Pest migration path simulation analysis method and system based on data analysis

Abstract

The invention discloses a pest migration path simulation analysis method and system based on data analysis, and relates to the technical field of agricultural pest control, and the main scheme is as follows: obtaining the historical migration path, geographic information and agricultural planting data of pests, and calculating the length, direction and regional attraction index of the migration path according to the historical migration path data; obtaining a historical migration path score; calculating the terrain and landform complexity according to the historical migratory flight geographic information data to obtain a historical migratory flight geographic information score; calculating a crop attraction index, a food resource stability index and an agroecological suitability index through historical migratory agricultural planting data, and further obtaining a historical migratory agricultural planting score; and constructing an initial model by taking the three scores as input features and the historical actual migration flight path as output features, carrying out iterative updating to obtain a standard model, inputting future score data into the standard model, and simulating the future migration flight path of the pests.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural pest control, and in particular to a pest migration path simulation analysis method and system based on data analysis. Background Art

[0002] Pest migration is a common phenomenon in agricultural production. Many pest species, such as locusts, rice planthoppers, armyworms, etc., have the ability to migrate long distances and will migrate on a large scale when the seasons change or the environmental conditions are unfavorable. This allows them to quickly appear in large numbers in new areas and cause serious damage to local crops. Due to the uncertainty of pest migration, it is difficult to accurately predict their paths, which poses a huge challenge to pest control. Accurately understanding the migration paths of pests is crucial for taking effective prevention and control measures in a timely manner. Traditional pest control methods mainly rely on experience and manual monitoring. It is difficult to predict the migration routes of pests in a timely and accurate manner. The model construction is not precise enough, the collected pest migration data is incomplete and single, and there is a lack of comprehensive data analysis. Decision support lacks scientific basis and dynamic updates, resulting in poor control effects and making it difficult to help agricultural management departments and farmers take corresponding prevention and control measures. Summary of the invention

[0003] 1. Technical issues to be resolved In view of the deficiencies in the prior art, the present invention provides a pest migration path simulation analysis method and system based on data analysis, which obtains historical migration path data, historical migration geographic information data and historical migration agricultural planting data of pests; obtains real-time path data, real-time geographic information data and real-time agricultural planting data, calculates corresponding scores based on these data, takes the score data as input features and the historical actual migration path as output features, constructs an initial model for pest migration path simulation, and continuously iterates and updates the model to obtain a standard model for pest migration path simulation, inputs the score data for a period of time in the future into the standard model, and simulates the migration path of pests in the future; solves the problems of inaccurate and incomplete collection of pest migration data and dynamic real-time updating of data; solves the problems of lack of comprehensive data analysis and lack of scientific basis for decision support, so that the prevention and control effect is greatly improved, which can help agricultural management departments and farmers to take corresponding prevention and control measures.

[0004] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for simulating and analyzing pest migration paths based on data analysis, comprising the following steps: Step 1: Obtain historical pest migration path data, historical migration geographic information data, and historical migration agricultural planting data; obtain real-time path data, real-time geographic information data, and real-time agricultural planting data; Step 2: Calculate the migration path length from the location where the pest is found to different migration areas based on the historical migration path data of the pests. and the direction of the flyway ; Calculate the regional attractiveness index of different migration areas based on historical migration route data and historical migration agricultural planting data ; According to the length of the migration path , direction of migration path and Regional Attractiveness Index Calculating historical flyway scores for different flyway regions ; Calculate the terrain complexity of pest migration to different migration areas based on historical migration geographic information data and landform complexity ; According to the complexity of the terrain and landform complexity Calculate the historical migration geographical information scores of different migration areas ; Calculate the crop attraction index of different migration areas based on historical migration agricultural planting data and food resource stability index ; Based on the crop attractiveness index and food resource stability index Calculation of agricultural ecological suitability index for different migration areas ; Based on the crop attractiveness index , Food Resource Stability Index and agroecological suitability index Calculate historical migration agricultural planting scores for different migration areas ; Step 3: Score the historical migration paths of different migration areas , Historical migration geographic information scoring and historical migratory agricultural planting scores As input features, the historical actual migration paths in the historical migration path data are used as output features to build an initial model for simulating pest migration paths. The initial model for simulating pest migration paths is iteratively updated through historical migration path data from different years to obtain a standard model for simulating pest migration paths. Step 4: Calculate the migration path score based on the acquired real-time path data, real-time geographic information data, and real-time agricultural planting data S. Migration geographic information score and Migratory Agriculture Planting Score , the migration path score S. Migration geographic information score and Migratory Agriculture Planting Score The data are input into the standard model for simulating pest migration routes to simulate the migration routes of pests in the future.

[0005] In the preferred embodiment of the above method for simulating and analyzing the migration path of pests based on data analysis: calculating the length of the migration path and the direction of the flyway The method is: Historical migration path data include the coordinate points of the migration paths to different migration areas ( , ); According to the coordinate point ( , ) Calculate the length of migration paths in different migration areas , the formula is as follows:

[0006] in,( , ) is the The coordinates of the coordinate points, ( , ) is the The adjacent coordinate points of a coordinate point, is the serial number of different coordinate points, and its value is ; is the total number of coordinates, which is a positive integer; Calculate the migration path directions of different migration areas based on historical migration path data , the formula is as follows: .

[0007] In the preferred embodiment of the above method for simulating and analyzing the migration path of pests based on data analysis: calculating the regional attraction index The method is: Historical migration path data also include food drivers for different migration areas and meteorological suitability factors ; Historical migration agricultural planting data including vegetation obstruction factors in different migration areas ; According to food drivers , meteorological suitability factor and vegetation obstruction factor Calculation of regional attractiveness index for different flyways , the formula is as follows: .

[0008] In the preferred embodiment of the above-mentioned pest migration path simulation analysis method based on data analysis: calculating the historical migration path score The method is: According to the length of the migration path , direction of migration path and Regional Attractiveness Index Calculating historical flyway scores for different flyway regions , the formula is as follows:

[0009] in, The length of the migration path The weight coefficient is 0.2 to 0.4; The direction of the migration path The weight coefficient is 0.3 to 0.4; Regional attractiveness index The weight coefficient is 0.3 to 0.4; and 1.

