Method and device for monitoring habitat suitability of insects
By obtaining ground survey data of insects and combining climate and non-climate variables, exploratory factor analysis and random forest algorithms are used to construct a habitat suitability monitoring model, which solves the problem of insufficient accuracy of insect habitat suitability monitoring in the existing technology, and realizes dynamics , high-precision monitoring effect.
Patent Information
- Application Number
- CN202411052959.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-19
Smart Images

Figure CN118981699A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of species environment research, and in particular to a method and device for monitoring the suitability of insect habitats. Background Art
[0002] Using species distribution models to monitor insect habitat suitability is a means of pest control. Species distribution models can combine species observation data with environmental variables to predict the potential distribution of species for habitat suitability assessment and risk zoning of invasive species.
[0003] In the prior art, there are methods that use machine learning algorithms to build species distribution models and combine remote sensing features with climate parameters to improve the accuracy of pest habitat suitability monitoring models. However, the life cycle of insects includes multiple stages, and they are also affected by multiple factors such as terrain and soil throughout their lives. Relying solely on climate parameters cannot fully reflect the habitat needs of insects. Therefore, how to dynamically and accurately monitor the habitat suitability of insects has become an urgent problem to be solved. Summary of the invention
[0004] Based on the above problems, the present application provides a method and device for monitoring the suitability of insect habitats, so as to construct an accurate insect habitat suitability monitoring model and realize dynamic and high-precision monitoring of insects.
[0005] The present application discloses a method for monitoring the suitability of insect habitats, the method comprising:
[0006] Based on the ground survey data of the target insect, obtaining the presence points and pseudo-absence points of the target insect;
[0007] Obtaining environmental variables corresponding to the existing point and the pseudo-absent point respectively; the environmental variables include climate variables and non-climate variables;
[0008] The climate variables were reconstructed through exploratory factor analysis;
[0009] A habitat suitability monitoring model is constructed based on the reconstructed climate variables and the non-climate variables to analyze the habitat suitability of the target insects.
[0010] Optionally, the obtaining of the presence points and pseudo-absence points of the target insect based on the ground survey data of the target insect includes:
[0011] Based on the ground survey data, acquiring the existence point;
[0012] The pseudo missing point is randomly generated outside a preset radius range with the coordinates of the existing point as the center.
[0013] Optionally, the step of respectively obtaining the environment variables corresponding to the existing point and the pseudo-absent point includes:
[0014] The environmental variables at the positions corresponding to the coordinates of the existing point and the coordinates of the pseudo-missing point are obtained according to the longitude and latitude.
[0015] Optionally, constructing a habitat suitability monitoring model based on the reconstructed climate variables and the non-climate variables includes:
[0016] constructing monitoring indicators based on the reconstructed climate variables and the non-climate variables;
[0017] Based on the monitoring indicators, the habitat suitability monitoring model is constructed using a random forest algorithm.
[0018] Optionally, after respectively obtaining the environmental variables corresponding to the existing point and the pseudo-absent point, the method further includes:
[0019] The environmental variables from multiple sources are resampled to unify the spatial resolution of the data.
[0020] Based on the above method for monitoring the suitability of insect habitats, the present application also discloses a device for monitoring the suitability of insect habitats, including: a point acquisition unit, a variable acquisition unit, a reconstruction unit and a modeling unit;
[0021] The point acquisition unit is used to acquire the presence points and pseudo absence points of the target insect based on the ground survey data of the target insect;
[0022] The variable acquisition unit is used to respectively acquire environmental variables corresponding to the existing point and the pseudo-absent point; the environmental variables include climate variables and non-climate variables;
[0023] The reconstruction unit is used to reconstruct the climate variables through exploratory factor analysis;
[0024] The modeling unit is used to construct a habitat suitability monitoring model based on the reconstructed climate variables and the non-climate variables to analyze the habitat suitability of the target insects.
[0025] Optionally, the point acquisition unit includes:
[0026] An existence point acquisition subunit, configured to acquire the existence point based on the ground survey data;
[0027] The pseudo missing point acquisition subunit is used to randomly generate the pseudo missing point outside a preset radius range with the coordinates of the existing point as the center.
