vehicle aerial photography, the acquiring grassland caterpillar data of the observation sample point by unmanned aerial vehicle aerial photography includes:
Uploading aerial photos, waypoints and route information of each flight through FragMAP;
And positioning and analyzing the grassland caterpillar data in time based on the collaborative analysis platform, wherein different analysts simultaneously perform the caterpillar number extraction work, and compare the grassland caterpillar analysis results of different personnel.
Specifically, the data acquired by the BELT flight mode is adopted for analyzing the number of grassland caterpillars in the research, as shown in fig. 3, after field personnel completes BELT aerial observation in the field, information such as aerial photos, waypoints and airlines of each flight is uploaded to a server through FragMAP. Indoor analysts locate and analyze grassland caterpillar data in time based on a collaborative analysis platform, firstly, according to longitude and latitude position information recorded in a aerial photo attribute file and waypoint information recorded in FragMAP aerial photo software, utilizing DJILocator which is independently researched and developed by a team to enable aerial photos to correspond to the waypoints one by one, and naming the located aerial photos as 1-16 in sequence according to the waypoint sequence. And then, issuing two repeated analysis tasks on the Web end by the positioned aerial photos, simultaneously extracting the quantity of the caterpillars by different analysts by using a grassland caterpillars analysis system (webpage version), and comparing the analysis results of the grassland caterpillars of different personnel. If the analysis results are the same, outputting the data of the aerial photo grassland caterpillars, and if the analysis results are different, entering the next round of cyclic analysis until all the analysis results are consistent. Based on Mavic Zoom unmanned aerial vehicle 2 times Zoom can accurate obtain grassland caterpillar density in the sample land, the decision coefficient R 2 =0.99 (p < 0.001) between unmanned aerial vehicle observation value and ground observation data, root mean square error RMSE=1.76 head/m 2.
In one example, a method of grassland caterpillars metaplasia differentiation based on unmanned aerial vehicle aerial photography, the environmental factors include grassland type, weather, soil, remote sensing vegetation index and terrain (DEM). The meteorological environment comprises air temperature, precipitation and radiation, soil comprises soil type, soil sand grain and clay content, remote sensing vegetation index NDVI has a good correlation with grassland coverage and biomass, NDVI data are selected from MODIS 16d maximum synthetic vegetation index product MOD13Q1, data are downloaded from the United states geological exploration bureau, 2011-2021 is selected for 5-9 months, spatial resolution is 250m, track numbers are h25v05 and h26v05, and 216 scenery images are counted. The MODIS data is preprocessed in format, projection conversion and the like by using a reprojection tool (MODIS reprojection tools, MRT). And calculating characteristic variables such as a maximum value, a minimum value, a medium value, a mean value, a range, a std, a sum and the like of the MODIS NDVI vegetation index in the annual growth season (5-9 months) 2011-2021 by utilizing ARCGIS RASTER calculator tools.
The meteorological data come from a team of spring and aroma researchers of a national meteorological information center, mainly comprises a daily value data set of air temperature, precipitation, radiation and the like in 2011-2021, and the spatial resolution is 5km. Using ARCGIS RASTER calculator tools, the maximum, minimum, mean and sum values for air temperature, precipitation and radiation were calculated for the annual growth season of 2011-2021 (5-9 months).
The soil type data is downloaded from the national academy of sciences of China and the institute of resource research, the soil clay and sand content data is downloaded from the cold region and dry region scientific data center of the northwest ecological environment institute of China academy of sciences, the topographic data may be obtained through the International agricultural research consultation team spatial information alliance website.
The above data were uniformly projected Albers in ArcGIS software and resampled to grid images with a resolution of 250m (keeping each type of grid data with the same number of rows and columns) for later use as input in constructing and predicting a grassland caterpillar niche.