[0010] In the preferred embodiment of the above method for simulating and analyzing the migration path of pests based on data analysis: calculating the terrain complexity and landform complexity The method is: Historical migration geographic information data including the total area of ​​the study area in different migration areas , Altitude , Relative height of terrain relief , the proportion of terrain types in the region and the area of ​​terrain fragmentation ; The total area of ​​the study area according to different migration zones , Altitude , Relative height of terrain relief , the proportion of terrain types in the region and the area of ​​terrain fragmentation Calculating the terrain complexity of different flyways , the formula is as follows:

[0011] in, For the The altitude of the elevation sampling point, is the sequence number of the altitude of different sampling points, and its value is ; is the number of elevation sampling points above sea level, which is a positive integer; For the The relative height of the topographic relief feature points, is the relative height sequence of different terrain relief feature points, and its value is ; is the number of relative heights of terrain relief feature points, which takes a positive integer value; For the The proportion of each terrain type in the region. is the serial number of the area proportion of different terrain types in the region, and its value is , is the proportion of the area occupied by the terrain type in the region, and its value is a positive integer; yes The influence coefficient of For the The area of ​​the terrain + broken area, is the serial number of the area of ​​different terrain fragmentation areas, and its value is ; is the area of ​​terrain fragmentation, which takes a positive integer; Historical migration geographic information data also includes geomorphic features of different migration areas , the total length within the geomorphic feature area , distribution coefficient of micro-topography , the number of micro-landforms per unit area , the longest scale of large geomorphic units and the longest dimension of the study area ; According to the geomorphological characteristics of different migration areas , the total length within the geomorphic feature area , distribution coefficient of micro-topography , the number of micro-landforms per unit area , the longest scale of large geomorphic units and the longest dimension of the study area Calculate the geomorphic complexity of pest migration to different migration areas , the formula is as follows:

[0012] in, For the Types of landform features, is the serial number of different landform features, and its value is ; is the number of geomorphic features, which is a positive integer; For the The total length of the geomorphic features in the area; For the The distribution coefficient of micro-relief, is the serial number of different micro-relief distribution coefficients, and its value is ; is the number of micro-relief distribution coefficients, which takes a positive integer; For the The number of micro-landforms per unit area; For the The longest dimension of a large geomorphic unit, is the longest scale serial number of different large geomorphic units, and its value is ; It is the number of the longest scale of large geomorphic units and takes a positive integer.

[0013] In the preferred embodiment of the above-mentioned pest migration path simulation analysis method based on data analysis: calculating the historical migration geographic information score The method is: According to the complexity of the terrain and landform complexity Calculate the historical migration geographical information scores of different migration areas , the formula is as follows:

[0014] in, The terrain complexity The weight coefficient is between 0.2 and 0.4; The complexity of the landform The weight coefficient is between 0.6 and 0.8; and .

[0015] In the preferred embodiment of the above method for simulating and analyzing the migration path of pests based on data analysis: calculating the crop attraction index and food resource stability index The method is: Historical migration agricultural planting data also includes crop planting areas in different migration areas and the attractiveness coefficient of crop planting area to pests ; According to the crop planting area in different migration areas and the attractiveness coefficient of crop planting area to pests Calculation of crop attraction index for different migration areas , the formula is as follows:

[0016] in, For the The area of ​​agricultural crops planted, is the serial number of different crop planting areas, and its value is ; is the area of ​​crop planting, which is a positive integer; For the The attractiveness coefficient of the crop planting area to pests; is the attraction coefficient of crop planting area to pests Impact factor; Historical migration agricultural planting data also include the duration of crop planting in different migration areas and crop planting group suitability coefficient ; Duration of crop planting according to different migration areas and crop planting group suitability coefficient Calculation of food resource stability index in different migration areas , the formula is as follows:

[0017] in, For Time period to The duration of crop cultivation in a time period, and is the serial number of different time periods, and its value is ; The time period of the historical record, which is a positive integer; For Time period to The suitability coefficient of crop planting groups within a time period.

[0018] In the preferred embodiment of the above method for simulating and analyzing the migration path of pests based on data analysis: calculating the agricultural ecological suitability index The method is: According to the crop attractiveness index and food resource stability index Calculation of agricultural ecological suitability index for different migration areas , the formula is as follows:

[0019] in, It is the ecological balance index.

[0020] In the preferred embodiment of the above-mentioned method for simulating and analyzing the migration path of pests based on data analysis: calculating the historical migration agricultural planting score The method is: According to the crop attractiveness index , Food Resource Stability Index and agroecological suitability index Calculate historical migration agricultural planting scores for different migration areas , the formula is as follows:

[0021] in, Crop Attractiveness Index The weight coefficient is between 0.2 and 0.4; Food resource stability index The weight coefficient is between 0.2 and 0.3; Agroecological suitability index The weight coefficient is between 0.4 and 0.5; and .

[0022] On the other hand, the present invention also discloses a pest migration path simulation analysis system based on data analysis, which is used to implement the above-mentioned intelligent management method: comprising: Data collection module, used to obtain historical migration path data, historical migration geographic information data and historical migration agricultural planting data of pests; obtain real-time path data, real-time geographic information data and real-time agricultural planting data; The scoring calculation module is used to calculate the migration path length of the pest discovery location from different migration areas based on the historical migration path data of the pests. and the direction of the flyway ; Calculate the regional attractiveness index of different migration areas based on historical migration route data and historical migration agricultural planting data ; According to the length of the migration path , direction of migration path and Regional Attractiveness Index Calculating historical flyway scores for different flyway regions ; Calculate the terrain complexity of pest migration to different migration areas based on historical migration geographic information data and landform complexity ; According to the complexity of the terrain and landform complexity Calculate the historical migration geographical information scores of different migration areas ; Calculate the crop attraction index of different migration areas based on historical migration agricultural planting data and food resource stability index ; Based on the crop attractiveness index and food resource stability index Calculation of agricultural ecological suitability index for different migration areas ; Based on the crop attractiveness index , Food Resource Stability Index and agroecological suitability index Calculate historical migration agricultural planting scores for different migration areas ; Modeling module for scoring historical migration paths of different migration areas , Historical migration geographic information scoring and historical migratory agricultural planting scores As input features, the historical actual migration paths in the historical migration path data are used as output features to build an initial model for simulating pest migration paths. The initial model for simulating pest migration paths is iteratively updated through historical migration path data from different years to obtain a standard model for simulating pest migration paths. The path simulation module is used to calculate the migration path score based on the acquired real-time path data, real-time geographic information data and real-time agricultural planting data. S. Migration geographic information score and Migratory Agriculture Planting Score , the migration path score S. Migration geographic information score and Migratory Agriculture Planting Score The data are input into the standard model for simulating pest migration routes to simulate the migration routes of pests in the future.

