Forestry pest control modeling system and method
By establishing a spatial distribution model of pest populations and analyzing the trend change in their diffusion direction, combining the competitive relationship and diffusion constraints between biological populations, the diffusion problem of pest populations in the existing technology is solved, and a more accurate diffusion boundary prediction is achieved.
Patent Information
- Application Number
- CN202510139961.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-08
- Publication Date
- 2025-06-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The prior art is difficult to effectively model the dynamic modeling of pest populations under nonlinear ecological interactions, resulting in diverse and difficult to predict diffusion patterns.
By obtaining the spatial distribution data of pest populations in the target forestry area, establishing a spatial distribution model, analyzing the trend changes in the diffusion direction, extracting the competitive relationship between various biological populations at different simulation stages, determining the constraints of diffusion, and adjusting the diffusion boundary based on the simulation confidence.
Dynamic modeling of pest populations under nonlinear ecological interactions is achieved, and the accuracy and credibility of diffusion boundary prediction are improved.
Smart Images
Figure CN120105876A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of simulation modeling, and more specifically, to a forestry pest control modeling system and method. Background Art
[0002] Simulation modeling simulates the behavior of real systems by building mathematical or computer models. It is widely used in engineering, ecology, economics and other fields. In simulation modeling, it is necessary to abstract and simplify the system to be studied, extract the main characteristics and relationships of the system, and then build a model that can describe its behavior. By inputting initial conditions and control variables, the simulation model can dynamically evolve in the computer to simulate the performance of the system in different situations. In forest pest management, simulation modeling technology can simulate the spread process and population dynamics of pests to help formulate scientific prevention and control strategies.
[0003] The diffusion equation model is the most common model for the current dynamic modeling of forest pest population spread. The diffusion equation model is based on the diffusion law in physics and is used to describe the diffusion process of pests in space. It is applicable to simple situations under a uniform environment. However, the ecological interactions between forest pest populations and other species (such as predators, parasites, competitors, etc.) greatly affect the spread pattern of pest populations. Among them, ecological interactions include predation behavior, competitive pressure, symbiotic relationships, etc. Ecological interactions change continuously in time and space and usually have nonlinear characteristics, resulting in diverse spread patterns of pest populations. Therefore, how to achieve dynamic modeling of pest populations under nonlinear ecological interactions has become a difficult problem faced by the industry. Summary of the invention
[0004] The present application provides a forestry pest control modeling system and method, which can realize dynamic modeling of pest populations under nonlinear ecological interactions.
[0005] In a first aspect, the present application provides a method for dynamic modeling of forest pest population diffusion, which is used in a forest pest control modeling system to perform dynamic modeling of pest population diffusion, and the method comprises the following steps: Acquire spatial distribution data of harmful organism populations in a target forestry area, simulate the harmful organism populations based on the spatial distribution data, and obtain a spatial distribution model of the harmful organism populations; Performing trend analysis on the diffusion direction of harmful organisms at different boundary points in the spatial distribution model to obtain trend changes in the diffusion direction of harmful organisms at different boundary points in the spatial distribution model; Extract the competition relationship between various biological populations at different simulation stages from the competition data between various biological populations in the target forestry area, and determine the constraint conditions for the spread of harmful biological populations at different simulation stages based on all the competition relationships and the spread characteristics of harmful biological populations at different periods; Determine the simulation confidence of the diffusion boundary of the pest population at different simulation stages according to the trend change amount of the pest diffusion direction at different boundary points in the spatial distribution model and the constraint conditions of the pest population diffusion at different simulation stages; The spread boundaries of the pest population within the spatial distribution model are adjusted based on all simulation confidences.
[0006] In some embodiments, simulating the pest population based on the spatial distribution data to obtain a spatial distribution model of the pest population specifically includes: Preprocessing the spatial distribution data to obtain preprocessed spatial distribution data; According to the preset machine learning model, the pre-processed spatial distribution data is forward propagated to obtain simulated feedback information of the pest population at different times; The pest population is simulated and modeled by using the simulated feedback information of the pest population at different times and the pre-processed spatial distribution data to obtain a spatial distribution model of the pest population.
[0007] In some embodiments, performing trend analysis on the diffusion direction of harmful organisms at different boundary points in the spatial distribution model to obtain trend changes in the diffusion direction of harmful organisms at different boundary points in the spatial distribution model specifically includes: Determining a trend change curve of the pest population by the diffusion direction of the pests at different boundary points in the spatial distribution model; The trend change amount of the harmful organism diffusion direction at different boundary points in the spatial distribution model is determined according to the trend change curve.