[0028] Optionally, the variable acquisition unit is used to:
[0029] The environmental variables at the positions corresponding to the coordinates of the existing point and the coordinates of the pseudo-missing point are obtained according to the longitude and latitude.
[0030] Optionally, the modeling unit includes:
[0031] An indicator construction subunit, used for constructing monitoring indicators according to the reconstructed climate variables and the non-climate variables;
[0032] The modeling subunit is used to construct the habitat suitability monitoring model using a random forest algorithm based on the monitoring indicators.
[0033] Optionally, after respectively acquiring the environmental variables corresponding to the existing point and the pseudo-absent point, the device further includes:
[0034] The resampling unit is used to resample the environmental variables from multiple sources to unify the spatial resolution of the data.
[0035] The present application discloses a method and device for monitoring the suitability of insect habitats. Based on the ground survey data of the target insects, its existence points and pseudo-absence points are obtained. The climate variables and non-climate variables corresponding to the existence points and pseudo-absence points are obtained respectively. Taking into account the multicollinearity and model overfitting risks caused by the mutual correlation between climate variables, the present application reconstructs the climate variables through exploratory factor analysis, which has good interpretability while retaining the main information of the original climate variables, can discover the potential structure of the variables, help simplify the data and understand the relationship between the variables. Based on the reconstructed climate variables and non-climate variables, a habitat suitability monitoring model is constructed to dynamically and accurately monitor the habitat suitability of target insects with multi-source and rich factors. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0037] Figure 1 A schematic diagram of a flow chart of a method for monitoring insect habitat suitability disclosed in an embodiment of the present application;
[0038] Figure 2a A schematic diagram showing the distribution of the presence points and pseudo absence points disclosed in the embodiments of the present application in the African region;
[0039] Figure 2b This is a flow chart of a method for monitoring habitat suitability of fall armyworm in Africa disclosed in an embodiment of the present application;
[0040] Figure 2c This is a schematic diagram of the habitat suitability distribution of the fall armyworm in Africa from January to March 2023, as disclosed in the embodiments of the present application;
[0041] Figure 2d This is a schematic diagram of the habitat suitability distribution of the fall armyworm in Africa from April to June 2023, as disclosed in the embodiments of the present application;
[0042] Figure 2e This is a schematic diagram of the habitat suitability distribution of the African fall armyworm from July to September 2023 disclosed in the embodiments of the present application;
[0043] Figure 2f This is a schematic diagram of the habitat suitability distribution of the fall armyworm in Africa from October to December 2023, as disclosed in the embodiments of the present application;
[0044] Figure 2g This is a schematic diagram of the transition status of suitable and unsuitable habitats of the fall armyworm in Africa from January to April 2023 and the center movement status of the existence points disclosed in the embodiments of the present application;
[0045] Figure 2h This is a schematic diagram of the transition between suitable and unsuitable habitats of the fall armyworm in Africa from April to July 2023 and the center movement of the existence point disclosed in the embodiment of the present application;
[0046] Figure 2i This is a schematic diagram of the transition status of suitable and unsuitable habitats of the fall armyworm in Africa from July to October 2023 and the center movement status of the existence point disclosed in the embodiment of the present application;
[0047] Figure 2j This is a schematic diagram of the transition status of suitable and unsuitable habitats of the fall armyworm in Africa from October to December 2023 and the center movement status of the existence point disclosed in the embodiment of the present application;
[0048] Figure 3 This is a schematic diagram of the structure of a device for monitoring the suitability of insect habitats disclosed in an embodiment of the present application. DETAILED DESCRIPTION
[0049] Species distribution model (SDM) can use the distribution data of specific species (response variable) and environmental data (explanatory variable) to predict and estimate the potential distribution area of species. Therefore, it is currently widely used in research on conservation biology, ecological invasion, habitat suitability assessment, etc., and the use of machine learning algorithms to construct SDM for habitat suitability monitoring is receiving increasing attention.