[0023] (III) Beneficial effects The present invention provides a method and system for simulating and analyzing pest migration paths based on data analysis, which has the following beneficial effects: (1) By obtaining historical migration route data, historical migration geographic information data, and historical migration agricultural planting data of pests, and obtaining real-time route data, real-time geographic information data, and real-time agricultural planting data, the problem of incomplete and single data collection was solved.

[0024] (2) A series of calculations were performed using the pests’ historical migration path data, historical migration geographic information data, and historical migration agricultural planting data to obtain the historical migration path scores, historical migration geographic information scores, and historical migration agricultural planting scores for different migration areas. Based on these scoring data, the problem of a single analysis method that cannot effectively process complex data was solved, making the data more scientific and more effective in pest control.

[0025] (3) By taking the historical migration path scores, historical migration geographic information scores and historical migration agricultural planting scores of different migration areas as input features and the historical actual migration paths in the historical migration path data as output features, an initial model for simulating pest migration paths was constructed. The initial model for simulating pest migration paths was iteratively updated using the historical migration path data of different years to obtain a standard model for simulating pest migration paths. This solved the problem of inaccurate model construction and dynamic real-time data updates, and enabled comprehensive analysis of the data. Building an accurate standard model for simulating pest migration paths can provide a strong decision-making basis for pest control.

[0026] (4) By inputting the calculated data from real-time data into the standard model for simulating pest migration paths, the migration paths of pests in the future can be simulated, thus solving the problem of poor control effects. Various control measures can be deployed in a targeted manner before the pests arrive, and more scientific and reasonable agricultural pest control policies and emergency response plans can be formulated based on the simulation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 The present invention is a schematic diagram of the working steps of a pest migration path simulation analysis method based on data analysis. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] See also Figure 1 The present invention provides a method for simulating and analyzing pest migration paths based on data analysis, comprising the following steps: Step 1: Obtain historical pest migration path data, historical migration geographic information data, and historical migration agricultural planting data; obtain real-time path data, real-time geographic information data, and real-time agricultural planting data; When using, combine the content of step 1: By obtaining historical migration route data, historical migration geographic information data and historical migration agricultural planting data of pests; obtaining real-time route data, real-time geographic information data and real-time agricultural planting data, the problem of incomplete and single data collection is solved.

[0030] Step 2: Calculate the migration path length from the location where the pest is found to different migration areas based on the historical migration path data of the pests. and the direction of the flyway ; Calculate the regional attractiveness index of different migration areas based on historical migration route data and historical migration agricultural planting data ; According to the length of the migration path , direction of migration path and Regional Attractiveness Index Calculating historical flyway scores for different flyway regions .

[0031] Calculate the terrain complexity of pest migration to different migration areas based on historical migration geographic information data and landform complexity ; According to the complexity of the terrain and landform complexity Calculate the historical migration geographical information scores of different migration areas .

[0032] Calculate the crop attraction index of different migration areas based on historical migration agricultural planting data and food resource stability index ; Based on the crop attractiveness index and food resource stability index Calculation of agricultural ecological suitability index for different migration areas ; Based on the crop attractiveness index , Food Resource Stability Index and agroecological suitability index Calculate historical migration agricultural planting scores for different migration areas .

[0033] Step 2 includes the following: Step 201: Calculate the length of the migration path and the direction of the flyway The method is: Different migration areas are the maximum areas that can be shadowed by pest migration. According to the historical pest migration routes, the areas with possible pest migration involved in the routes are divided into multiple independent areas, which is convenient for early warning of different areas and timely reduction of economic losses caused by pests.

[0034] Historical migration path data include the coordinate points of the migration paths to different migration areas ( , ); It should be noted that the coordinate point ( , ) is centered on the monitoring site. When pests enter the monitoring range, the position of the pests is converted into relative coordinates through the angle and distance measurement function of the radar, thereby obtaining a series of coordinate points ( , ) to depict the migration paths of pests near monitoring sites.

[0035] According to the coordinate point ( , ) Calculate the length of migration paths in different migration areas , the formula is as follows:

[0036] in,( , ) is the The coordinates of the coordinate points, ( , ) is the The adjacent coordinate points of a coordinate point, is the serial number of different coordinate points, and its value is ; is the total number of coordinates, which is a positive integer; in the formula ( , ) corresponds to the last coordinate point ( , ); It should be noted that the principle of this formula is: based on the distance formula between two points, the length of the entire migration path is obtained by accumulating the distance between every two adjacent coordinate points. , which is of great significance for analyzing the migratory behavior and range of pests; the coordinate point ( , ) is obtained through monitoring records of historical migration routes of pests.

[0037] Calculate the migration path directions of different migration areas based on historical migration path data , the formula is as follows:

[0038] It should be noted that the principle of this formula is: two adjacent coordinate points ( , )and( , ), and the inverse tangent function is used to calculate the migration path direction of different migration areas The calculated value represents the flight direction of the pest from one coordinate point to the next during its migration.

[0039] Step 202: Calculate the regional attractiveness index The method is: Historical migration path data also include food drivers for different migration areas , meteorological suitability factor .

[0040] Historical migration agricultural planting data including vegetation obstruction factors in different migration areas .