[0008] In some embodiments, extracting the competition relationship between various biological populations at different simulation stages from the competition data between various biological populations in the target forestry area specifically includes: Cluster the competition data among various biological populations in the target forestry area to obtain multiple data clusters; The competition data among various biological populations in the target forestry area are segmented to obtain different data segments, and then the competition factors among various biological populations in the target forestry area in different time periods are determined; The competitive relationship between various biological populations in different simulation stages is determined based on all data clusters and the competition factors between various biological populations in the target forestry area under different time periods.
[0009] In some embodiments, the constraint conditions for the spread of the pest population at different simulation stages are determined based on all competition relationships and the spread characteristics of the pest population at different periods, specifically including: Determine the simulation state parameters of the pest population spread at different simulation stages through the spread characteristics of the pest population at different periods; The constraints of the pest population spread at different simulation stages are determined according to all the competition relationships and the simulation state parameters of the pest population spread at different simulation stages.
[0010] In some embodiments, determining the simulation confidence of the diffusion boundary of the pest population at different simulation stages according to the trend change amount of the pest diffusion direction at different boundary points in the spatial distribution model and the constraint conditions of the pest population diffusion at different simulation stages specifically includes: Determining multiple trend fluctuation coefficients according to a preset sliding window and the trend change amount of the harmful organism diffusion direction at different boundary points in the spatial distribution model; Determine the confidence value of the pest population spread trend during simulation through all trend fluctuation coefficients; The simulation confidence of the diffusion boundary of the pest population at different simulation stages is determined according to the confidence value of the diffusion trend of the pest population during simulation and the constraint conditions of the pest population diffusion at different simulation stages.
[0011] In some embodiments, adjusting the diffusion boundary of the pest population in the spatial distribution model based on all simulation confidences specifically includes: Determining a correction factor for the spread boundary of the pest population within the spatial distribution model based on all simulation confidences; The current diffusion boundary of the harmful organism population in the spatial distribution model is corrected by the correction factor.
[0012] In a second aspect, the present application provides a forestry pest control modeling system, the system comprising a dynamic modeling unit, the dynamic modeling unit comprising: An acquisition module is used to acquire spatial distribution data of harmful organism populations in a target forestry area, and simulate the harmful organism populations based on the spatial distribution data to obtain a spatial distribution model of the harmful organism populations; A processing module, used to perform trend analysis on the diffusion direction of harmful organisms at different boundary points in the spatial distribution model, and obtain the trend change amount of the diffusion direction of harmful organisms at different boundary points in the spatial distribution model; The processing module is also used to extract the competition relationship between various biological populations in different simulation stages from the competition data between various biological populations in the target forestry area, and determine the constraint conditions for the spread of harmful biological populations in different simulation stages according to all the competition relationships and the spread characteristics of harmful biological populations in different periods; The processing module is further used to determine the simulation confidence of the diffusion boundary of the harmful organism population at different simulation stages according to the trend change amount of the harmful organism diffusion direction at different boundary points in the spatial distribution model and the constraint conditions of the harmful organism population diffusion at different simulation stages; An execution module is used to adjust the diffusion boundary of the pest population in the spatial distribution model based on all simulation confidences.
[0013] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned method for dynamic modeling of forest pest population spread.
[0014] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for dynamic modeling of the spread of forest pest populations is implemented.
[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: In the forestry pest control modeling system and method provided in the present application, the spatial distribution data of the pest population in the target forestry area are first obtained, and the pest population is simulated based on the spatial distribution data to obtain a spatial distribution model of the pest population; a trend analysis is performed on the diffusion direction of the pests at different boundary points in the spatial distribution model to obtain the trend change amount of the pest diffusion direction at different boundary points in the spatial distribution model; the competition relationship between various biological populations in different simulation stages is extracted from the competition data between various biological populations in the target forestry area, and the constraint conditions for the diffusion of the pest population in different simulation stages are determined according to all the competition relationships and the diffusion characteristics of the pest population in different periods; the simulation confidence of the diffusion boundary of the pest population in different simulation stages is determined according to the trend change amount of the pest diffusion direction at different boundary points in the spatial distribution model and the constraint conditions for the diffusion of the pest population in different simulation stages; the diffusion boundary of the pest population in the spatial distribution model is adjusted based on all the simulation confidences.