In one example, a study area grassland caterpillar ecological niche simulation model is constructed based on 2021 grassland caterpillar spatial distribution data and environmental factor data in combination with BIOMOD simulation software. And the occurrence probability spatial differentiation condition of the insect pests in the grasslands of the Qilin mountain country families in the recent 11 years is estimated by combining with environmental factors such as meteorological factors, soil, remote sensing vegetation indexes, terrain and the like in 2011-2021. And on the basis of the method, the plant-area caterpillars in the park of Qilishan China are divided.
Specifically, the constructing an ecological niche model by using the grassland caterpillar data and the environmental factors comprises the following steps:
And screening all the environmental factors by combining the Pearson correlation coefficient and the factor Importance index Importance. Before the ecological environment factors are used for constructing a model, in order to reduce the influence of the autocorrelation among the factors and the information redundancy on the running speed and the simulation precision of the model, the research combines Pearson correlation coefficient and factor Importance index Importance to screen all the factors. First, the importance of each factor to the detection target is tested using the idea and importance calculation function of leave-one-out cross-validation. Secondly, carrying out Pearson correlation analysis on all factors with importance values larger than 0.1, and reserving only 1 factor of 0.7, wherein an importance calculation formula is as follows:
Importance=1-cor (pred_ref, pred_buffered), where ref is the set containing all environmental factors; the shuffled is a set after randomly eliminating a single environmental factor; cor pred_ref is the prediction result of all environmental factors; pred_shuffled is the model prediction result after a factor is removed.
The results of the variable autocorrelation test are shown in fig. 4, and 12 variables of grassland type, soil type, elevation, radiation average, radiation maximum, surface soil sand content, precipitation average, precipitation maximum, surface cosmid content, deep cosmid content, NDVI average, and standard deviation were analyzed by Pearson correlation. The 12 environmental variable importance values and relative contribution rates are shown in fig. 5. Among all the screened environmental variables, the importance value of the radiation average value is the highest and is 0.282, and the relative contribution rate is 28.89%; the maximum value, average value and the importance value of the sand content of the surface layer are between 0.10 and 0.20, and the importance values of other variables are all lower than 0.10; the importance value of the soil type is the lowest, only 0.002, and the relative contribution rate is 0.20%.
BIOMOD together provide tens of species distribution models, such as generalized linear models (generalized linear model, GLM) and generalized enhanced regression models (generalized boosted regression models, GBM), for selection. In order to screen out the optimal ecological niche model, the study randomly divides grassland caterpillar observation data into two parts, wherein 70% of samples are used for training the ecological niche model, and the rest 30% of samples are used for verifying model accuracy. The optimal niche model is screened by using three indexes of Kappa, TSS (true SKILL STATISTICS) and AUC (area under curve), wherein Kappa is used for evaluating the consistency of the predicted results, and the TSS is calculated according to the following formula:
TSS＝Sensitivity+Specificity-1＝TPR-FPR
Wherein, sensitivity is Sensitivity, SPECIFICITY is specificity, TPR (true positive rate) true positive rate and FPR (falsepositive rate) false positive rate, the TSS value range is (0, 1), the closer the value is to 1, the larger the difference value between the true positive rate and the false positive rate is, and the better the model effect is; the AUC is defined as the area enclosed by the coordinate axes under the ROC curve (subject working characteristic curve), which is the comprehensive index reflecting the sensitivity and specificity continuous variables, and the range of values of the AUC reflecting the sensitivity to signal stimulus at each point on the curve is (0.5, 1), wherein the closer to 1 is the better the model prediction effect, and the closer to 0.5 is the model is the closer to random guess, and the model is the less prediction value.
Further, a method for dividing grassland caterpillars into suitable areas based on unmanned aerial vehicle aerial photography, wherein the dividing the grassland caterpillars suitable areas according to the spatial distribution probability comprises the following steps:
The grassland caterpillars are divided into different grades according to the size of the spatial distribution probability. Specifically, an optimal grassland caterpillar ecological level model is screened based on Kappa, TSS and AUC, and the potential spatial distribution probability of the grassland caterpillar in the Qinghai district of the Qilin mountain country family of the public garden in 2011-2021 is predicted by using the optimal ecological level model. When the annual potential distribution probability is more than 50%, the grassland pests are considered to be harmful, and a livability index IH is assigned as 1; otherwise, the value of 0 is assigned to the value that the formation cannot be considered as harmful. IH from 2011 to 2021 is subjected to space superposition operation, and the division rule of the grassland caterpillar suitable living area is shown in table 1. And grading the accumulated IH value in the last 10 years to obtain the grassland caterpillar habitat area distribution map.