[0041] According to food drivers , meteorological suitability factor and vegetation obstruction factor Calculation of regional attractiveness index for different flyways , the formula is as follows:

[0042] It should be noted that the principle of this formula is: driven by food factors , meteorological suitability factor and the reverse indicator of vegetation obstruction Multiply to get the regional attractiveness index of different migration areas ; When food-driven factors , meteorological suitability factor Large, and vegetation obstruction factor When the regional attractiveness index is small, The larger the value, the stronger the attraction of the area to pests. It refers to a quantitative indicator of the impact of food-related factors on the behavior of individual or group organisms in scenarios related to biological migration, such as the migration of pests between different regions. It scores the crop planting area, crop growth stage and crop type. For example, the larger the planting area, the higher the score is given, and the more the growth stage meets the feeding needs of pests, the higher the score is given. The crop type is scored according to the type of pest and the degree of its preference for crops. For example, when the pest is a locust, locusts like to eat wheat, corn, sorghum and rice, and are given a higher score. Sweet potato leaves, aquatic plants and soybeans that do not like to eat plants are given a low score. The three scores of crop planting area, crop growth stage and crop type are added together to obtain the food driving factor. ; Meteorological suitability factor It is used to measure the degree of meteorological conditions on pest migration activities; the impact of different temperatures, humidity, wind levels, etc. on pest migration is scored separately. Temperatures and humidity that are more suitable for pest migration, such as 20-35°C and humidity 60%-80%, are given high scores. The further away from this range, the lower the score. If the wind direction is consistent with the migration direction, it is recorded as a positive score, and the opposite is recorded as a negative score. The score is added or subtracted as the wind level changes, and then the three scores of the impact of different temperatures, humidity, wind levels, etc. on pest migration are added and summed to form a meteorological suitability factor. ; Vegetation obstruction factor A quantitative indicator used to measure the hindering effect of vegetation characteristics on pest migration activities, reflecting the degree of resistance or obstacle formed by factors such as vegetation type and distribution density on the movement of pests in space; the degree of hinderance of different vegetation types, densities and structures to pests is scored, such as trees can be given a lower score, herbs can be given a higher score, high density can be given a higher score, low density can be given a lower score, etc.; plants with patchy distribution can be given a higher score, strip distribution and uniform distribution can be given a lower score. The scores of the degree of hinderance of different vegetation types, densities and structures to pests are added together to obtain the vegetation hinderance factor .

[0043] Step 203: Calculate historical flyway scores The method is: According to the length of the migration path , direction of migration path and Regional Attractiveness Index Calculating historical flyway scores for different flyway regions , the formula is as follows:

[0044] in, The length of the migration path The weight coefficient is 0.2 to 0.4. Length of the migration path Determine the importance of The direction of the migration path The weight coefficient is 0.3 to 0.4. Direction of the flyway Determine the importance of Regional attractiveness index The weight coefficient is 0.3 to 0.4. Regional attractiveness index The importance of 1.

[0045] It should be noted that the principle of this formula is: Historical migration path score Used to measure the quality of historical migration routes in different migration areas; length of migration routes The larger the historical migration path score The higher the value, the more representative the length of the migration path is; the direction of the migration path The larger the historical migration path score The higher the value, the more representative the migration path direction is; Regional attractiveness index The larger the historical migration path score The higher it is, the more representative the regional attractiveness index is.

[0046] Step 204: Calculate terrain complexity and landform complexity The method is: Historical migration geographic information data including the total area of ​​the study area in different migration areas , Altitude , Relative height of terrain relief , the proportion of terrain types in the region and the area of ​​terrain fragmentation .

[0047] The total area of ​​the study area according to different migration zones , Altitude , Relative height of terrain relief , the proportion of terrain types in the region and the area of ​​terrain fragmentation Calculating the terrain complexity of different flyways , the formula is as follows:

[0048] in, For the The altitude of the elevation sampling point, is the sequence number of the altitude of different sampling points, and its value is ; is the number of elevation sampling points above sea level, which is a positive integer; For the The relative height of the topographic relief feature points, is the relative height sequence of different terrain relief feature points, and its value is ; is the number of relative heights of terrain relief feature points, which takes a positive integer value; For the The proportion of each terrain type in the region. is the serial number of the area proportion of different terrain types in the region, and its value is , is the proportion of the area occupied by the terrain type in the region, and its value is a positive integer; yes The influence coefficient of The proportion of terrain types in the region Determine the extent of impact; For the The area of ​​the terrain fragmentation area, is the serial number of the area of ​​different terrain fragmentation areas, and its value is ; It is the area of ​​terrain fragmentation, which takes a positive integer.

[0049] It should be noted that the total area of ​​the study area after normalization , Altitude , Relative height of terrain relief , the proportion of terrain types in the region and the area of ​​terrain fragmentation The above formula is used to calculate the total area of ​​the study area using the GIS data to determine the boundaries of the study area. Total area of ​​study area Refers to the total area of ​​the geographical area affected by the pest migration; altitude The total area of ​​the study area The altitude of different sampling points in the formula The part is used to calculate the sum of the squares of the altitude differences between adjacent elevation sampling points, which reflects the degree of altitude change in the region. The greater the altitude change, the more complex the terrain. The measured data is processed and analyzed through laser radar technology; in the formula The part is used to calculate the sum of the squares of the relative height differences between adjacent terrain undulation feature points, which reflects the degree of terrain undulation in the region. The greater the terrain undulation, the higher the complexity of the terrain. The proportion of the area occupied by the terrain type in the region It refers to the ratio of the area occupied by various types of terrain in a region, such as mountains, plateaus, plains, hills, basins, etc., to the total area of ​​the entire region. It is a quantitative indicator used to describe the characteristics of regional terrain composition. Part of it is used to consider the impact of different terrain types and their proportions on terrain complexity. yes The influence coefficient is determined according to the influence of different terrain types on terrain complexity; the area of ​​terrain fragmentation area It refers to the size of the area where the terrain is complex, discontinuous, and divided into multiple small pieces or fragments. The terrain fragmentation area is identified by observing satellite remote sensing images or aerial remote sensing images. This part is used to consider the impact of terrain fragmentation on terrain complexity. The larger the area and the greater the number of terrain fragmentation areas, the higher the terrain complexity.

[0050] Historical migration geographic information data also includes geomorphic features of different migration areas , the total length within the geomorphic feature area , distribution coefficient of micro-topography , the number of micro-landforms per unit area , the longest scale of large geomorphic units and the longest dimension of the study area .