[0016] It can be seen that in this application, the simulation confidence of the diffusion boundary of the pest population at different simulation stages can be determined according to the trend change amount of the pest diffusion direction at different boundary points in the spatial distribution model and the constraint conditions of the pest population diffusion at different simulation stages; wherein, firstly, the spatial distribution data of the pest population in the target forestry area is obtained, and the spatial distribution model of the pest population is constructed; secondly, the trend analysis of the diffusion direction of the pests at different boundary points in the spatial distribution model is carried out to obtain the trend change amount of the pest diffusion direction at different boundary points in the spatial distribution model, and the trend analysis can reflect the dynamic evolution characteristics of the pest diffusion in time and space, thereby providing parameters for simulating the diffusion of pests under nonlinear ecological interactions; then, the competitive relationship between various biological populations at different simulation stages is extracted, wherein the competitive relationship represents the simulation of the mutual competition between various biological populations due to resource competition in the simulation stage. The interaction parameters can simulate the mutual influence of different biological populations in resource utilization and ecological competition during the simulation process through competitive relationships. Further, the constraints on the spread of harmful populations at different simulation stages are determined, wherein the constraints represent the parameters that limit the diffusion process of harmful populations in nonlinear ecological interactions during the simulation stage, and the constraints help to more accurately reflect the nonlinear interactions and diffusion laws of harmful populations in complex ecosystems; then, the simulation confidence of the diffusion boundary of the harmful population at different simulation stages is determined, and the simulation confidence can evaluate the credibility of the diffusion boundary of the harmful population under nonlinear ecological interactions during the simulation stage; finally, the diffusion boundary of the harmful population in the spatial distribution model is dynamically adjusted based on all simulation confidences to improve the prediction accuracy of the model for the actual diffusion boundary; in summary, the scheme of the present application can realize dynamic modeling of harmful populations under nonlinear ecological interactions. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 is an exemplary flow chart of a method for modeling the dynamics of forest pest population spread according to some embodiments of the present application; Figure 2 is a schematic diagram of a process for determining the competitive relationship between various biological populations according to some embodiments of the present application; Figure 3 is a schematic diagram of a flow chart of determining a simulation confidence level of a diffusion boundary according to some embodiments of the present application; Figure 4 is a schematic diagram of the structure of a dynamic modeling unit according to some embodiments of the present application; Figure 5 It is a structural schematic diagram of a computer device for implementing a method for dynamic modeling of forest pest population spread according to some embodiments of the present application. DETAILED DESCRIPTION
[0018] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0019] refer to Figure 1 , which is an exemplary flow chart of a method for dynamic modeling of forestry pest population diffusion according to some embodiments of the present application. The method 100 for dynamic modeling of forestry pest population diffusion mainly includes the following steps: In step 101, the spatial distribution data of the harmful organism population in the target forestry area is obtained, and the harmful organism population is simulated based on the spatial distribution data to obtain a spatial distribution model of the harmful organism population.
[0020] It should be noted that the spatial distribution data in the present application consists of the location information, population size, and population density of pest populations in the target forestry area at one-hour intervals in the last month, where the location information contains the location coordinates of all pests in the pest population, the population size consists of the number of pests at different locations, and one moment represents one hour.
[0021] In specific implementation, the spatial distribution data of harmful biological populations in the target forestry area is obtained through the biological monitoring database of the target forestry area.
[0022] In some embodiments, the following steps may be used to simulate the pest population based on the spatial distribution data to obtain a spatial distribution model of the pest population: Preprocessing the spatial distribution data to obtain preprocessed spatial distribution data; According to the preset machine learning model, the pre-processed spatial distribution data is forward propagated to obtain simulated feedback information of the pest population at different times; The pest population is simulated and modeled by using the simulated feedback information of the pest population at different times and the pre-processed spatial distribution data to obtain a spatial distribution model of the pest population.
[0023] In a specific implementation, the spatial distribution data is preprocessed to obtain the preprocessed spatial distribution data, which can be achieved in the following manner, namely: the Pandas library in Python is used to interpolate the missing values in the spatial distribution data, and then the interpolated spatial distribution data is standardized to obtain the preprocessed spatial distribution data.
[0024] It should be noted that the machine learning model in the present application can train the convolutional neural network model through historical spatial distribution data, and use the model obtained after the training as the preset machine learning model, wherein the model weights are optimized through the back propagation algorithm. At the same time, the input data of the machine learning model is the location information of the pest population in the target forestry area, and the output data of the machine learning model is the predicted population size and predicted population density.