TABLE 1 grassland pest control grading
The field observation result shows that the spatial distribution of the grassland caterpillars in the research area is large, 24 sampling points of the grassland caterpillars in all observation sampling points account for 5.77% of all monitoring sampling points, and the grassland caterpillars are scattered in the county of the source of the gate, the county of the Qili and the just-inspected county; among different monitoring points, the number difference of grassland caterpillars is larger, the minimum is only 1 head, and the maximum is 2046 heads. The number of the grassland caterpillars of 16 aerial photography sample lands in the same monitoring sample point is also large, and the number is up to 136, and the minimum number is 0. As for the investigation result of the unmanned aerial vehicle of the grassland caterpillars in 2021, the grassland caterpillars are mainly distributed in the wild cattle ditch villages and Muller towns in Qilin county, the Mongolian villages and Zhu Gu villages in Huang city of Menyuan county, and other areas.
In one example, the evaluating the ecological niche model according to the Kappa, TSS and AUC indexes, and screening out the optimal ecological niche model comprises: the RF model has the highest simulation precision on the grassland caterpillar ecological niche. Specifically, the model accuracy results are evaluated using test set data as shown in table 2:
TABLE 2 results of accuracy test of grassland caterpillar ecological niche model
Table 2 Accuracy test for the niche model of Gynaephora alpheraki
Among all the ecological niche models, models with Kappa coefficients greater than 0.5 are GLM, GBM and RF, and Kappa coefficients are 0.50, # 54 and 0.60 respectively; models with TSS greater than 0.6 were GLM, GBM, ANN and RF, respectively, with TSS of 0.76,0.69,0.68 and 0.75 in order; models with AUC greater than 0.7 were GLM, GBM, ANN, FDA, MARS and RF, respectively. And (3) synthesizing three kinds of evaluation indexes, wherein the simulation precision of the RF model on the grassland caterpillar ecological level is highest, and the RF model is an optimal prediction model. Its Kappa, TSS and AUC were 0.60, 0.75 and 0.93, respectively.
Further, based on the optimal grassland caterpillars ecological level model prediction model and 2011-2021 environmental factor dataset, the spatial distribution probabilities of 2011-2021 grassland caterpillars are respectively predicted, and as shown in fig. 6, the regions with higher occurrence probabilities of 2011-2021 grassland caterpillars are mainly distributed in the middle and southeast parts of the research area, and are mostly found in the county of the gate source, the county of the Qilin, the county of the just-scout and the county of Tianjun. In all years, the area of the region with the occurrence probability of grassland caterpillars between 0% and 20% is the largest, and the region accounts for 69.28% to 87.45% of the total area of the whole research area; secondly, the area with the occurrence probability of 20-30 percent accounts for 7.21-13.24 percent of the total area of the whole research; the occurrence probability of the grassland caterpillars is between 30 and 40 percent, and the proportion of more than 50 percent of the area to the total area of the whole research area is similar and is between 1.66 and 10.96 percent. In all probability types, the area proportion of the region with the occurrence probability of grassland caterpillars between 40% and 50% is minimum, and the region accounts for 0.97% to 3.72% of the total area of the whole research area. For the region with the occurrence probability of the grassland caterpillars being greater than 50%, the area of the region shows a gradually increasing change trend in 11 years, wherein the area in 2011 is the smallest, and the area in 2017 is the largest, and the area in 2011 is the largest, and the area in the whole research area is 10.96%. The area after 2015-2021 is more than 5% of the total area of the whole study area.