[0050] This application takes the fall armyworm as an example. The life cycle of this species includes four stages: egg, larva, pupa, and adult. Its growth, development, reproduction, and migration are affected by factors such as host vegetation, soil, topography, and land use type. Short-term climate fluctuations also affect the behavior and population dynamics of the fall armyworm. Therefore, in order to fully and objectively reflect the habitat needs of the fall armyworm, and to predict the year-round distribution and seasonal outbreaks of the fall armyworm in terms of distribution, this application, based on the analysis of the life cycle of the fall armyworm, integrates multi-source earth observation data and constructs indicators for dynamic monitoring of the habitat suitability of the fall armyworm. And a habitat suitability monitoring model for the fall armyworm is constructed in combination with the random forest algorithm in machine learning, and its habitat suitability is analyzed in time periods (e.g., monthly), to achieve dynamic and high-precision monitoring of the fall armyworm.
[0051] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0052] Embodiment 1: This application discloses a method for monitoring the suitability of insect habitats.
[0053] For details, please refer to Figure 1 The method for monitoring the suitability of insect habitats disclosed in this embodiment includes the following steps:
[0054] Step 101: Based on the ground survey data of the target insect, the presence points and pseudo-absence points of the target insect are obtained.
[0055] In the method described in this embodiment, ground survey data of target insects (such as fall armyworm) provided by the Food and Agriculture Organization of the United Nations can be obtained, and these data can be pre-processed such as data cleaning to obtain existence points and pseudo-absence points. Among them, the existence points and pseudo-absence points are the coordinates (latitude and longitude) of the points, the existence points indicate that the target insect exists at the coordinates, and the pseudo-absence points indicate that the target insect does not exist at the coordinates.
[0056] As an optional method, after obtaining the existing points based on the ground survey data, pseudo missing points are randomly generated outside the preset radius range with the coordinates of the existing points as the center. The preset radius range can be set according to actual needs, and the range is not specifically limited here, as long as the pseudo missing points can be generated.
[0057] Step 102: Obtain the environmental variables corresponding to the existing point and the pseudo-absent point respectively.
[0058] In the method described in this embodiment, the environmental variables of the location are extracted according to the coordinates (latitude and longitude) of the existence point and the pseudo-absence point. The environmental variables may include climate variables (temperature, humidity, precipitation, etc.) and non-climate variables (vegetation, soil properties, slope, etc.).
[0059] As an optional method, taking the fall armyworm as an example, this embodiment obtains variables such as climate, vegetation, land use, altitude, and soil properties through the Google Earth Engine (GEE) cloud computing platform. Variables such as the air temperature 2 meters above the ground, the earth's surface temperature, the soil temperature 0 to 7 cm underground, wind force, precipitation, and the soil moisture content 0 to 7 cm underground are obtained through the ERA5-Land global data set. The vegetation normalization index provided by MOD13A3 V6.1 in the GEE cloud computing platform reflects the information of the host vegetation of the fall armyworm and can be used as an indicator to quantify the damage of pests to vegetation productivity.
[0060] In addition, land use, altitude, and slope variables may affect the occurrence and spread of fall armyworm by changing precipitation patterns and amounts, temperature dynamics, vegetation types, planting patterns, and the direction, angle, and intensity of the sun on the earth's surface. Therefore, this embodiment obtains land use types classified according to the annual International Geosphere-Biosphere Program IGBP (International Geosphere-Biosphere Program) based on MCD12Q1 v061 in the MODIS land cover type product. And obtain the altitude and slope from the digital elevation data provided by the Shuttle Radar Topography Mission SRTM (Shuttle Radar Topography Mission). Since soil properties are involved in affecting the survival of fall armyworm pupae and the emergence of adults, this embodiment obtains the sand content, clay content, and silt content of the soil from the global digital soil mapping system SoilGrids.