[0025] In specific implementation, forward propagation operation is performed on the preprocessed spatial distribution data according to the preset machine learning model to obtain simulated feedback information of the pest population at different times. The following method can be used for the implementation, namely: the position information at different times in the preprocessed spatial distribution data is input into the preset machine learning model, so as to output the predicted population size and predicted population density of the pest population at different times through the machine learning model, select a time as the selected time, subtract the predicted population size at the selected time from the population size at the selected time, and use the subtraction value as the population size bias value at the selected time, subtract the predicted population density at the selected time from the population density at the selected time, and use the subtraction value as the population density bias value at the selected time, further multiply the population density bias value at the selected time by the population density at the selected time, and use the multiplication value as the simulated feedback information of the pest population at the selected time, and continue to determine the simulated feedback information of the remaining pest populations at different times. Other methods can also be used in other embodiments, which will not be repeated here.
[0026] It should be noted that the simulation feedback information described in this application represents the feedback parameters for simulating the nonlinear diffusion of harmful organism populations during the simulation modeling process.
[0027] In specific implementation, the pest population is simulated and modeled through the simulated feedback information of the pest population at different times and the pre-processed spatial distribution data, and the spatial distribution model of the pest population can be implemented in the following way, namely: based on the cellular automaton model, the simulated feedback information of the pest population at different times is set as the diffusion condition of the cellular automaton model, wherein the diffusion condition is set such that if the simulated feedback information at the current moment is lower than the simulated feedback information at the previous and next moments, the pest will diffuse, otherwise, no processing is performed, and then MATLAB is used to perform cellular automaton simulation on the pre-processed spatial distribution data, and the model obtained after the simulation is used as the spatial distribution model of the pest population. Other methods can also be used in other embodiments, which are not limited here.
[0028] It should be noted that the spatial distribution model described in the present application represents a diffusion simulation model of the spatial distribution of pest populations, wherein there are multiple boundary points in the spatial distribution model, wherein the boundary points represent the positions of pests at the boundary at different times, and at the same time, each boundary point corresponds to the number of pests. As time goes by, the number of boundary points will also increase, and the number of pests will also increase.
[0029] In step 102, a trend analysis is performed on the spreading direction of harmful organisms at different boundary points in the spatial distribution model to obtain the trend change amount of the spreading direction of harmful organisms at different boundary points in the spatial distribution model.
[0030] In some embodiments, the trend analysis of the spread direction of harmful organisms at different boundary points in the spatial distribution model is performed to obtain the trend change amount of the spread direction of harmful organisms at different boundary points in the spatial distribution model. The following steps can be used to achieve this: Determining a trend change curve of the pest population by the diffusion direction of the pests at different boundary points in the spatial distribution model; The trend change amount of the harmful organism diffusion direction at different boundary points in the spatial distribution model is determined according to the trend change curve.
[0031] It should be noted that the diffusion direction in the present application refers to the direction in which the number of pests at the boundary point increases fastest, which can be achieved by taking the negative number of the gradient of the number of pests at the boundary point as the diffusion direction.
[0032] In specific implementation, first, the trend change curve of the pest population is determined by the diffusion direction of the pests at different boundary points in the spatial distribution model, which can be implemented in the following way, namely: the diffusion directions of the pests at different boundary points in the spatial distribution model are sorted in ascending order, and then the sorted sequence is fitted using an existing linear fitting algorithm (such as a least squares support vector machine algorithm), and the fitted curve is used as the trend change curve of the pest population, wherein the values on the trend change curve are all used as diffusion direction fitting values, and each diffusion direction fitting value corresponds to a diffusion direction. Other methods can also be used in other embodiments, which are not limited here.
[0033] It should be noted that the trend change curve described in the present application represents the change curve of the spread trend of the pest population.
[0034] In specific implementation, the trend change amount of the pest diffusion direction at different boundary points in the spatial distribution model is determined according to the trend change curve. The following method is used, namely: a boundary point is selected from the spatial distribution model as the selected boundary point, the pest diffusion direction at the selected boundary point is subtracted from the diffusion direction fitting value on the trend change curve corresponding to the pest diffusion direction at the selected boundary point, and the subtracted value is divided by the pest diffusion direction at the selected boundary point, and the divided value is used as the trend change amount of the pest diffusion direction at the selected boundary point, and the trend change amount of the pest diffusion direction at the remaining boundary points in the spatial distribution model is continued to be determined. Other methods can also be used in other embodiments, which will not be repeated here.
[0035] It should be noted that the trend change amount described in the present application represents the degree of change of the diffusion direction of the pests at the boundary point in the spatial dimension. The larger the trend change amount, the higher the degree of change of the diffusion direction of the pests at the boundary point in the spatial dimension, and vice versa.