As shown in fig. 7, the space-time variation condition of the grassland caterpillars in the study area of 2011-2021 is that the grassland caterpillars are in small area ratio and are mainly distributed in the county of the gate source in the southeast of the study area (2011-2013). When the grassland caterpillars are large in harmful area, the variation trend gradually increases from southeast to northwest is shown. The number of Qilin counties, just-visited counties and Tianjun counties gradually increases from the source county to the northwest county. The spatial superposition operation is carried out on the region where the grassland caterpillars are harmful within 11 years, and the result is shown in figure 8. For 11 years, most areas of the study area do not have the phenomenon that grassland caterpillars are harmful (the occurrence year is 0), and the area of the grassland caterpillars accounts for 78.31% of the total area of the study; the area of the grassland caterpillars with the harmful year between 1 and 4 years accounts for 19.24 percent of the total area of the study area. The grassland caterpillars are less in proportion of the years with the harmful year being more than 5 and account for 2.45% of the total area of the whole research area, and are mainly distributed in eastern areas of the county of Menyuan, qilin county and Ganyuan Tianjun.
Further, the grassland caterpillar habitat is divided as shown in fig. 9, wherein the primary, secondary and tertiary habitat areas are smaller and occupy 14.68% of the total area of the study area. Is mainly distributed in eastern regions of research areas, including most of the areas of the county of the source of the door, the middle and southeast of the Qilin county, the middle of the just-visited county and the eastern region of Tianjun county. The areas of the four-level and five-level suitable living areas are larger, and account for 85.32% of the total area of the whole research area. Is mainly distributed in the western region of research area, including the most part of the German Ha city and Tianjun county, the North of Qili county, the south of the just-scouted county and the southwest of the Men Yuan county.
Furthermore, the unmanned aerial vehicle aerial photo taking and deep learning algorithm can replace a manual identification mode, so that the photo data analysis speed can be greatly improved, and errors in manual subjective judgment are reduced. Secondly, the unmanned aerial vehicle investigation data has a small age, the grassland caterpillar ecological level simulation model has a certain error, and the research result has a certain uncertainty, so that the unmanned aerial vehicle aerial photographing monitoring of grassland caterpillar is very necessary to develop long-time sequences, fixed points and repetition based on a large number of aerial photographing sample lands. In addition, the design of the investigation route is reasonable in the unmanned aerial vehicle investigation data process, the route should pass through all possible areas of grassland caterpillars, both the horizontal direction change and the vertical height change are required, and the monitoring work of the grassland caterpillars in future also needs to supplement and newly increase observation patterns on the basis of the existing monitoring points so as to grasp the space-time dynamic change information of the national park grassland caterpillars in a more detailed manner.
The invention obtains the optimal ecological niche simulation model of the grassland caterpillars in the research area based on unmanned aerial vehicle aerial observation grassland caterpillars data and corresponding vegetation, soil, climate and other environmental factors. On the basis, the space-time dynamic change condition of the ecological position of the grassland caterpillar in 2011-2021 is simulated and analyzed, so that a map of the grassland caterpillar suitable-living area of the research area is obtained. Studies have shown that the RF model is optimal for estimating the zoology of grassland caterpillars, with average values of Kappa, TSS and AUC of 0.60,0.75 and 0.93, respectively. In general, grassland caterpillars are harmful areas with a small area, accounting for 1.91 to 10.96 of the total area of the investigation region, but in recent years, the area of the grassland caterpillars is kept above 5% of the total area of the investigation region, which is a trend of increasing the harmful areas. The grassland caterpillars are apt to grow progressively from southeast to northwest, wherein the primary, secondary and tertiary regions are larger in proportion and account for 89.78% of the total area of the whole study.