[0061] In the method described in this embodiment, as an optional method, after obtaining the environmental variables, the GEE cloud computing platform can also be used to resample the obtained multi-source data to unify the spatial resolution of the data. Specifically, a resampling of 1 km can be performed. The final environmental variables are shown in the following table:
[0062] Table 1 Environmental variables used in constructing the monthly habitat suitability monitoring index for Spodoptera frugiperda
[0063]
[0064]
[0065] Step 103: Reconstruct the climate variables through exploratory factor analysis.
[0066] In the method described in this embodiment, considering that the correlation between climate variables in environmental variables may lead to multicollinearity, which in turn causes the final constructed model to overfit, resulting in low prediction reliability, this embodiment reconstructs the climate variables through exploratory factor analysis.
[0067] Exploratory factor analysis is a statistical method used to discover the potential structure behind variables, help simplify data and understand the relationship between variables. Its core idea is to find the common variability (common factors) between variables, identify hidden, small number of potential factor structures, attribute common factors to potential factors, and achieve the purpose of data dimensionality reduction. Exploratory factor analysis can reveal the potential patterns and relationships between variables, that is, the structure and patterns behind the data. Exploratory factor analysis assumes that the observed data (i.e., climate variables) are composed of linear combinations of common factors and special factors. Its mathematical formula is as follows:
[0068] X=LF T +∈ (1)
[0069] Where X is the n*p observed data matrix, L is the n*f factor loading matrix, F is the p*f factor score matrix, f is the number of common factors, and ∈ is the n*p residual matrix.
[0070] In the method described in this embodiment, the factor loading matrix L represents the linear relationship between each variable and each common factor, and the factor score matrix F represents the score of each sample on each common factor. The residual matrix ∈ contains the part that cannot be explained by the factor, that is, the special factor.
[0071] Step 104: constructing a habitat suitability monitoring model based on the reconstructed climate variables and the non-climate variables to analyze the habitat suitability of the target insects.
[0072] In the method described in this embodiment, monitoring indicators are constructed based on the reconstructed climate variables and non-climate variables. Based on the monitoring indicators, a habitat suitability monitoring model is constructed using a random forest algorithm.
[0073] Random forest classifier is an integrated learning method, in which multiple decision trees are integrated, and the final prediction result is obtained by voting using self-service sampling and random feature selection. As an optional method, in the process of constructing the habitat suitability monitoring model in this embodiment, a five-fold cross validation is used, and the performance of the habitat suitability monitoring model is evaluated using accuracy, sensitivity, specificity, F1-score, area under the receiver operating characteristic curve (AUC), Kappa coefficient and true skill statistic (TSS). Among them, the five-fold cross validation results are shown in the following table:
[0074] Table 2 Model evaluation based on five-fold cross validation
[0075] Accuracy Sensitivity Specificity F1-score AUC Kappa TSS Fold-1 0.977 0.981 0.973 0.977 0.977 0.954 0.954 Fold-2 0.975 0.981 0.968 0.975 0.975 0.949 0.950 Fold-3 0.977 0.981 0.973 0.977 0.977 0.954 0.954 Fold-4 0.974 0.982 0.967 0.974 0.974 0.949 0.949 Fold-5 0.974 0.981 0.966 0.974 0.974 0.947 0.947 Average 0.975 0.981 0.969 0.975 0.975 0.951 0.951
[0076] As shown in Table 2, the habitat suitability monitoring model constructed by the method described in this example showed high accuracy (>0.9) in terms of accuracy, sensitivity, specificity, F1 score, AUC, Kappa and TSS.
[0077] The method described in this embodiment combines remote sensing data with high temporal resolution based on the analysis of the insect life cycle to propose a habitat suitability monitoring model that integrates multi-source earth observation data such as climate, land use, vegetation, and soil. Among them, the method for constructing habitat suitability monitoring indicators based on exploratory factor analysis retains the main information of the original climate variables while also having good interpretability. Model construction based on the random forest algorithm also helps to achieve dynamic and high-precision monitoring of insects.
[0078] Example 2: This application discloses another method for monitoring insect habitat suitability. The method described in this example is introduced for monthly habitat suitability monitoring of fall armyworm.