[0036] In step 103, the competition relationship between various biological populations at different simulation stages is extracted from the competition data between various biological populations in the target forestry area, and the constraint conditions for the spread of harmful biological populations at different simulation stages are determined based on all the competition relationships and the spread characteristics of harmful biological populations at different periods.
[0037] In some embodiments, reference Figure 2 As shown, this figure is a schematic diagram of the process of determining the competition relationship between various biological populations in some embodiments of the present application. In this embodiment, the competition relationship between various biological populations at different simulation stages can be extracted from the competition data between various biological populations in the target forestry area, which can be achieved by the following steps: Cluster the competition data among various biological populations in the target forestry area to obtain multiple data clusters; The competition data among various biological populations in the target forestry area are segmented to obtain different data segments, and then the competition factors among various biological populations in the target forestry area in different time periods are determined; The competitive relationship between various biological populations in different simulation stages is determined based on all data clusters and the competition factors between various biological populations in the target forestry area under different time periods.
[0038] It should be noted that the competition data in this application represents data consisting of the intensity of resource competition for limited resources (such as food, water sources, habitats, etc.) among various biological populations at one-hour intervals in the last month, among which the quotient between the maximum number of individuals per unit area of different biological populations at the same moment and the amount of water per unit area can be taken as the resource competition intensity at the current moment.
[0039] In specific implementation, clustering the competition data among various biological populations in the target forestry area to obtain multiple data clusters can be achieved in the following manner, namely: using an existing clustering algorithm (such as DBSCAN) to cluster the competition data among various biological populations to obtain multiple clusters, and all the obtained clusters are used as data clusters. Other methods can also be used in other embodiments, which are not limited here.
[0040] It should be noted that the data cluster described in this application is a set consisting of resource competition intensities in competition data.
[0041] In addition, it should be noted that the simulation stage described in the present application represents a time period in the simulation process, where the time period is in units of one day, and each time period corresponds to a simulation stage.
[0042] In specific implementation, the competition data among various biological populations in the target forestry area are segmented to obtain different data segments, and then the competition factors among various biological populations in the target forestry area in different time periods are determined. This can be achieved in the following manner, namely: first, the competition data are divided into data segments of different time periods in chronological order, and for each data segment, the absolute value of the difference between the maximum value and the minimum value in the data segment is used as the competition factor among various biological populations in the target forestry area in the time period corresponding to the data segment, and then the competition factors among various biological populations in the target forestry area in different time periods are obtained. Other methods can also be used in other embodiments, which will not be repeated here.
[0043] It should be noted that the competition factors described in this application represent the intensity parameters of the demand for resources by various biological populations.
[0044] In specific implementation, the competition relationship between various biological populations in different simulation stages is determined based on all data clusters and the competition factors between various biological populations in the target forestry area in different time periods. This can be achieved in the following way, namely: calculating the distance between the cluster centers of each data cluster, then summing up all the distances, and using the summed value as the competition distance. Then, the competition factors between various biological populations in the target forestry area in different time periods are multiplied by the competition distances, and the multiplied values are used as the competition relationship between various biological populations in the simulation stages corresponding to different time periods. Other methods can also be used in other embodiments, which will not be repeated here.
[0045] It should be noted that the competition relationship described in the present application represents the parameters for simulating the interaction between various biological populations due to competition for resources during the simulation stage.
[0046] In some embodiments, the following steps may be used to determine the constraints on the spread of pest populations at different simulation stages based on all competition relationships and the spread characteristics of pest populations at different times: Determine the simulation state parameters of the pest population spread at different simulation stages through the spread characteristics of the pest population at different periods; The constraints of the pest population spread at different simulation stages are determined according to all the competition relationships and the simulation state parameters of the pest population spread at different simulation stages.
[0047] It should be noted that the diffusion characteristics in the present application refer to the characteristics of the spread of pest populations in forestry areas, which can be measured by the diffusion rate, wherein the diffusion rate represents the distance that the pest population spreads per unit time; in addition, it should be noted that the period in the present application refers to a period of three days, with a total of ten different periods.
[0048] In specific implementation, the simulation state parameters of the pest population diffusion at different simulation stages are determined by the diffusion characteristics of the pest population at different periods, which can be achieved in the following manner, namely: first, the diffusion characteristics of the pest population at different periods are averaged, and the obtained average is used as the diffusion equilibrium value of the pest population; then, the competition factors among various biological populations in the target forestry area at different time periods are obtained, and the competition factors among various biological populations in the target forestry area at different time periods are divided by the diffusion equilibrium value of the pest population respectively, and the values obtained by the division are used as the simulation state parameters of the pest population diffusion at the simulation stages corresponding to different time periods; other methods may also be used in other embodiments, which are not limited here.