[0051] According to the geomorphological characteristics of different migration areas , the total length within the geomorphic feature area , distribution coefficient of micro-topography , the number of micro-landforms per unit area , the longest scale of large geomorphic units and the longest dimension of the study area Calculate the geomorphic complexity of pest migration to different migration areas , the formula is as follows:

[0052] in, For the Types of landform features, is the serial number of different landform features, and its value is ; is the number of geomorphic features, which is a positive integer; For the The total length of the geomorphic features in the area; For the The distribution coefficient of micro-relief, is the serial number of different micro-relief distribution coefficients, and its value is ; is the number of micro-relief distribution coefficients, which takes a positive integer; For the The number of micro-landforms per unit area; For the The longest dimension of a large geomorphic unit, is the longest scale serial number of different large geomorphic units, and its value is ; It is the number of the longest scale of large geomorphic units and takes a positive integer.

[0053] It should be noted that the geomorphic features of different migration areas are normalized. , the total length within the geomorphic feature area , distribution coefficient of micro-topography , the number of micro-landforms per unit area , the longest scale of large geomorphic units and the longest dimension of the study area Carry out the above formula calculation; the principle of this formula is: The part is used to consider the influence of different landform features and their total length in the area on the landform complexity; landform complexity It is used to measure the complexity of regional landforms and reflects the comprehensive complexity of regional landforms. In GIS software, the terrain relief is calculated through neighborhood analysis, the size of an analysis window is determined, and the difference between the maximum and minimum values ​​in the window is calculated as the terrain relief value of the central pixel of the window. Then, the pixels of the entire study area are calculated to obtain the distribution value of the terrain relief. Geomorphic characteristics It refers to the characteristics of various forms on the earth's surface, including the undulating form of the terrain, slope and aspect and other landform type characteristics; through the professional geographic information system software to identify and classify landform features, it can integrate landform data from various sources, such as field measurement data, remote sensing data, geological maps, etc. After importing these data into GIS software, spatial analysis and visualization can be performed; the terrain analysis tools of the software can quickly calculate terrain characteristic parameters such as slope and aspect, and display them intuitively in the form of maps. Combined with geological map data, the landform change characteristics of different geological structure areas can be analyzed; the total length of the landform characteristic area It refers to the cumulative length of geomorphic elements such as mountains, river valleys, and coastlines in an area with specific geomorphic features. By measuring the horizontal angle, vertical angle, and distance of the target point, the position of the geomorphic feature point can be accurately determined. When measuring the geomorphic length, a series of measuring points are set along the geomorphic element, and the distance between adjacent points is measured using a total station. These distances are then added up to obtain the total length, thereby obtaining the total length within the geomorphic feature area. ; Distribution coefficient of micro-relief It is a quantitative indicator used to measure the distribution of micro-geomorphology in a specific area. By setting up multiple sample plots in the study area, the micro-geomorphology distribution coefficient of the entire area is estimated by counting the number, area or other relevant characteristics of the micro-geomorphology in the sample plots. For example, for the mound micro-geomorphology on a grassland, a square sample plot with a side length of 10 meters can be set. In each sample plot, the micro-geomorphology is recorded in detail, such as the number of mounds, the coverage area of ​​the mounds, etc. Assuming that in a total of m sample plots, the sum of micro-geomorphology related indicators is B, and the total area of ​​the sample plot is b, then the micro-geomorphology distribution coefficient is B / b; in the formula The part is used to consider the distribution of different micro-topography and its impact on the landform complexity in terms of its number per unit area; the number of micro-topography per unit area It refers to the number of micro-geomorphological individuals contained in the measurement unit of one square meter. It is an indicator used to quantify the spatial distribution density of micro-geomorphology, which can help us intuitively understand the density of micro-geomorphology in a certain area. By setting up multiple sample plots in the study area, the micro-geomorphology in the sample plots is counted, and then the number of micro-geomorphology per unit area is obtained based on the sample area and the number of sample plots. The longest scale of a large geomorphological unit is It refers to the linear distance in a geomorphic unit that can represent the maximum spatial extension range of the geomorphic unit. It is an important indicator for measuring the size of a geomorphic unit and reflects the maximum extension of the landform in space. It is determined by recording the coordinates of the measuring points through field measurement combined with remote sensing image analysis and using a real-time dynamic positioning system to calculate the distance between the two points. The largest part is used to consider the influence of the longest scale of large geomorphic units on geomorphic complexity. The larger the scale of large geomorphic units, the greater the influence on geomorphic complexity. It refers to the distance from one boundary point to the farthest boundary point within the entire geographical area designated for research. A number of important control points are selected on the boundary of the research area through a real-time dynamic positioning system, and the coordinate information of these points is recorded. After the measurement is completed, the coordinate data is imported into professional geographic information processing software. By calculating the distance between points or the curve distance along the boundary trajectory, the longest distance is obtained as the longest scale of the research area.

[0054] Step 205: Calculate the historical migration geographic information score The method is: According to the complexity of the terrain and landform complexity Calculate the historical migration geographical information scores of different migration areas , the formula is as follows:

[0055] in, The terrain complexity The weight coefficient is 0.2~0.4, according to The complexity of the terrain Determine the importance of The complexity of the landform The weight coefficient is 0.6 to 0.8. The complexity of the terrain The importance of .

[0056] It should be noted that the principle of this formula is: historical migration geographical information score Reflects the comprehensive evaluation of historical migration geographical information of different migration areas; terrain complexity The larger the value, the higher the historical migration geographical information score. The larger the value, the more representative the complex terrain is when evaluating the geographical information of pest migration. The larger the value, the higher the historical migration geographical information score. The larger it is, the more representative the landform complexity is when evaluating geographic information of pest migration.

[0057] Step 206: Calculate the crop attractiveness index and food resource stability index The method is: Historical migration agricultural planting data also includes crop planting areas in different migration areas and the attractiveness coefficient of crop planting area to pests .

[0058] According to the crop planting area in different migration areas and the attractiveness coefficient of crop planting area to pests Calculation of crop attraction index for different migration areas , the formula is as follows:

[0059] in, For the The area of ​​crops planted, is the serial number of different crops, and its value is ; is the area of ​​crop planting, which is a positive integer; For the The attractiveness coefficient of the planting area of ​​the crop to pests; is the attractiveness coefficient of crop planting area to pests The impact factor of The attractiveness coefficient of crop planting area to pests The degree of impact is determined.