[0079] In the method described in this embodiment, Africa, which is severely affected by the fall armyworm, is used as the study area (25°22′W-63°30′E, 34°49′S-37°20′N). According to the ground survey data of the Food and Agriculture Organization of the United Nations from 2018 to 2022, the fall armyworm is currently widely distributed on the African continent, and western Africa and eastern Africa are the areas with the most dense distribution of fall armyworm. Three-quarters of Africa's area is distributed between the Tropic of Cancer and the Tropic of Capricorn, and the equator passes through it. The areas with an annual average temperature of more than 20°C in the continent account for about 95% of the continent's area. For fall armyworms that do not have dormancy, a warm climate is conducive to their survival and reproduction. At the same time, Africa has diverse climate types and extremely uneven precipitation distribution. The diversity of climate and landform types leads to large differences in the habitat suitability of fall armyworms in different regions of Africa in each month. The steps of the embodiment of the present application are described below in conjunction with the accompanying drawings in the embodiment of the present application:
[0080] Step 1: Based on the ground survey data of fall armyworm in Africa, obtain the presence points and pseudo-absence points of fall armyworm in Africa.
[0081] In the method described in this embodiment, the distribution of presence points and pseudo-absence points in Africa is as follows: Figure 2a shown.
[0082] Step 2: Obtain the environmental variables corresponding to the existence points and pseudo-missing points, and reconstruct the variables using exploratory factor analysis techniques.
[0083] Step 3: Based on the reconstructed environmental variables, a habitat suitability monitoring model is constructed to analyze the habitat suitability of the fall armyworm.
[0084] In the method described in this embodiment, Figure 2b As shown, when extracting environmental variables, the climate grid (i.e., environmental variables related to climate) and other grids (i.e., environmental variables unrelated to climate) are extracted separately. When constructing monitoring indicators, the obtained climate variables (such as the air temperature 2m above the ground, the surface temperature, etc.) are subjected to exploratory factor analysis, and the processed climate variables and other variables (such as the normalized vegetation index, land use, etc.) are used as monitoring indicators together. Subsequently, a habitat suitability monitoring model is constructed based on random forests, and the model is evaluated and optimized until the model meets the requirements for use. Finally, the habitat suitability monitoring model is put into use, and a monthly habitat suitability analysis is carried out to obtain the monthly habitat suitability distribution of the fall armyworm in Africa, as well as the transition between suitable and unsuitable habitats. Among them, Figure 2b The monthly habitat suitability distribution map at the bottom is composed of Figure 2c~2f constitute, Figure 2bThe transition diagram between the suitable and unsuitable areas at the bottom is Figure 2g~2j constitute, so Figure 2b The monthly habitat suitability distribution map and the latitude and longitude (horizontal and vertical coordinates) of the transition map between suitable and unsuitable habitats can be found in Figure 2c~2j .
[0085] In the method described in this embodiment, based on the habitat suitability monitoring model, the habitat suitability distribution of fall armyworm in Africa in 2023 was analyzed, and its temporal and spatial variation characteristics were obtained. The habitat suitability distribution of each month from January to March (from top to bottom) is as follows Figure 2c As shown in Figure 2, the habitat suitability distribution of each month from April to June (from top to bottom) is as follows Figure 2d As shown in Figure 2, the habitat suitability distribution of July to September (from top to bottom) is as follows Figure 2e As shown in Figure 2, the habitat suitability distribution of each month from October to December (from top to bottom) is as follows Figure 2f As shown. Among them, Figure 2c-2e Both can be used Figure 2f Legend in . Figure 2c~2f As shown in the figure, most of the ground survey points in 2023 are located in areas with a high habitat suitability index, which further verifies the effectiveness of the model. The areas with a high habitat suitability index for fall armyworms in Africa are mainly distributed in western Africa south of the Sahara Desert and eastern Africa. In the north of the Sahara Desert, the habitat suitability index in the Nile Delta region is also high in each month.