[0049] It should be noted that the simulation state parameters described in the present application represent parameters for controlling the spread state of the harmful organism population during the simulation stage.
[0050] In specific implementation, the constraint conditions for the spread of pest populations at different simulation stages are determined based on all competition relationships and simulation state parameters of the spread of pest populations at different simulation stages, which can be achieved in the following manner, namely: first, all competition relationships are differentially processed, and then all values obtained after the differential processing are summed up, and the summed value is used as the competition differential value; then, the simulation state parameters of the spread of pest populations at different simulation stages are multiplied by the competition differential value, and the multiplied values are used as the constraint conditions for the spread of pest populations at different simulation stages. Other methods can also be used in other embodiments, which are not limited here.
[0051] It should be noted that the constraints described in the present application represent parameters that restrict the diffusion process of harmful organism populations in nonlinear ecological interactions during the simulation stage.
[0052] In step 104, the simulation confidence of the diffusion boundary of the pest population at different simulation stages is determined according to the trend change of the pest diffusion direction at different boundary points in the spatial distribution model and the constraint conditions of the pest population diffusion at different simulation stages.
[0053] In some embodiments, reference Figure 3 As shown, this figure is a schematic diagram of the process of determining the simulation confidence of the diffusion boundary in some embodiments of the present application. In this embodiment, the simulation confidence of the diffusion boundary of the pest population at different simulation stages is determined according to the trend change amount of the pest diffusion direction at different boundary points in the spatial distribution model and the constraint conditions of the pest population diffusion at different simulation stages. The following steps can be used to achieve it: First, in step 1041, a plurality of trend fluctuation coefficients are determined according to a preset sliding window and the trend change amount of the harmful organism diffusion direction at different boundary points in the spatial distribution model; Secondly, in step 1042, the confidence value of the spread trend of the harmful organism population during simulation is determined by all trend fluctuation coefficients; Then, in step 1043, the simulation confidence of the diffusion boundary of the pest population at different simulation stages is determined according to the confidence value of the diffusion trend of the pest population during simulation and the constraint conditions of the pest population diffusion at different simulation stages.
[0054] It should be noted that the sliding window described in the present application represents a window for processing all trend changes, and can be set using a fixed-length sequence, wherein the fixed length can be set using the value obtained by taking the square root of the total number of trend changes and rounding it down.
[0055] In specific implementation, multiple trend fluctuation coefficients are determined based on a preset sliding window and the trend change amount in the direction of pest diffusion at different boundary points in the spatial distribution model. The method is as follows: first, all trend change amounts are sorted in ascending order, and the sequence obtained after ascending order is used as a trend change sequence. Then, the trend change sequence is slid using a sliding window, wherein the sliding step size is set to one step, and the sliding is stopped when the sliding window aligns with the last trend change amount in the trend change sequence. For each step of the sliding window, the standard deviation of all trend change amounts covered by the sliding window is divided by the mean of all trend change amounts covered by the sliding window, and the value obtained by the division is used as the trend fluctuation coefficient of the sliding window at the current step, thereby obtaining multiple trend fluctuation coefficients. Other methods may also be used in other embodiments, which will not be repeated here.
[0056] It should be noted that the trend fluctuation coefficient described in this application reflects the degree of change in the diffusion direction.
[0057] In specific implementation, the confidence value of the spread trend of the pest population during simulation can be determined by all trend fluctuation coefficients in the following manner, namely: taking the average of all trend fluctuation coefficients, and using the obtained average as the confidence value of the spread trend of the pest population during simulation, wherein the confidence value of the spread trend represents the parameter value of the stability of the spread trend of the pest population during the simulation process. Other methods may also be used in other embodiments, which are not limited here.
[0058] In specific implementation, the simulation confidence of the diffusion boundary of the pest population at different simulation stages can be determined according to the confidence value of the diffusion trend of the pest population during simulation and the constraints on the diffusion of the pest population at different simulation stages. This can be achieved in the following way, namely: the constraints on the diffusion of the pest population at different simulation stages are multiplied by the confidence value of the diffusion trend of the pest population during simulation, and the multiplied values are used as the simulation confidence of the diffusion boundary of the pest population at different simulation stages. Other methods can also be used in other embodiments, which will not be repeated here.
[0059] It should be noted that the simulation confidence described in this application represents the parameter value for evaluating the credibility of the diffusion boundary of the pest population under nonlinear ecological interactions during the simulation stage, wherein the diffusion boundary represents the boundary formed by the position coordinates of the spread of the pest population during the simulation stage.