[0060] It should be noted that the principle of this formula is: Crop attractiveness index The planting area of ​​each crop Multiply its attractiveness to pests Multiply by the impact factor The crop attractiveness index is obtained by summing the products of Reflects the overall attractiveness of crops to pests in a region; crop planting area It is an important factor in determining the attractiveness index of crops. The larger the planting area, the greater the potential attractiveness to pests. It is obtained through agricultural statistical data. The attractiveness coefficient of crop planting area to pests It is used to measure the comprehensive impact of each crop based on its planting area and its attractiveness to pests; a grade range is set based on the attractiveness of the crop's planting area to pests, and basic scores are assigned to different crops according to the pests' preferences, such as high basic scores for wheat and sorghum, and low basic scores for sweet potato leaves and soybeans. Then, points are assigned based on the size of the planting area. For example, the larger the planting area, the higher the score. After multiplying the two scores, the result is pre-processed for standardization and converted into a coefficient of 0-100 as the attractiveness coefficient of the crop planting area to pests. .

[0061] Historical migration agricultural planting data also include the duration of crop planting in different migration areas and crop planting group suitability coefficient .

[0062] Duration of crop planting according to different migration areas and crop planting group suitability coefficient Calculation of food resource stability index in different migration areas , the formula is as follows:

[0063] in, For Time period to The duration of crop cultivation in a time period, and is the serial number of different time periods, and its value is ; The time period of the historical record, which is a positive integer; For Time period to The suitability coefficient of the crop planting group within a time period.

[0064] It should be noted that the principle of this formula is: Food resource stability index The numerator is Time period to The duration of crop cultivation in a time period Suitability coefficient of planting group The double sum of the products, the denominator is the sum of the products from Time period to Duration of crop planting in a time period The double summation of the duration and suitability of crops in different time periods is taken into account, which can more accurately assess the stability of food resources in a region to pests; the duration of crop planting The suitability coefficient of crop planting groups is obtained by statistics of crop planting conditions in different time periods. It is obtained by comprehensively evaluating factors such as the preference of pests for crops in different time periods and the crop growth environment; and the duration of crop planting They jointly determine the food resource stability index. The higher the suitability coefficient, the higher the food resource stability.

[0065] Step 207: Calculate the agricultural ecological suitability index The method is: According to the crop attractiveness index and food resource stability index Calculation of agricultural ecological suitability index for different migration areas , the formula is as follows:

[0066] in, It is the ecological balance index.

[0067] It should be noted that the principle of this formula is: through the ecological balance index Food Resource Stability Index The average of the subtractions is multiplied by the crop attractiveness index Obtain the agricultural ecological suitability index of different migration areas ; Ecological balance index It represents the ecological balance of the area and is obtained by counting the number and distribution of different species through field surveys and sample collection.

[0068] Step 208: Calculate historical migration agricultural planting scores The method is: According to the crop attractiveness index , Food Resource Stability Index and agroecological suitability index Calculate historical migration agricultural planting scores for different migration areas , the formula is as follows:

[0069] in, Crop attractiveness index The weight coefficient is 0.2~0.4, according to Crop attractiveness index Determine the importance of Food resource stability index The weight coefficient is 0.2~0.3, according to Food resource stability index Determine the importance of Agroecological suitability index The weight coefficient is 0.4~0.5, according to Agroecological suitability index The importance of .

[0070] It should be noted that the principle of this formula is: Historical migration agricultural planting score Reflects the comprehensive evaluation of the historical migration agricultural planting situation in different migration areas; crop attraction index The larger the historical migration agricultural planting score The larger the value, the more representative the planting situation of crops that are more attractive to pests; Food resource stability index The larger the historical migration agricultural planting score The larger the value, the more representative the planting conditions of crops that are more attractive to pests. The larger the historical migration agricultural planting score The larger it is, the more representative it is of the planting conditions of crops that are more attractive to pests.

[0071] When used, combine the contents of step 201 to step 208: A series of calculations were performed through the historical migration route data of pests, historical migration geographic information data and historical migration agricultural planting data, and the historical migration route scores, historical migration geographic information scores and historical migration agricultural planting scores of different migration areas were obtained respectively. Based on these scoring data, the problem of the single analysis method and the inability to effectively process complex data was solved, which can make the data more scientific and more effective in pest control.

[0072] Step 3: Score the historical migration paths of different migration areas , Historical migration geographic information scoring and historical migratory agricultural planting scores The actual historical migration paths in the historical migration path data are used as input features and the output features to construct an initial model for simulating pest migration paths. The initial model for simulating pest migration paths is iteratively updated using historical migration path data from different years to obtain a standard model for simulating pest migration paths.

[0073] When using, combine the content of step 3: By taking the historical migration path scores, historical migration geographic information scores and historical migration agricultural planting scores of different migration areas as input features and the historical actual migration paths in the historical migration path data as output features, an initial model for simulating pest migration paths is constructed, and the initial model for simulating pest migration paths is iteratively updated through the historical migration path data of different years to obtain a standard model for simulating pest migration paths; the problems of inaccurate model construction and dynamic real-time data updating are solved, and the data can be comprehensively analyzed; agricultural management departments can rely on the analysis results of the standard model for simulating pest migration paths to provide a strong decision-making basis for pest control.

[0074] Step 4: Calculate the migration path score based on the acquired real-time path data, real-time geographic information data, and real-time agricultural planting data S. Migration geographic information score and Migratory Agriculture Planting Score S, score the migration path S. Migration geographic information score and Migratory Agriculture Planting Score S is input into the standard model for simulating pest migration routes to simulate the migration routes of pests in the future.

[0075] When using, combine the content of step 4: calculate the migration path score based on the acquired real-time path data, real-time geographic information data, and real-time agricultural planting data S. Migration geographic information score and Migratory Agriculture Planting Score S, score the migration path S. Migration geographic information score and Migratory Agriculture Planting Score S is input into the standard model for simulating pest migration routes to simulate the migration routes of pests in the future.