[0086] In the method described in this embodiment, according to the distribution of the habitat suitability of fall armyworm presence points and pseudo-absence points concentrated at the ends of 0 and 1, the habitat suitability index = 0.5 can be determined as the threshold for dividing suitable and unsuitable areas. The areas that change from unsuitable areas to suitable areas in each month indicate the hot spots for fall armyworm control. The transition status of suitable and unsuitable areas from January to February, February to March, and March to April (from top to bottom) is shown in the figure. Figure 2g As shown in Figure 2, the habitat suitability distribution of April to May, May to June, and June to July (from top to bottom) is as follows: Figure 2h As shown in Figure 2, the habitat suitability distribution from July to August, August to September, and September to October (from top to bottom) is as follows: Figure 2i As shown in Figure 2, the habitat suitability distribution from October to November and from November to December (from top to bottom) is as follows Figure 2j As shown. Among them, Figure 2g~2i Both can be used Figure 2j The legend in . Figure 2g~2jThe transition between suitable and unsuitable habitats of the fall armyworm in Africa from January to December 2023 and the movement of the center of the existence point determined by the standard deviation ellipse algorithm are shown. From January to February, a large area of new suitable habitats was added at the junction of South Africa, Botswana and Zimbabwe in southern Africa. From February to March, large areas of new suitable habitats appeared in western, central and eastern Africa, among which the suitable habitats of Ethiopia, Mozambique, Madagascar and Kenya, Uganda, Rwanda, Burundi and Tanzania around Lake Victoria increased significantly, while a large area at the junction of South Africa, Botswana and Zimbabwe in southern Africa changed from the original suitable habitat to the unsuitable habitat. From March to April, the suitable habitat in southern Africa continued to decrease, while the area of suitable habitats in western, central and eastern Africa continued to increase. From April to August, the area of suitable habitat in western Africa continued to expand, while the area of suitable habitat in eastern Africa decreased, and the center of existence moved northwest from eastern Africa to western Africa. From August to December, the area of suitable habitat in western Africa gradually decreased, and the center of existence moved southeast from western Africa to central Africa.
[0087] Based on the method for monitoring the suitability of insect habitats disclosed in the above embodiment, this embodiment correspondingly discloses a device for monitoring the suitability of insect habitats. Figure 3 , the device for monitoring the suitability of insect habitats comprises: a point acquisition unit 301, a variable acquisition unit 302, a reconstruction unit 303 and a modeling unit 304;
[0088] The point acquisition unit 301 is used to acquire the presence points and pseudo absence points of the target insect based on the ground survey data of the target insect;
[0089] The variable acquisition unit 302 is used to respectively acquire environmental variables corresponding to the existing point and the pseudo-absent point; the environmental variables include climate variables and non-climate variables;
[0090] The reconstruction unit 303 is used to reconstruct the climate variables through exploratory factor analysis;
[0091] The modeling unit 304 is used to construct a habitat suitability monitoring model based on the reconstructed climate variables and the non-climate variables to analyze the habitat suitability of the target insects.
[0092] Optionally, the point acquisition unit 301 includes:
[0093] An existence point acquisition subunit, configured to acquire the existence point based on the ground survey data;
[0094] The pseudo missing point acquisition subunit is used to randomly generate the pseudo missing point outside a preset radius range with the coordinates of the existing point as the center.
[0095] Optionally, the variable acquisition unit 302 is used to:
[0096] The environmental variables at the positions corresponding to the coordinates of the existing point and the coordinates of the pseudo-missing point are obtained according to the longitude and latitude.
[0097] Optionally, the modeling unit 304 includes:
[0098] An indicator construction subunit, used for constructing monitoring indicators according to the reconstructed climate variables and the non-climate variables;
[0099] The modeling subunit is used to construct the habitat suitability monitoring model using a random forest algorithm based on the monitoring indicators.
[0100] Optionally, after respectively acquiring the environmental variables corresponding to the existing point and the pseudo-absent point, the device further includes:
[0101] The resampling unit is used to resample the environmental variables from multiple sources to unify the spatial resolution of the data.
[0102] The embodiments in this specification are described in a progressive manner. As for the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the methods.
[0103] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0104] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0105] The features described in the embodiments of this specification can be replaced or combined with each other, so that professional and technical personnel in this field can implement or use the present application.