[0060] In step 105, the diffusion boundary of the pest population in the spatial distribution model is adjusted based on all simulation confidences.
[0061] In some embodiments, adjusting the diffusion boundary of the pest population in the spatial distribution model based on all simulation confidences can be achieved by the following steps: Determining a correction factor for the pest population spread boundary within the spatial distribution model based on all simulation confidence levels; The correction factor is used to correct the current diffusion boundary of the harmful organism population in the spatial distribution model.
[0062] In specific implementation, the correction factor of the pest population diffusion boundary in the spatial distribution model can be determined based on all simulation confidences in the following manner, namely: all simulation confidences are subjected to differential processing, and then the average of the values obtained after the differential processing is calculated, and the obtained average is used as the correction factor of the pest population diffusion boundary in the spatial distribution model. Other methods can also be used in other embodiments, which are not limited here.
[0063] In specific implementation, the correction of the current diffusion boundary of the pest population in the spatial distribution model by the correction factor can be achieved in the following manner, namely: obtaining the position coordinates of the current diffusion boundary of the pest population in the spatial distribution model, adding the correction factor to the position coordinates of the current diffusion boundary, and then obtaining the corrected diffusion boundary of the pest population. In other embodiments, other methods can also be used, which will not be repeated here.
[0064] In addition, in another aspect of the present application, in some embodiments, the present application provides a forestry pest control modeling system, the system comprising a dynamic modeling unit, reference Figure 4 , which is a schematic diagram of the structure of a dynamic modeling unit according to some embodiments of the present application, the dynamic modeling unit 400 includes: an acquisition module 401, a processing module 402 and an execution module 403, which are described as follows: Acquisition module 401, in this application, acquisition module 401 is mainly used to acquire spatial distribution data of harmful organism populations in a target forestry area, simulate the harmful organism populations based on the spatial distribution data, and obtain a spatial distribution model of the harmful organism populations; Processing module 402, in the present application, the processing module 402 is used to perform trend analysis on the diffusion direction of harmful organisms at different boundary points in the spatial distribution model, and obtain the trend change amount of the diffusion direction of harmful organisms at different boundary points in the spatial distribution model; It should be noted that the processing module 402 described in the present application is also used to extract the competition relationship between various biological populations at different simulation stages from the competition data between various biological populations in the target forestry area, and determine the constraint conditions for the spread of harmful biological populations at different simulation stages according to all the competition relationships and the spread characteristics of harmful biological populations at different periods; In addition, the processing module 402 in the present application is also used to determine the simulation confidence of the diffusion boundary of the harmful organism population at different simulation stages according to the trend change amount of the harmful organism diffusion direction at different boundary points in the spatial distribution model and the constraint conditions of the harmful organism population diffusion at different simulation stages; Execution module 403, in the present application, the execution module 403 is mainly used to adjust the diffusion boundary of the harmful organism population in the spatial distribution model based on all simulation confidences.
[0065] In addition, the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned method for dynamic modeling of forest pest population spread.
[0066] In some embodiments, reference Figure 5, which is a schematic diagram of the structure of a computer device for implementing a method for dynamically modeling the spread of forest pest populations according to some embodiments of the present application. The method for dynamically modeling the spread of forest pest populations in the above embodiments can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.
[0067] Processor 501 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more processors for controlling the execution of the method for dynamic modeling of forest pest population spread in the present application.
[0068] The communication bus 502 may be used to transmit information between the above-mentioned components.
[0069] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.
[0070] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The method described in the above method embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.
[0071] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.
[0072] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).
[0073] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.
[0074] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned method for dynamic modeling of forest pest population spread.
[0075] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.
[0076] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A method for dynamic modeling of forestry pest population diffusion, used in a forestry pest control modeling system for dynamic modeling of pest population diffusion, characterized in that: The method comprises the following steps: Acquire spatial distribution data of harmful organism populations in a target forestry area, simulate the harmful organism populations based on the spatial distribution data, and obtain a spatial distribution model of the harmful organism populations; Performing trend analysis on the diffusion direction of harmful organisms at different boundary points in the spatial distribution model to obtain trend changes in the diffusion direction of harmful organisms at different boundary points in the spatial distribution model; Extract the competition relationship between various biological populations at different simulation stages from the competition data between various biological populations in the target forestry area, and determine the constraint conditions for the spread of harmful biological populations at different simulation stages based on all the competition relationships and the spread characteristics of harmful biological populations at different periods; Determine the simulation confidence of the diffusion boundary of the pest population at different simulation stages according to the trend change amount of the pest diffusion direction at different boundary points in the spatial distribution model and the constraint conditions of the pest population diffusion at different simulation stages; The spread boundaries of the pest population within the spatial distribution model are adjusted based on all simulation confidences.