In a second aspect, there is provided a grassland caterpillars metaplasia division system based on unmanned aerial vehicle aerial photography, the system comprising:
The grassland caterpillar data acquisition module is used for setting an observation sample point and acquiring grassland caterpillar data of the observation sample point by unmanned aerial vehicle aerial photography;
the environment factor acquisition module is used for acquiring environment factors corresponding to the observation sample points;
the ecological niche model building module is used for building an ecological niche model by utilizing the grassland caterpillar data and the environmental factors based on BIOMOD simulation software;
The ecological niche model screening module is used for evaluating the ecological niche model according to three indexes of Kappa, TSS and AUC and screening out an optimal ecological niche model;
And the grassland caterpillar suitable living area dividing module predicts the spatial distribution probability of the grassland caterpillar by utilizing the optimal ecological niche model and divides the grassland caterpillar suitable living area according to the spatial distribution probability.
In a third aspect, a terminal is provided, including a memory and a processor, where the memory stores computer instructions executable on the processor, and where the processor executes the computer instructions to perform the steps associated with any one of the grassland caterpillar beneficial differentiation methods.
The processor may be a single or multi-core central processing unit or a specific integrated circuit, or one or more integrated circuits configured to implement the invention.
Embodiments of the subject matter and the functional operations described in this specification can be implemented in: tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and structural equivalents thereof, or a combination of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by, or to control the operation of, data processing apparatus. Alternatively or additionally, the program instructions may be encoded on a manually-generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode and transmit information to suitable receiver apparatus for execution by data processing apparatus.
The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).
Processors suitable for the execution of a computer program include, by way of example, general and/or special purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read only memory and/or a random access memory. The essential elements of a computer include a central processing unit for carrying out or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks, etc. However, a computer does not have to have such a device. Furthermore, the computer may be embedded in another device, such as a mobile phone, a Personal Digital Assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device such as a Universal Serial Bus (USB) flash drive, to name a few.
While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features of specific embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. On the other hand, the various features described in the individual embodiments may also be implemented separately in the various embodiments or in any suitable subcombination. Furthermore, although features may be acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
Similarly, although operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In some cases, multitasking and parallel processing may be advantageous. Moreover, the separation of various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
The foregoing detailed description of the invention is provided for illustration, and it is not to be construed that the detailed description of the invention is limited to only those illustration, but that several simple deductions and substitutions can be made by those skilled in the art without departing from the spirit of the invention, and are to be considered as falling within the scope of the invention.
Claims (8)
1. The method for distinguishing grassland caterpillars suitable for living based on unmanned aerial vehicle aerial photography is characterized by comprising the following steps of:
setting an observation sample point, and acquiring grassland caterpillar data of the observation sample point by using unmanned aerial vehicle aerial photography;
Acquiring environmental factors corresponding to the observation sample points;
the setting of the observation sample point comprises:
on one hand, the generation and distribution rule of grassland caterpillars is considered; on the other hand, the spatial distribution of grassland caterpillars is obtained, and when field observation sample points are set, observation sample areas are set at intervals of 10km along main traffic roads and human reachable areas;
The size of each observation sample point is 250m multiplied by 250m, and each observation sample point is provided with a Grid flight route of 200m multiplied by 200m and 3 Belt flight routes of 40m multiplied by 40 m;
The obtaining of the grassland caterpillar data of the observation sample point by unmanned aerial vehicle aerial photography comprises the following steps:
Positioning and analyzing grassland caterpillars data in time based on a collaborative analysis platform, wherein different analysts simultaneously extract the caterpillars and compare the grassland caterpillars of different personnel; if the analysis results are the same, outputting the data of the aerial photo grassland caterpillars, and if the analysis results are different, entering the next round of cyclic analysis until all the analysis results are consistent;
Based on BIOMOD simulation software, constructing an ecological niche model by utilizing the grassland caterpillar data and the environmental factors;
the constructing an ecological niche model by utilizing the grassland caterpillar data and the environmental factors comprises the following steps:
Screening all environmental factors by combining Pearson correlation coefficients and factor Importance index Importance; the analysis of the Pearson correlation coefficient includes:
Passing the grassland type, soil type, elevation, radiation average, radiation maximum, surface soil sand content, precipitation average, precipitation maximum, surface cosmid content, deep cosmid content, NDVI average, and standard deviation through Pearson correlation analysis; among all the screened environmental variables, the importance value of the radiation average value is the highest, and the relative contribution rate is 28.89%; the maximum value, average value and the importance value of the sand content of the surface layer are between 0.10 and 0.20, and the importance values of other variables are all lower than 0.10; the importance value of the soil type is the lowest;
evaluating the ecological niche model according to three indexes of Kappa, TSS and AUC, and screening out an optimal ecological niche model;
and predicting the spatial distribution probability of the grassland caterpillars by using the optimal ecological niche model, and dividing the grassland caterpillars suitable living areas according to the spatial distribution probability.