[0076] By inputting real-time data into the standard model for simulating pest migration routes, the migration routes of pests in the future are simulated, which solves the problem of poor prevention and control effects. Various prevention and control measures can be deployed in a targeted manner before the pests arrive, and more scientific and reasonable agricultural pest control policies and emergency response plans can be formulated based on the simulation results.

[0077] On the other hand, the present invention also discloses a pest migration path simulation analysis system based on data analysis, which is used to implement the above-mentioned pest migration path simulation analysis method, including: The data collection module is used to obtain historical migration path data, historical migration geographic information data and historical migration agricultural planting data of pests; obtain real-time path data, real-time geographic information data and real-time agricultural planting data.

[0078] The scoring calculation module is used to calculate the migration path length of the pest discovery location from different migration areas based on the historical migration path data of the pests. and the direction of the flyway ; Calculate the regional attractiveness index of different migration areas based on historical migration route data and historical migration agricultural planting data ; According to the length of the migration path , direction of migration path and Regional Attractiveness Index Calculating historical flyway scores for different flyway regions .

[0079] Calculate the terrain complexity of pest migration to different migration areas based on historical migration geographic information data and landform complexity ; According to the complexity of the terrain and landform complexity Calculate the historical migration geographical information scores of different migration areas .

[0080] Calculate the crop attraction index of different migration areas based on historical migration agricultural planting data and food resource stability index ; Based on the crop attractiveness index and food resource stability index Calculation of agricultural ecological suitability index for different migration areas ; Based on the crop attractiveness index , Food Resource Stability Index and agroecological suitability index Calculate historical migration agricultural planting scores for different migration areas .

[0081] Modeling module for scoring historical migration paths of different migration areas , Historical migration geographic information scoring and historical migratory agricultural planting scores As input features, the historical actual migration paths in the historical migration path data are used as output features to build an initial model for simulating pest migration paths. The initial model for simulating pest migration paths is iteratively updated through historical migration path data from different years to obtain a standard model for simulating pest migration paths. The path simulation module is used to calculate the migration path score based on the acquired real-time path data, real-time geographic information data and real-time agricultural planting data. S. Migration geographic information score and Migratory Agriculture Planting Score , the migration path score S. Migration geographic information score and Migratory Agriculture Planting Score The data are input into the standard model for simulating pest migration routes to simulate the migration routes of pests in the future.

[0082] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware or in combination with computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0083] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A pest migration path simulation analysis method based on data analysis, characterized in that: The following steps are involved: Step 1: Obtain historical pest migration route data, historical migration geographic information data, and historical migration agricultural planting data; Obtain real-time path data, real-time geographic information data, and real-time agricultural planting data; Step 2: Calculate the migration path length from the location where the pest is found to different migration areas based on the historical migration path data of the pests. and the direction of the flyway ; Calculate the regional attractiveness index of different migration areas based on historical migration route data and historical migration agricultural planting data ; According to the length of the migration path , direction of migration path and Regional Attractiveness Index Calculating historical flyway scores for different flyway regions ; Calculate the terrain complexity of pest migration to different migration areas based on historical migration geographic information data and landform complexity ; According to the complexity of the terrain and landform complexity Calculate the historical migration geographical information scores of different migration areas ; Calculate the crop attraction index of different migration areas based on historical migration agricultural planting data and food resource stability index ; Based on the crop attractiveness index and food resource stability index Calculation of agricultural ecological suitability index for different migration areas ; Based on the crop attractiveness index , Food Resource Stability Index and agroecological suitability index Calculate historical migration agricultural planting scores for different migration areas ; Step 3: Score the historical migration paths of different migration areas , Historical migration geographic information scoring and historical migratory agricultural planting scores As input features, the historical actual migration paths in the historical migration path data are used as output features to build an initial model for simulating pest migration paths. The initial model for simulating pest migration paths is iteratively updated through historical migration path data from different years to obtain a standard model for simulating pest migration paths. Step 4: Calculate the migration path score based on the acquired real-time path data, real-time geographic information data, and real-time agricultural planting data S. Migration geographic information score and Migratory Agriculture Planting Score , the migration path score S. Migration geographic information score and Migratory Agriculture Planting Score The data are input into the standard model for simulating pest migration routes to simulate the migration routes of pests in the future.

2. The method for simulating and analyzing pest migration paths based on data analysis according to claim 1, characterized in that: Calculating the length of the flyway and the direction of the flyway The method is: Historical migration path data include the coordinate points of the migration paths to different migration areas ( , ); According to the coordinate point ( , ) Calculate the length of migration paths in different migration areas , the formula is as follows: in,( , ) is the The coordinates of the coordinate points, ( , ) is the The adjacent coordinate points of a coordinate point, is the serial number of different coordinate points, and its value is ; is the total number of coordinates, which is a positive integer; Calculate the migration path directions of different migration areas based on historical migration path data , the formula is as follows: 。 3. The method for simulating and analyzing pest migration paths based on data analysis according to claim 2, characterized in that: Calculating the regional attractiveness index The method is: Historical migration path data also include food drivers for different migration areas and meteorological suitability factors ; Historical migration agricultural planting data including vegetation obstruction factors in different migration areas ; According to food driving factors , meteorological suitability factor and vegetation obstruction factor Calculation of regional attractiveness index for different flyways , the formula is as follows: 。 4. The method for simulating and analyzing pest migration paths based on data analysis according to claim 3, characterized in that: Calculating Historical Flyway Scores The method is: According to the length of the migration path , direction of migration path and Regional Attractiveness Index Calculating historical flyway scores for different flyway regions , the formula is as follows: in, The length of the migration path The weight coefficient is between 0.2 and 0.4; The direction of the migration path The weight coefficient is 0.3 to 0.4; Regional attractiveness index The weight coefficient is 0.3 to 0.4; and 1.