2. The method according to claim 1, characterized in that The spatial distribution model of the harmful organism population is obtained by simulating the harmful organism population based on the spatial distribution data, and specifically includes: Preprocessing the spatial distribution data to obtain preprocessed spatial distribution data; According to the preset machine learning model, the pre-processed spatial distribution data is forward propagated to obtain simulated feedback information of the pest population at different times; The pest population is simulated and modeled by using the simulated feedback information of the pest population at different times and the pre-processed spatial distribution data to obtain a spatial distribution model of the pest population.
3. The method according to claim 1, characterized in that The trend analysis is performed on the diffusion direction of the harmful organisms at different boundary points in the spatial distribution model to obtain the trend change amount of the diffusion direction of the harmful organisms at different boundary points in the spatial distribution model, which specifically includes: Determining a trend change curve of the pest population by the diffusion direction of the pests at different boundary points in the spatial distribution model; The trend change amount of the harmful organism diffusion direction at different boundary points in the spatial distribution model is determined according to the trend change curve.
4. The method according to claim 1, characterized in that The competition relationships among various biological populations at different simulation stages are extracted from the competition data among various biological populations in the target forestry area, including: Cluster the competition data among various biological populations in the target forestry area to obtain multiple data clusters; The competition data among various biological populations in the target forestry area are segmented to obtain different data segments, and then the competition factors among various biological populations in the target forestry area in different time periods are determined; The competitive relationship between various biological populations in different simulation stages is determined based on all data clusters and the competition factors between various biological populations in the target forestry area under different time periods.
5. The method according to claim 1, characterized in that According to all the competition relationships and the diffusion characteristics of the pest population at different times, the constraints on the spread of the pest population at different simulation stages are determined, including: Determine the simulation state parameters of the pest population spread at different simulation stages through the spread characteristics of the pest population at different periods; The constraints of the pest population spread at different simulation stages are determined according to all the competition relationships and the simulation state parameters of the pest population spread at different simulation stages.
6. The method according to claim 1, characterized in that The simulation confidence of the diffusion boundary of the pest population at different simulation stages is determined according to the trend change amount of the pest diffusion direction at different boundary points in the spatial distribution model and the constraint conditions of the pest population diffusion at different simulation stages, which specifically includes: Determining multiple trend fluctuation coefficients according to a preset sliding window and the trend change amount of the harmful organism diffusion direction at different boundary points in the spatial distribution model; Determine the confidence value of the pest population spread trend during simulation through all trend fluctuation coefficients; The simulation confidence of the diffusion boundary of the pest population at different simulation stages is determined according to the confidence value of the diffusion trend of the pest population during simulation and the constraint conditions of the pest population diffusion at different simulation stages.
7. The method according to claim 1, characterized in that Adjusting the diffusion boundary of the pest population in the spatial distribution model based on all simulation confidences specifically includes: Determining a correction factor for the pest population spread boundary within the spatial distribution model based on all simulation confidence levels; The correction factor is used to correct the current diffusion boundary of the harmful organism population in the spatial distribution model.
8. A forestry pest control modeling system, the system comprising a dynamic modeling unit, characterized in that: The dynamic modeling unit comprises: An acquisition module is used to acquire spatial distribution data of harmful organism populations in a target forestry area, and simulate the harmful organism populations based on the spatial distribution data to obtain a spatial distribution model of the harmful organism populations; A processing module, used to perform trend analysis on the diffusion direction of harmful organisms at different boundary points in the spatial distribution model, and obtain the trend change amount of the diffusion direction of harmful organisms at different boundary points in the spatial distribution model; The processing module is also used to extract the competition relationship between various biological populations in different simulation stages from the competition data between various biological populations in the target forestry area, and determine the constraint conditions for the spread of harmful biological populations in different simulation stages according to all the competition relationships and the spread characteristics of harmful biological populations in different periods; The processing module is further used to determine the simulation confidence of the diffusion boundary of the harmful organism population at different simulation stages according to the trend change amount of the harmful organism diffusion direction at different boundary points in the spatial distribution model and the constraint conditions of the harmful organism population diffusion at different simulation stages; An execution module is used to adjust the diffusion boundary of the pest population in the spatial distribution model based on all simulation confidences.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method for dynamic modeling of forest pest population spread described in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for dynamic modeling of forest pest population spread as described in any one of claims 1 to 7 is implemented.