2. The method for distinguishing grassland caterpillars from each other according to claim 1, wherein the acquiring the grassland caterpillars data of the observation sample by unmanned aerial vehicle comprises:
the aerial photographs, waypoints and route information for each flight are uploaded through FragMAP.
3. The method for distinguishing grassland caterpillars from each other according to claim 1, wherein the environmental factors include weather, soil, remote sensing vegetation index and topography.
4. The method for identifying a grassland caterpillar habitat based on unmanned aerial vehicle according to claim 1, wherein Kappa is used to evaluate the consistency of the predicted results, and the formula for calculating the TSS is as follows:
TSS＝Sensitivity+Specificity-1＝TPR-FPR
Wherein Sensitivity is Sensitivity, SPECIFICITY is specificity, TPR represents true positive rate, FPR represents false positive rate, and the TSS value range is (0, 1); the AUC is defined as the area enclosed by the coordinate axis under the ROC curve, and the value range of the AUC is (0.5, 1).
5. The method for dividing the grassland caterpillars into regions according to the space distribution probability, which is based on unmanned aerial vehicle aerial photography, according to claim 1, comprising:
the grassland caterpillars are divided into different grades according to the size of the spatial distribution probability.
6. The method for dividing grassland caterpillars into regions suitable for living based on unmanned aerial vehicle aerial photography according to claim 1, wherein the step of evaluating the ecological niche model according to three indexes of Kappa, TSS and AUC and screening out the optimal ecological niche model comprises the following steps:
The RF model has the highest simulation precision on the grassland caterpillar ecological niche.
7. Grassland caterpillar survival distinguishing system based on unmanned aerial vehicle takes photo by plane, its characterized in that, the system includes:
The grassland caterpillar data acquisition module is used for setting an observation sample point and acquiring grassland caterpillar data of the observation sample point by unmanned aerial vehicle aerial photography;
the environment factor acquisition module is used for acquiring environment factors corresponding to the observation sample points;
the setting of the observation sample point comprises:
on one hand, the generation and distribution rule of grassland caterpillars is considered; on the other hand, the spatial distribution of grassland caterpillars is obtained, and when field observation sample points are set, observation sample areas are set at intervals of 10km along main traffic roads and human reachable areas;
The size of each observation sample point is 250m multiplied by 250m, and each observation sample point is provided with a Grid flight route of 200m multiplied by 200m and 3 Belt flight routes of 40m multiplied by 40 m;
The obtaining of the grassland caterpillar data of the observation sample point by unmanned aerial vehicle aerial photography comprises the following steps:
Positioning and analyzing grassland caterpillars data in time based on a collaborative analysis platform, wherein different analysts simultaneously extract the caterpillars and compare the grassland caterpillars of different personnel; if the analysis results are the same, outputting the data of the aerial photo grassland caterpillars, and if the analysis results are different, entering the next round of cyclic analysis until all the analysis results are consistent;
the ecological niche model building module is used for building an ecological niche model by utilizing the grassland caterpillar data and the environmental factors based on BIOMOD simulation software;
the constructing an ecological niche model by utilizing the grassland caterpillar data and the environmental factors comprises the following steps:
Screening all environmental factors by combining Pearson correlation coefficients and factor Importance index Importance; the analysis of the Pearson correlation coefficient includes:
Passing the grassland type, soil type, elevation, radiation average, radiation maximum, surface soil sand content, precipitation average, precipitation maximum, surface cosmid content, deep cosmid content, NDVI average, and standard deviation through Pearson correlation analysis; among all the screened environmental variables, the importance value of the radiation average value is the highest, and the relative contribution rate is 28.89%; the maximum value, average value and the importance value of the sand content of the surface layer are between 0.10 and 0.20, and the importance values of other variables are all lower than 0.10; the importance value of the soil type is the lowest;
The ecological niche model screening module is used for evaluating the ecological niche model according to three indexes of Kappa, TSS and AUC and screening out an optimal ecological niche model;
And the grassland caterpillar suitable living area dividing module predicts the spatial distribution probability of the grassland caterpillar by utilizing the optimal ecological niche model and divides the grassland caterpillar suitable living area according to the spatial distribution probability.