[0106] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for monitoring insect habitat suitability, characterized in that: include: Based on the ground survey data of the target insect, obtaining the presence points and pseudo absence points of the target insect; Obtaining environmental variables corresponding to the existing point and the pseudo-absent point respectively; the environmental variables include climate variables and non-climate variables; The climate variables were reconstructed through exploratory factor analysis; A habitat suitability monitoring model is constructed based on the reconstructed climate variables and the non-climate variables to analyze the habitat suitability of the target insects.
2. The method according to claim 1, characterized in that: The method of obtaining the presence points and pseudo-absence points of the target insects based on the ground survey data of the target insects includes: Based on the ground survey data, obtaining the existence point; The pseudo missing point is randomly generated outside a preset radius range with the coordinates of the existing point as the center.
3. The method according to claim 1, characterized in that The step of respectively obtaining the environment variables corresponding to the existing point and the pseudo-absent point includes: The environmental variables at the positions corresponding to the coordinates of the existing point and the coordinates of the pseudo-absent point are acquired according to the longitude and latitude.
4. The method according to claim 1, characterized in that: The step of constructing a habitat suitability monitoring model based on the reconstructed climate variables and the non-climate variables includes: constructing monitoring indicators based on the reconstructed climate variables and the non-climate variables; Based on the monitoring indicators, the habitat suitability monitoring model is constructed using a random forest algorithm.
5. The method according to claim 1, characterized in that After respectively obtaining the environmental variables corresponding to the existing point and the pseudo-absent point, the method further includes: The environmental variables from multiple sources are resampled to unify the spatial resolution of the data.
6. A device for monitoring the suitability of insect habitats, characterized in that: include: Point acquisition unit, variable acquisition unit, reconstruction unit and modeling unit; The point acquisition unit is used to acquire the presence points and pseudo absence points of the target insect based on the ground survey data of the target insect; The variable acquisition unit is used to respectively acquire environmental variables corresponding to the existing point and the pseudo-absent point; the environmental variables include climate variables and non-climate variables; The reconstruction unit is used to reconstruct the climate variables through exploratory factor analysis; The modeling unit is used to construct a habitat suitability monitoring model based on the reconstructed climate variables and the non-climate variables to analyze the habitat suitability of the target insects.
7. The device according to claim 6, characterized in that The point acquisition unit comprises: An existence point acquisition subunit, configured to acquire the existence point based on the ground survey data; The pseudo missing point acquisition subunit is used to randomly generate the pseudo missing point outside a preset radius range with the coordinates of the existing point as the center.
8. The device according to claim 6, characterized in that The variable acquisition unit is used to: The environmental variables at the positions corresponding to the coordinates of the existing point and the coordinates of the pseudo-absent point are acquired according to the longitude and latitude.
9. The device according to claim 6, characterized in that The modeling unit comprises: An indicator construction subunit, used for constructing monitoring indicators according to the reconstructed climate variables and the non-climate variables; The modeling subunit is used to construct the habitat suitability monitoring model based on the monitoring indicators using the random forest algorithm.
10. The device according to claim 6, characterized in that After respectively acquiring the environmental variables corresponding to the existing point and the pseudo-absent point, the device further includes: The resampling unit is used to resample the environmental variables from multiple sources to unify the spatial resolution of the data.
Citation Information
Patent Citations
Locust disaster potential high-risk area identification method, device and equipment and storage medium
CN114419431A
Insect migration prediction method and device
CN115544808A
Combined model method for predicting future suitable habitat change trend of cordyceps sinensis
CN117634182A
Ecological source place identification method based on habitat suitability, risk and quality framework
CN118313985A
Method for predicting suitability of wetland waterfowl habitat
CN118364939A
Cited By
Forestry pest early warning model construction system and method
CN120031676A
A forestry pest early warning model construction system and method
CN120031676B
Method and system for evaluating biological health condition of cultivated land soil based on exploratory factor analysis
CN120594804A
An arable land soil biological health condition evaluation method and system based on exploratory factor analysis
CN120594804B