5. The method for simulating and analyzing pest migration paths based on data analysis according to claim 4, characterized in that: Calculating terrain complexity and landform complexity The method is: Historical migration geographic information data including the total area of ​​the study area in different migration areas , Altitude , Relative height of terrain relief , the proportion of terrain types in the region and the area of ​​terrain fragmentation ; The total area of ​​the study area according to different migration zones , Altitude , Relative height of terrain relief , the proportion of terrain types in the region and the area of ​​terrain fragmentation Calculating the terrain complexity of different flyways , the formula is as follows: in, For the The altitude of the elevation sampling point, is the sequence number of the altitude of different sampling points, and its value is ; is the number of elevation sampling points above sea level, which is a positive integer; For the The relative height of the topographic relief feature points, is the relative height sequence of different terrain relief feature points, and its value is ; is the number of relative heights of terrain relief feature points, which takes a positive integer value; For the The proportion of each terrain type in the region. is the serial number of the area proportion of different terrain types in the region, and its value is , is the proportion of the area occupied by the terrain type in the region, and its value is a positive integer; yes The influence coefficient of For the The area of ​​the terrain + broken area, is the serial number of the area of ​​different terrain fragmentation areas, and its value is ; is the area of ​​terrain fragmentation, which takes a positive integer; Historical migration geographic information data also includes geomorphic features of different migration areas , the total length within the geomorphic feature area , distribution coefficient of micro-topography , the number of micro-landforms per unit area , the longest scale of large geomorphic units and the longest dimension of the study area ; According to the geomorphological characteristics of different migration areas , the total length within the geomorphic feature area , distribution coefficient of micro-topography , the number of micro-landforms per unit area , the longest scale of large geomorphic units and the longest dimension of the study area Calculate the geomorphic complexity of pest migration to different migration areas , the formula is as follows: in, For the Types of geomorphic features, is the serial number of different landform features, and its value is ; is the number of geomorphic features, which is a positive integer; For the The total length of the geomorphic features in the area; For the The distribution coefficient of micro-relief, is the serial number of different micro-relief distribution coefficients, and its value is ; is the number of micro-relief distribution coefficients, which takes a positive integer; For the The number of micro-landforms per unit area; For the The longest dimension of a large geomorphic unit, is the longest scale serial number of different large geomorphic units, and its value is ; It is the number of the longest scale of large geomorphic units and takes a positive integer.

6. The method for simulating and analyzing pest migration paths based on data analysis according to claim 5, characterized in that: Calculate the historical migration geographic information score The method is: According to the complexity of the terrain and landform complexity Calculate the historical migration geographical information scores of different migration areas , the formula is as follows: in, The terrain complexity The weight coefficient is between 0.2 and 0.4; The complexity of the landform The weight coefficient is between 0.6 and 0.8; and .

7. The method for simulating and analyzing pest migration paths based on data analysis according to claim 6, characterized in that: Calculating the crop attractiveness index and food resource stability index The method is: Historical migration agricultural planting data also includes crop planting areas in different migration areas and the attractiveness coefficient of crop planting area to pests ; According to the crop planting area in different migration areas and the attractiveness coefficient of crop planting area to pests Calculation of crop attraction index for different migration areas , the formula is as follows: in, For the The area of ​​agricultural crops planted, is the serial number of different crop planting areas, and its value is ; is the area of ​​crop planting, which is a positive integer; For the The attractiveness coefficient of the crop planting area to pests; is the attraction coefficient of crop planting area to pests Impact factor; Historical migration agricultural planting data also include the duration of crop planting in different migration areas and crop planting group suitability coefficient ; Duration of crop planting according to different migration areas and crop planting group suitability coefficient Calculation of food resource stability index in different migration areas , the formula is as follows: in, For Time period to The duration of crop cultivation in a time period, and is the serial number of different time periods, and its value is ; The time period of the historical record, which is a positive integer; For Time period to The suitability coefficient of crop planting groups within a time period.

8. The method for simulating and analyzing pest migration paths based on data analysis according to claim 7, characterized in that: Calculation of agroecological suitability index The method is: According to the crop attractiveness index and food resource stability index Calculation of agricultural ecological suitability index for different migration areas , the formula is as follows: in, It is the ecological balance index.

9. The method for simulating and analyzing pest migration paths based on data analysis according to claim 8, characterized in that: Calculating Historical Flyway Agricultural Planting Scores The method is: According to the crop attractiveness index , Food Resource Stability Index and agroecological suitability index Calculate historical migration agricultural planting scores for different migration areas , the formula is as follows: in, Crop Attractiveness Index The weight coefficient is between 0.2 and 0.4; Food resource stability index The weight coefficient is between 0.2 and 0.3; Agroecological suitability index The weight coefficient is 0.3~0.4; and .

10. A pest migration path simulation analysis system based on data analysis, characterized in that: include: Data collection module, used to obtain historical migration route data, historical migration geographic information data and historical migration agricultural planting data of pests; Obtain real-time path data, real-time geographic information data, and real-time agricultural planting data; The scoring calculation module is used to calculate the migration path length of the pest discovery location from different migration areas based on the historical migration path data of the pests. and the direction of the flyway ; Calculate the regional attractiveness index of different migration areas based on historical migration route data and historical migration agricultural planting data ; According to the length of the migration path , direction of migration path and Regional Attractiveness Index Calculating historical flyway scores for different flyway regions ; Calculate the terrain complexity of pest migration to different migration areas based on historical migration geographic information data and landform complexity ; According to the complexity of the terrain and landform complexity Calculate the historical migration geographical information scores of different migration areas ; Calculate the crop attraction index of different migration areas based on historical migration agricultural planting data and food resource stability index ; Based on the crop attractiveness index and food resource stability index Calculation of agricultural ecological suitability index for different migration areas ; Based on the crop attractiveness index , Food Resource Stability Index and agroecological suitability index Calculate historical migration agricultural planting scores for different migration areas ; Modeling module for scoring historical migration paths of different migration areas , Historical migration geographic information scoring and historical migratory agricultural planting scores As input features, the historical actual migration paths in the historical migration path data are used as output features to build an initial model for simulating pest migration paths. The initial model for simulating pest migration paths is iteratively updated through historical migration path data from different years to obtain a standard model for simulating pest migration paths. The path simulation module is used to calculate the migration path score based on the acquired real-time path data, real-time geographic information data and real-time agricultural planting data. S. Migration geographic information score and Migratory Agriculture Planting Score , the migration path score S. Migration geographic information score and Migratory Agriculture Planting Score The data are input into the standard model for simulating pest migration routes to simulate the migration routes of pests in the future.

Images