8. A terminal comprising a memory and a processor, the memory having stored thereon computer instructions executable on the processor, wherein the processor, when executing the computer instructions, performs the steps associated with the grassland caterpillar method of distinguishing between grassland caterpillars of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211640504.0A CN116403125B (en) | 2022-12-20 | 2022-12-20 | Grassland caterpillar suitable living area dividing method, system and terminal based on unmanned aerial vehicle aerial photography |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211640504.0A CN116403125B (en) | 2022-12-20 | 2022-12-20 | Grassland caterpillar suitable living area dividing method, system and terminal based on unmanned aerial vehicle aerial photography |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116403125A CN116403125A (en) | 2023-07-07 |
| CN116403125B true CN116403125B (en) | 2024-05-14 |
Family
ID=87011137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211640504.0A Active CN116403125B (en) | 2022-12-20 | 2022-12-20 | Grassland caterpillar suitable living area dividing method, system and terminal based on unmanned aerial vehicle aerial photography |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116403125B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139717A (en) * | 2021-03-31 | 2021-07-20 | 北京农业信息技术研究中心 | Crop seedling condition grading remote sensing monitoring method and device |
| CN114049446A (en) * | 2021-10-08 | 2022-02-15 | 广州珠矶科技有限公司 | Soil pollutant distribution visualization method, device and medium for unmanned aerial vehicle and BIM |
| CN114065481A (en) * | 2021-10-14 | 2022-02-18 | 中国科学院地理科学与资源研究所 | Grassland data monitoring method and system based on big data and readable storage medium |
| KR20220049687A (en) * | 2020-10-14 | 2022-04-22 | 전주비전대학교산학협력단 | Evaluation method of vegetation index accuracy using low-cost drone optical sensor |
| CN115311343A (en) * | 2022-04-22 | 2022-11-08 | 花立民 | Grassland pest occurrence area investigation method based on multi-stage sampling |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3287007A1 (en) * | 2016-08-24 | 2018-02-28 | Bayer CropScience AG | Control of pests based on the prediction of infestation risks |
| US11328506B2 (en) * | 2019-12-26 | 2022-05-10 | Ping An Technology (Shenzhen) Co., Ltd. | Crop identification method and computing device |
-
2022
- 2022-12-20 CN CN202211640504.0A patent/CN116403125B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20220049687A (en) * | 2020-10-14 | 2022-04-22 | 전주비전대학교산학협력단 | Evaluation method of vegetation index accuracy using low-cost drone optical sensor |
| CN113139717A (en) * | 2021-03-31 | 2021-07-20 | 北京农业信息技术研究中心 | Crop seedling condition grading remote sensing monitoring method and device |
| CN114049446A (en) * | 2021-10-08 | 2022-02-15 | 广州珠矶科技有限公司 | Soil pollutant distribution visualization method, device and medium for unmanned aerial vehicle and BIM |
| CN114065481A (en) * | 2021-10-14 | 2022-02-18 | 中国科学院地理科学与资源研究所 | Grassland data monitoring method and system based on big data and readable storage medium |
| CN115311343A (en) * | 2022-04-22 | 2022-11-08 | 花立民 | Grassland pest occurrence area investigation method based on multi-stage sampling |
Non-Patent Citations (3)
| Title |
|---|
| Predicting the Distribution of Oxytropis ochrocephala Bunge in the Source Region of the Yellow River (China) Based on UAV Sampling Data and Species Distribution Model;Xinyu Zhang等;Remote sensing;20211217;第1-16页 * |
| 基于BIOMOD的黄河源区高原鼠兔潜在分布及其影响因子;杜嘉星;孙义;向波;陈建军;秦彧;侯秀敏;于红妍;宜树华;;草业科学;20190415(04);4+161-170 * |
| 应用BioMod集成多种模型研究物种的空间分布――以铁杉在中国的潜在分布为例;毕迎凤;许建初;李巧宏;Antoine Guisan;Wilfried Thuiller;Niklaus E.Zimmermann;杨永平;杨雪飞;;植物分类与资源学报;20131009(05);第113-121页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116403125A (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Silva et al. | Comparison of small-and large-footprint lidar characterization of tropical forest aboveground structure and biomass: a case study from Central Gabon | |
| Higgins et al. | Vegetation sampling and measurement | |
| Oindo et al. | Mapping habitat and biological diversity in the Maasai Mara ecosystem | |
| Fernández-Guisuraga et al. | Radiative transfer modeling to measure fire impact and forest engineering resilience at short-term | |
| Han et al. | Fuzzy clustering of maize plant-height patterns using time series of UAV remote-sensing images and variety traits | |
| Madsen et al. | Detecting shrub encroachment in seminatural grasslands using UAS LiDAR | |
| Fernández-Guisuraga et al. | Monitoring post-fire neighborhood competition effects on pine saplings under different environmental conditions by means of UAV multispectral data and structure-from-motion photogrammetry | |
| Herbei et al. | Processing and Use of Satellite Images in Order to Extract Useful Information in Precision Agriculture. | |
| Geng et al. | Migratory locust habitat analysis with PB-AHP model using Time-Series satellite images | |
| Jiang et al. | Monitoring the coastal environment using remote sensing and GIS techniques | |
| Dashpurev et al. | A cost-effective method to monitor vegetation changes in steppes ecosystems: A case study on remote sensing of fire and infrastructure effects in eastern Mongolia | |
| CN113570273B (en) | Spatialization method and system for irrigation farmland statistical data | |
| CN116403125B (en) | Grassland caterpillar suitable living area dividing method, system and terminal based on unmanned aerial vehicle aerial photography | |
| Khadka et al. | Forest and other land cover assessment in Nepal using Collect Earth | |
| Rode et al. | Habitat assessment and species niche modelling | |
| Schaepman et al. | River floodplain vegetation scenario development using imaging spectroscopy derived products as input variables in a dynamic vegetation model | |
| Zhang | Multi-scale vegetation-aeolian transport interaction in drylands: remote sensing and modeling | |
| Xiao et al. | 3D reconstruction and characterization of cotton bolls in situ based on UVA technology | |
| Kumar et al. | A study of spatio-temporal landuse/land cover change dynamics in Rudraprayag District,(Garhwal Himalaya) using Remote Sensing and GIS | |
| Nakajima | Estimating tree growth using crown metrics derived from LiDAR data | |
| Jande et al. | Prediction of Land Use Change in Katsina-Ala through a Geospatial Approach | |
| Guo et al. | Image-based estimation of crown volume of individual street trees by plane calculation of angle disparity | |
| Zhu et al. | The Structure of Potential Amur Tiger (Panthera Tigris Altaica) Habitats and Evaluation of Its Prey in Taipingou National Reserve (China) Based on Remote Sensing Data | |
| Hirvonen et al. | Assessing the influence of megafauna on multi-scale structural woody vegetation features in East African savannas using terrestrial and airborne laser scanning | |
| Adusei | Land Cover Change in a Savanna Environment. A Case Study of Bawku Municipal |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |