Grass-livestock balance evaluation method and device, computer equipment and storage medium

Abstract

The present application relates to grassland grazing management technical field, especially relates to a kind of grass-livestock balance evaluation method, based on the environmental variable data of the grid unit of target grassland and the corresponding category grass-livestock balance random forest regression model is carried out regression, obtain the grass-livestock balance correlation regression data of grid unit, according to grass-livestock balance correlation regression data corresponding category grass-livestock carrying capacity calculation is carried out, obtain grass-livestock carrying capacity index, on the scale of grid unit, the grass-livestock balance state of target grassland is dynamically monitored.Based on grass-livestock carrying capacity index, theoretical grass-livestock carrying capacity is calculated, obtain theoretical grass-livestock carrying capacity, combined with actual grass-livestock carrying capacity, grass-livestock balance evaluation is carried out, obtain grass-livestock balance evaluation result, can effectively reflect the change of grassland productivity pattern and carrying capacity pressure, further improve the precision and timeliness of grass-livestock management, provide important basis for the change of grassland carrying capacity and the evaluation of grass-livestock balance pressure.

Description

Technical Field

[0001] This invention relates to the field of grassland grazing management technology, and in particular to a method, apparatus, computer equipment, and storage medium for assessing grassland-livestock balance. Background Technology

[0002] Grasslands provide multiple ecosystem services, serving as the foundation for livestock development and a habitat for wildlife. In ecological protection and wildlife management, scientifically assessing grassland carrying capacity is crucial for the sustainable use of grassland resources. In recent years, remote sensing technology and machine learning methods have been widely applied to grassland carrying capacity research.

[0003] However, current grassland carrying capacity assessment technologies have significant limitations. They quantify forage supply solely by inverting grassland aboveground biomass or net primary productivity through remote sensing, equating biomass with carrying capacity as the core criterion. The indicators are too simplistic and neglect the comprehensive effect of multi-dimensional grassland-livestock balance correlation data on forage nutritional value. This makes it difficult to accurately estimate grassland carrying capacity, thus failing to guide precision grazing management and hindering the formulation of sustainable strategies. Summary of the Invention

[0004] Based on this, the purpose of this invention is to provide a method, apparatus, computer equipment, and storage medium for assessing grassland-livestock balance. The method involves performing regression analysis on environmental variable data of target grassland grid cells and corresponding categories of grassland-livestock balance random forest regression models to obtain grassland-livestock balance correlation regression data for each grid cell. Based on this correlation regression data, the carrying capacity of grassland for each category is calculated to obtain a grassland-livestock carrying capacity index. This allows for dynamic monitoring of the grassland-livestock balance status at the grid cell scale. Theoretical grassland-livestock carrying capacity is calculated based on the carrying capacity index to obtain the theoretical carrying capacity. Combined with the actual carrying capacity, a grassland-livestock balance assessment is conducted to obtain the assessment results. This effectively reflects changes in grassland productivity patterns and carrying capacity pressure, further improving the accuracy and timeliness of grassland-livestock management, and providing important evidence for assessing changes in grassland carrying capacity and grassland-livestock balance pressure.

[0005] In a first aspect, embodiments of this application provide a method for assessing grass-livestock balance, comprising the following steps:

[0006] Obtain environmental variable data for several categories of several grid cells of the target grassland within a target time period, wherein the environmental variable data includes several environmental variables;

[0007] The environmental variable data of several categories of several grid cells of the target grassland within the target time period are input into the preset corresponding category of grassland-livestock balance random forest regression model for regression, so as to obtain grassland-livestock balance correlation regression data of several categories of several grid cells of the target grassland within the target time period.

[0008] Based on the grassland-livestock balance correlation regression data of several categories, the grassland-livestock carrying capacity index of the corresponding categories is calculated to obtain the grassland-livestock carrying capacity index of several categories of several grid cells of the target grassland within the target time period.

[0009] The theoretical grass-livestock carrying capacity is calculated based on the grass-livestock carrying capacity index of several categories of several grid units of the target grassland within the target time period, so as to obtain the theoretical grass-livestock carrying capacity of the target grassland within the target time period.

[0010] Obtain the actual grass-livestock carrying capacity of the target grassland within the target time period; conduct a grass-livestock balance assessment based on the theoretical and actual grass-livestock carrying capacity of the target grassland within the target time period, and obtain the grass-livestock balance assessment result of the target grassland within the target time period.

[0011] Secondly, embodiments of this application provide a grass-livestock balance assessment device, comprising:

[0012] The data acquisition module is used to obtain environmental variable data of several categories of several grid cells of the target grassland within a target time period, wherein the environmental variable data includes several environmental variables;

[0013] The data regression module is used to input the environmental variable data of several categories of several grid cells of the target grassland within a target time period into a preset corresponding category of grassland-livestock balance random forest regression model for regression, so as to obtain grassland-livestock balance correlation regression data of several categories of several grid cells of the target grassland within a target time period.

[0014] The grass-livestock carrying capacity index calculation module is used to calculate the grass-livestock carrying capacity index of the corresponding category based on the grass-livestock balance correlation regression data of several categories, and obtain the grass-livestock carrying capacity index of several categories of several grid units of the target grassland within the target time period.

[0015] The theoretical grass-livestock carrying capacity calculation module is used to calculate the theoretical grass-livestock carrying capacity based on the grass-livestock carrying capacity index of several categories of several grid units of the target grassland within a target time period, and to obtain the theoretical grass-livestock carrying capacity of the target grassland within the target time period.

[0016] The grass-livestock balance assessment module is used to obtain the actual grass-livestock carrying capacity of the target grassland within a target time period; and to conduct a grass-livestock balance assessment based on the theoretical and actual grass-livestock carrying capacity of the target grassland within the target time period, thereby obtaining the grass-livestock balance assessment result of the target grassland within the target time period.

[0017] Thirdly, embodiments of this application provide a computer device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, it implements the steps of the grass-livestock balance assessment method as described in the first aspect.

[0018] Fourthly, embodiments of this application provide a storage medium storing a computer program that, when executed by a processor, implements the steps of the grass-livestock balance assessment method as described in the first aspect.

[0019] This application provides a method, apparatus, computer equipment, and storage medium for assessing grassland-livestock balance. It performs regression analysis based on environmental variable data of target grassland grid cells and corresponding categories of grassland-livestock balance random forest regression models to obtain grassland-livestock balance correlation regression data for each grid cell. Based on this correlation regression data, it calculates the grassland-livestock carrying capacity for each category to obtain a grassland-livestock carrying capacity index. This allows for dynamic monitoring of the grassland-livestock balance status at the grid cell scale. Theoretical grassland-livestock carrying capacity is calculated based on the carrying capacity index to obtain the theoretical carrying capacity. Combined with the actual carrying capacity, a grassland-livestock balance assessment is conducted to obtain the assessment results. This effectively reflects changes in grassland productivity patterns and carrying capacity pressure, further improving the accuracy and timeliness of grassland-livestock management, and providing important evidence for assessing changes in grassland carrying capacity and grassland-livestock balance pressure.

[0020] To better understand and implement this invention, the following detailed description is provided in conjunction with the accompanying drawings. Attached Figure Description

[0021] Figure 1 A flowchart illustrating a grass-livestock balance assessment method provided in one embodiment of this application;

[0022] Figure 2 A flowchart illustrating step S6 of the grass-livestock balance assessment method provided in another embodiment of this application;

[0023] Figure 3 This is a flowchart illustrating step S3 of a grass-livestock balance assessment method provided in one embodiment of this application.

[0024] Figure 4 This is a flowchart illustrating step S4 of a grass-livestock balance assessment method provided in one embodiment of this application.

[0025] Figure 5 This is a flowchart illustrating step S42 of the grass-livestock balance assessment method provided in one embodiment of this application;

[0026] Figure 6 This is a flowchart illustrating step S5 of a grass-livestock balance assessment method provided in one embodiment of this application.

[0027] Figure 7 A flowchart illustrating step S5 of the grass-livestock balance assessment method provided in yet another embodiment of this application;

[0028] Figure 8 This is a schematic diagram of the structure of a grass-livestock balance assessment device provided in one embodiment of this application;

[0029] Figure 9 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. Detailed Implementation

[0030] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0031] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0032] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0033] Please see Figure 1 , Figure 1 The following is a flowchart illustrating a grass-livestock balance assessment method provided in one embodiment of this application. The method includes the following steps:

[0034] S1: Obtain environmental variable data for several categories of several raster cells of the target grassland within the target time period.

[0035] The subject of the grass-livestock balance assessment method is the assessment equipment of the grass-livestock balance assessment method (hereinafter referred to as assessment equipment). In an optional embodiment, the assessment equipment can be a computer device, a server, or a server cluster composed of multiple computer devices.

[0036] In this embodiment, the evaluation device obtains environmental variable data for several categories of several grid cells of the target grassland within a target time period. The environmental variable data includes several environmental variables. Specifically, the several categories of environmental variable data include environmental variable data corresponding to aboveground biomass, environmental variable data corresponding to crude protein, and environmental variable data corresponding to net energy.

[0037] S2: Input the environmental variable data of several categories of several grid cells of the target grassland within the target time period into the preset corresponding category of grassland-livestock balance random forest regression model for regression, and obtain grassland-livestock balance correlation regression data of several categories of several grid cells of the target grassland within the target time period.

[0038] In this embodiment, the evaluation device inputs environmental variable data of several categories from several grid cells of the target grassland within a target time period into a preset, corresponding category of grassland-livestock balance random forest regression model for regression analysis. This yields grassland-livestock balance correlation regression data for several categories from several grid cells of the target grassland within the target time period. The grassland-livestock balance correlation regression data includes aboveground biomass regression data, crude protein regression data, and net energy regression data. The device dynamically monitors the amount and quality of forage grasses, as well as the number of livestock and ungulate wild herbivores in the target grassland at the grid cell scale, to conduct real-time assessment of the grassland-livestock balance status.

[0039] In an optional embodiment, step S6 is further included: training the grass-livestock balance random forest regression model for the corresponding category. Before step S2, please refer to [link to previous section]. Figure 2 , Figure 2 A flowchart illustrating step S6 of the grass-livestock balance assessment method provided in another embodiment of this application includes steps S61 to S63, as detailed below:

[0040] S61: Obtain the initial environmental variable data of the target grassland within the sample time period and the measured data of the grassland-livestock balance association for several categories; perform correlation analysis between the measured data of the grassland-livestock balance association for several categories and several initial environmental variables in the initial environmental variable data to obtain the correlation analysis results between the measured data of the grassland-livestock balance association for several categories and several initial environmental variables.

[0041] In this embodiment, the evaluation device obtains initial environmental variable data of the target grassland within the sample time period. This initial environmental variable data includes vegetation environmental variable data, climate environmental variable data, topographic environmental variable data, soil environmental variable data, and remote sensing spectral environmental variable data. The vegetation environmental variable data includes several vegetation environmental variables, including photosynthetically active radiation component, normalized difference moisture index (NDMI), shortwave infrared (SWIR), enhanced vegetation index (EVI), leaf area index (LAI), normalized difference vegetation index (NDVI), soil-adjusted vegetation index (SAVI), converted vegetation index (TVI), and net primary productivity (NPP). The climate environmental variable data includes average annual temperature (MAT), average annual precipitation (MAP), and evapotranspiration (ET). The topographic environmental variable data includes topographic humidity index (TWI), three-dimensional topographic analysis indices (Sp1, Sp2), and elevation data (ELE). The soil environmental variable data includes soil organic carbon content (SOC), clay content (Clay), soil pH, and soil total nitrogen (TN). The remote sensing spectral environmental variable data includes remote sensing spectral data (Band1-Band7).

[0042] The evaluation equipment obtains measured data on grass-livestock balance correlation for several categories of the target grassland within a sample time period, wherein the measured data on grass-livestock balance correlation includes measured data on aboveground biomass, measured data on crude protein, and measured data on net energy.

[0043] Specifically, the evaluation equipment obtains aboveground biomass measurement data and crude protein measurement data input by the user. The aboveground biomass measurement data is obtained by setting up sampling points in representative areas of different grassland types within the target grassland, with relatively uniform spatial vegetation distribution. At each sampling point, three 1m × 1m subplots are set up. During sampling, the aboveground portion of the grassland within the subplot is cut flush with the ground using scissors. Subsequently, the samples are dried in a 65℃ oven to constant weight and weighed. The obtained weight is the dry weight of the aboveground biomass (unit: kg / ha). -1 Finally, the average of the measurements from the three subplots was taken as the measured aboveground biomass data for that sampling point. The crude protein measured data was obtained after the aboveground biomass (AGB) of each grassland quadrat was measured, inedible portions were removed, and the remaining samples were mixed and ground using a grinder. The ground samples were then sieved through a 1 mm sieve and measured using the Kjeldahl method.

[0044] The evaluation equipment obtains measured data of acid-washed fibers. Based on the measured data of the acid-washed fibers and a preset net energy calculation algorithm, net energy data is obtained. The net energy calculation algorithm is as follows:

[0045] R NE = [1.044-(0.0119×R] ADF )]

[0046] In the formula, R NE For net energy, R ADF These are measured data for acid-washed fibers.

[0047] The evaluation equipment uses the Pearson coefficient calculation method to perform correlation analysis between the measured data of the grass-livestock balance association in several categories and several initial environmental variables in the initial environmental variable data, and obtains the correlation analysis results between the measured data of the grass-livestock balance association in several categories and several initial environmental variables. The correlation analysis results include positive correlation, negative correlation and no correlation.

[0048] S62: Based on the correlation analysis results, construct intermediate environmental variable data corresponding to the measured data of grass-livestock balance correlation for several categories; using a feature selection method based on random forest, select several target environmental variables from the intermediate environmental variable data corresponding to the measured data of grass-livestock balance correlation for several categories, and construct target environmental variable data corresponding to the measured data of grass-livestock balance correlation for several categories.

[0049] In this embodiment, the evaluation device, based on the correlation analysis results, removes the initial environmental variables that are not correlated according to the correlation analysis results, and constructs intermediate environmental variable data corresponding to the measured data of the grass-livestock balance in several categories. The intermediate environmental variable data includes several intermediate environmental variables selected from the initial environmental variable data.

[0050] The evaluation equipment uses a feature selection method based on random forest to select several target environmental variables from the intermediate environmental variable data corresponding to the measured data of the grass-livestock balance association in several categories, and constructs the target environmental variable data corresponding to the measured data of the grass-livestock balance association in several categories.

[0051] Specifically, for the intermediate environmental variable data corresponding to the measured data of the grass-livestock balance correlation for each category, the evaluation device constructs the shadow feature matrix X of the intermediate environmental variable data. shadow The shadow feature matrix includes several features, which are the intermediate environmental variables. The evaluation device randomly permutes the original feature matrix X. real Calculate the column vectors to construct the extended matrix X. extended =[X real ,X shadow The extended matrix X of the intermediate environmental variable data corresponding to the measured data of the grass-livestock balance correlation for each category is calculated. extendedInputting the data into a pre-defined random forest model to calculate feature importance scores (Z). j Calculate if Z satisfies j >max(Z shadow ), where Z shadow If the maximum importance score of all shadow features is found, and the significance p < 0.05, then feature j is considered significant. j Consistently significantly higher than Z shadow As an important feature; Z j Features that are consistently insignificant are considered unimportant, while statistically marginal features are considered uncertain. Iterative processing is performed based on these uncertain features. Important features and the features after iterative processing are used as target environmental variables. Several target environmental variables are selected from the intermediate environmental variable data corresponding to the measured data of the grass-livestock balance association in several categories, and target environmental variable data corresponding to the measured data of the grass-livestock balance association in several categories are constructed.

[0052] By introducing random shadow features as a reference benchmark, the arbitrariness of manually setting importance thresholds is avoided, ensuring that feature selection is statistically significant (p<0.05). Furthermore, redundant variables that are not significantly different from shadow features are automatically removed during iteration, reducing the impact of collinearity in high-dimensional remote sensing data.

[0053] S63: Construct sample datasets based on measured data of grass-livestock balance associations for several categories and corresponding target environmental variable data to obtain sample datasets of grass-livestock balance for several categories; use the random forest method to train on the sample datasets of grass-livestock balance for several categories to construct random forest regression models of grass-livestock balance for several categories.

[0054] In this embodiment, the evaluation device constructs a sample dataset based on the measured data of grass-livestock balance association in several categories and the corresponding target environmental variable data, thereby obtaining a sample dataset of grass-livestock balance in several categories.

[0055] The evaluation device employs a random forest method, training on a dataset of grassland-livestock balance samples across several categories to construct random forest regression models for grassland-livestock balance across multiple categories. Specifically, the evaluation device uses bootstrap sampling to extract several samples from the grassland-livestock balance dataset, where each sample includes several environmental variables. Based on these samples, the evaluation device generates different decision trees by introducing randomness. Each tree learns independently and generates predictions, thus constructing random forest regression models for grassland-livestock balance across multiple categories.

[0056] In the grass-livestock balance random forest regression model, the predictions generated by each tree are ultimately merged into a single prediction, effectively reducing the risk of overfitting that may occur with individual decision trees. This results in better performance compared to any single prediction. Furthermore, the grass-livestock balance random forest regression model can handle both classification / regression and numerical features simultaneously, reducing the risk of overfitting through averaging of the decision trees and exhibiting high stability.

[0057] S3: Based on the grassland-livestock balance correlation regression data of several categories, calculate the grassland-livestock carrying capacity index of the corresponding categories to obtain the grassland-livestock carrying capacity index of several categories of several grid units of the target grassland within the target time period.

[0058] In this embodiment, the evaluation device calculates the grass-livestock carrying capacity index of the corresponding category based on the grass-livestock balance correlation regression data of several categories, and obtains the grass-livestock carrying capacity index of several categories of several grid units of the target grassland within the target time period.

[0059] Please see Figure 3 , Figure 3 The flowchart of step S3 in the grassland-livestock balance assessment method provided in one embodiment of this application is as follows: Steps S31 to S32 are detailed below:

[0060] S31: Obtain grass and livestock demand data for several grid cells of the target grassland within the target time period.

[0061] In this embodiment, the evaluation device obtains grass-livestock demand data for several grid cells of the target grassland within a target time period. The grass-livestock demand data includes the daily dry matter demand, the daily crude protein demand, and the daily net energy demand of a standard livestock unit.

[0062] S32: Based on the grass-livestock demand, several categories of grass-livestock balance correlation regression data, and a preset grass-livestock carrying capacity index calculation algorithm, calculate the grass-livestock carrying capacity index of the corresponding categories to obtain the grass-livestock carrying capacity index of several categories of several grid units of the target grassland within the target time period.

[0063] In this embodiment, the evaluation device calculates the grass-livestock carrying capacity index for the corresponding categories based on the grass-livestock demand, several categories of grass-livestock balance correlation regression data, and a preset grass-livestock carrying capacity index calculation algorithm. This yields several categories of grass-livestock carrying capacity indices for several grid cells of the target grassland within a target time period. The grass-livestock carrying capacity index includes the aboveground biomass grass-livestock carrying capacity index, the crude protein grass-livestock carrying capacity index, and the net energy grass-livestock carrying capacity index. The grass-livestock carrying capacity index calculation algorithm is as follows:

[0064]

[0065] In the formula, TCC AGB TCC is the aboveground biomass carrying capacity index for grass and livestock. CP The crude protein forage-livestock carrying capacity index, TCC NE P is the net energy carrying capacity index for grass and livestock. AGB For aboveground biomass regression data, R AGB P represents the daily dry matter requirement per standard livestock unit. CP For crude protein regression data, R CP P represents the daily crude protein requirement per standard livestock unit. NE For net energy regression data, R NE The net energy requirement per standard livestock unit per day is , the forage utilization rate is , H is the proportion of edible feed, and T is the number of days in the target time period. Specifically, the number of days in the target time period can be the number of grazing days.

[0066] S4: Calculate the theoretical grass-livestock carrying capacity index of several categories of several grid units of the target grassland within the target time period to obtain the theoretical grass-livestock carrying capacity of the target grassland within the target time period.

[0067] In this embodiment, the evaluation device calculates the theoretical grass-livestock carrying capacity based on the grass-livestock carrying capacity index of several categories of several grid units of the target grassland within the target time period, thereby obtaining the theoretical grass-livestock carrying capacity of the target grassland within the target time period.

[0068] Please see Figure 4 , Figure 4 The flowchart of step S4 in the grassland-livestock balance assessment method provided in one embodiment of this application is as follows: Steps S41 to S43 are detailed below:

[0069] S41: Standardize the grass-livestock carrying capacity index of several categories of several grid cells of the target grassland within the target time period to obtain the standardized grass-livestock carrying capacity index of several categories of several grid cells of the target grassland within the target time period.

[0070] In this embodiment, the evaluation device performs standardization processing on the grass-livestock carrying capacity index of several categories of several grid units of the target grassland within a target time period to obtain the standardized grass-livestock carrying capacity index of several categories of several grid units of the target grassland within a target time period. Specifically, the standardization processing can adopt positive standardization processing and negative standardization processing.

[0071] S42: Based on the standardized grass-livestock carrying capacity index of several categories of several grid cells of the target grassland within the target time period, calculate the weights and entropy values ​​to obtain the weight parameters and entropy values ​​of the grass-livestock carrying capacity index of several categories of several grid cells.

[0072] In this embodiment, the evaluation device calculates the weights and entropy values ​​of the grass-livestock carrying capacity index of several categories of several grid cells of the target grassland within a target time period after standardization, thereby obtaining the weight parameters of the grass-livestock carrying capacity index of several categories of several grid cells and the entropy values ​​of the grass-livestock carrying capacity index of several categories.

[0073] Please see Figure 5 , Figure 5 The flowchart of step S42 in the grassland-livestock balance assessment method provided in one embodiment of this application is as follows: Steps S421 to S423 are detailed below:

[0074] S421: Based on the standardized grass-livestock carrying capacity index of several grid units of the target grassland within the target time period and the preset correlation coefficient calculation algorithm, obtain the correlation coefficient between the grass-livestock carrying capacity indices of several categories.

[0075] In this embodiment, the evaluation device obtains the correlation coefficients between several categories of grass-livestock carrying capacity indices based on several grid cells of the target grassland within a target time period after standardization, and a preset correlation coefficient calculation algorithm. The correlation coefficient calculation algorithm is as follows:

[0076]

[0077] In the formula, r jk Let X′ be the correlation coefficient between the grass-livestock carrying capacity index of category j and the grass-livestock carrying capacity index of category k. ij X- represents the grass-livestock carrying capacity index of the j-th category in the i-th grid cell after standardization. J X represents the average of the grass-livestock carrying capacity index for the j-th category after standardization. ik This represents the grass-livestock carrying capacity index for the k-th category of the i-th grid cell after standardization. is the average of the grass-livestock carrying capacity index for the kth category after standardization, where n is the number of grid cells.

[0078] S422: Calculate the standard deviation of the grass-livestock carrying capacity index of several categories in several grid cells of the target grassland within the target time period after standardization, and obtain the standard deviation of the grass-livestock carrying capacity index of several categories in several grid cells; obtain the weight parameters of the grass-livestock carrying capacity index of several categories in several grid cells based on the standard deviation of the grass-livestock carrying capacity index of several categories in several grid cells, the correlation coefficient between the grass-livestock carrying capacity index of several categories, and the preset weight calculation algorithm.

[0079] In this embodiment, the evaluation device calculates the standard deviation of the grass-livestock carrying capacity index of several categories in several grid cells of the target grassland within a target time period after standardization, thereby obtaining the standard deviation of the grass-livestock carrying capacity index of several categories in several grid cells, wherein the standard deviation is:

[0080]

[0081] In the formula, S ij is the standard deviation of the grass-livestock carrying capacity index for the j-th category of the i-th grid cell.

[0082] The evaluation equipment obtains weight parameters for the grass-livestock carrying capacity indices of several categories in several grid cells based on the standard deviation of the grass-livestock carrying capacity indices of several categories, the correlation coefficients between the grass-livestock carrying capacity indices of several categories, and a preset weight calculation algorithm. The weight calculation algorithm is as follows:

[0083]

[0084] In the formula, w ij S is the weighting parameter for the grass-livestock carrying capacity index of the j-th category in the i-th grid cell. ij Let r be the standard deviation of the grass-livestock carrying capacity index for the j-th category in the i-th grid cell. ij Let be the correlation coefficient between the grass-livestock carrying capacity index of category j and the grass-livestock carrying capacity index of category j.

[0085] S423: Based on the grass-livestock carrying capacity index of several categories of several grid units of the target grassland within the target time period after standardization and the preset entropy calculation algorithm, obtain the entropy values ​​of several categories of grass-livestock carrying capacity index.

[0086] In this embodiment, the evaluation device obtains the entropy values ​​of several categories of grass-livestock carrying capacity indices based on several grid cells of the target grassland within a target time period after standardization, and a preset entropy calculation algorithm. The entropy calculation algorithm is as follows:

[0087]

[0088] In the formula, P j Let be the entropy value of the grass-livestock carrying capacity index for the j-th category.

[0089] S43: Based on the standardized grass-livestock carrying capacity index of several categories of several grid cells of the target grassland within the target time period, the weight parameters of the grass-livestock carrying capacity index of several categories of several grid cells, the entropy value of the grass-livestock carrying capacity index of several categories, and the preset carrying capacity calculation algorithm, obtain the theoretical grass-livestock carrying capacity of the target grassland within the target time period.

[0090] In this embodiment, the evaluation device obtains the theoretical grass-livestock carrying capacity of the target grassland within the target time period based on the standardized grass-livestock carrying capacity index of several categories of several grid cells within the target time period, the weight parameters of the grass-livestock carrying capacity index of several categories of several grid cells, the entropy value of the grass-livestock carrying capacity index of several categories, and a preset carrying capacity calculation algorithm. The carrying capacity calculation algorithm is as follows:

[0091]

[0092] In the formula, TCC represents the theoretical carrying capacity of grass and livestock. i,AGB TCC is the aboveground biomass carrying capacity index for the i-th grid cell. i,CP TCC is the crude protein carrying capacity index for livestock in the i-th grid cell. i,NE W represents the net energy carrying capacity index of the i-th grid cell. i AGB W is the weighting parameter for the aboveground biomass carrying capacity index of the i-th grid cell. i CP W is the weighting parameter for the crude protein forage-livestock carrying capacity index of the i-th grid cell. i NE P is the weighting parameter for the crude protein forage-livestock carrying capacity index of the i-th grid cell. AGB Let P be the entropy value of the aboveground biomass grass-livestock carrying capacity index of the i-th grid cell. CP Let P be the entropy value of the crude protein forage-livestock carrying capacity index of the i-th grid cell. NE Let be the entropy value of the crude protein carrying capacity index for livestock in the i-th grid cell.

[0093] S5: Obtain the actual grass-livestock carrying capacity of the target grassland within the target time period; conduct a grass-livestock balance assessment based on the theoretical grass-livestock carrying capacity and the actual grass-livestock carrying capacity of the target grassland within the target time period, and obtain the grass-livestock balance assessment result of the target grassland within the target time period.

[0094] In this embodiment, the evaluation device obtains the actual grass-livestock carrying capacity of the target grassland within a target time period. Based on the theoretical and actual grass-livestock carrying capacity of the target grassland within the target time period, the evaluation device performs a grass-livestock balance assessment to obtain the grass-livestock balance assessment result for the target grassland within the target time period.

[0095] The actual grass-grazing carrying capacity includes both grazing grass-grazing carrying capacity and wild grass-grazing carrying capacity. Please refer to [link / reference]. Figure 6 , Figure 6 The flowchart of step S5 in the grassland-livestock balance assessment method provided in one embodiment of this application includes steps S51 to S53, as follows:

[0096] S51: Obtain the area data of the target grassland, the grazing livestock stock of the target grassland during the target time period, the wild livestock stock, the duration of the grassland growing season, and the duration of the grassland non-growing season.

[0097] In this embodiment, the evaluation device obtains the area data of the target grassland, the grazing livestock stock of the target grassland during the target time period, the wild livestock stock, the duration of the grassland growing season, and the duration of the grassland non-growing season. The grazing livestock stock includes the mid-term grazing livestock stock and the late-term grazing livestock stock.

[0098] S52: Based on the area data of the target grassland, the grazing livestock stock of the target grassland in the target time period, the duration of the grassland growing season, the duration of the grassland non-growing season, and the preset grazing livestock carrying capacity calculation algorithm, obtain the grazing livestock carrying capacity of the target grassland in the target time period.

[0099] In this embodiment, the evaluation device obtains the grazing carrying capacity of the target grassland within the target time period based on the area data of the target grassland, the grazing livestock stock of the target grassland during the target time period, the duration of the grassland growing season, the duration of the grassland non-growing season, and a preset grazing livestock carrying capacity calculation algorithm. The grazing livestock carrying capacity calculation algorithm is as follows:

[0100]

[0101] In the formula, PCC livestock Stock is used to measure the carrying capacity of livestock during grazing. y,Mid For medium-term grazing livestock stock, T warmStock represents the duration of the grassland growing season, S represents the area of ​​the target grassland, and Stock represents the area of ​​the target grassland. y,End T represents the final stock of grazing livestock. cold The duration of the non-growing season for grassland;

[0102] S53: Based on the area data of the target grassland, the wild grass-livestock stock of the target grassland in the target time period, and the preset wild grass-livestock carrying capacity calculation algorithm, obtain the wild grass-livestock carrying capacity of the target grassland in the target time period.

[0103] In this embodiment, the evaluation device obtains the wild grass-livestock carrying capacity of the target grassland during the target time period based on the area data of the target grassland, the wild grass-livestock carrying capacity of the target grassland during the target time period, and a preset wild grass-livestock carrying capacity calculation algorithm. The wild grass-livestock carrying capacity calculation algorithm is as follows:

[0104]

[0105] In the formula, PCC wildlife Stock represents the carrying capacity of wild grass-fed livestock. wildlife T represents the stock of wild grass and livestock, and T represents the duration of the target time period.

[0106] Please see Figure 7 , Figure 7 The flowchart of step S5 in the grass-livestock balance assessment method provided in another embodiment of this application includes steps S54 to S55, as follows:

[0107] S54: Based on the theoretical grass-livestock carrying capacity of the target grassland within the target time period, the actual grass-livestock carrying capacity including the pasture carrying capacity, the wild grass-livestock carrying capacity, and the preset grass-livestock balance index calculation algorithm, obtain the grass-livestock balance index of the target grassland within the target time period.

[0108] In this embodiment, the evaluation device obtains the grass-livestock balance index of the target grassland within the target time period based on the theoretical grass-livestock carrying capacity, the actual grass-livestock carrying capacity (including pasture-livestock carrying capacity and wild grass-livestock carrying capacity), and a preset grass-livestock balance index calculation algorithm. The grass-livestock balance index calculation algorithm is as follows:

[0109]

[0110] PCC = PCC livestock +PCC wildlife

[0111] In the formula, FSDI is the grass-livestock balance index, and PCC is the comprehensive grass-livestock carrying capacity;

[0112] S55: Based on the grass-livestock balance index of the target grassland within the target time period and several preset threshold intervals, confirm the threshold interval in which the grass-livestock balance index is located, obtain the grass-livestock balance assessment result corresponding to the threshold interval in which the grass-livestock balance index is located, and use it as the grass-livestock balance assessment result of the target grassland within the target time period.

[0113] In this embodiment, the evaluation device determines the threshold range in which the grass-livestock balance index is located based on the grass-livestock balance index of the target grassland within the target time period and several preset threshold ranges, and obtains the grass-livestock balance evaluation result corresponding to the threshold range in which the grass-livestock balance index is located, which serves as the grass-livestock balance evaluation result of the target grassland within the target time period.

[0114] Specifically, when the grass-livestock balance index is within the threshold range of (-∞, 0.5), a first grass-livestock balance assessment result corresponding to the threshold range of the grass-livestock balance index is obtained. The first grass-livestock balance assessment result is used to indicate that the target grassland is lightly grazed during the target time period. When the grass-livestock balance index is within the threshold range of [0.5, 1.5], a second grass-livestock balance assessment result corresponding to the threshold range of the grass-livestock balance index is obtained. The second grass-livestock balance assessment result is used to indicate that the target grassland has a stable balance between grassland resources and grazing demand during the target time period. When the grass-livestock balance index is within the threshold range of (1.5, 3], a third grass-livestock balance assessment result corresponding to the threshold range of the grass-livestock balance index is obtained. The livestock balance assessment results indicate a slight imbalance between grassland resources and grazing demand in the target grassland during the target time period. When the grassland-livestock balance index is within the threshold range of (3, 5), a fourth grassland-livestock balance assessment result corresponding to the threshold range of the grassland-livestock balance index is obtained. The fourth grassland-livestock balance assessment result indicates a moderate imbalance between grassland resources and grazing demand in the target grassland during the target time period. When the grassland-livestock balance index is within the threshold range of (10, +∞), a fifth grassland-livestock balance assessment result corresponding to the threshold range of the grassland-livestock balance index is obtained. The fifth grassland-livestock balance assessment result indicates a severe imbalance between grassland resources and grazing demand in the target grassland during the target time period, and the ecological function of the grassland is severely damaged.

[0115] Environmental variable data from target grassland grid cells and corresponding categories of stochastic forest regression models for grassland-livestock balance are used to obtain grassland-livestock balance correlation regression data for each grid cell. Based on this data, the carrying capacity of grassland for each category is calculated to obtain a grassland-livestock carrying capacity index. This allows for dynamic monitoring of the grassland-livestock balance status at the grid cell scale. Theoretical carrying capacity is then calculated based on the carrying capacity index to obtain the theoretical carrying capacity. Combined with actual carrying capacity, a grassland-livestock balance assessment is conducted to obtain the assessment results. This assessment effectively reflects changes in grassland productivity patterns and carrying capacity pressure, further improving the accuracy and timeliness of grassland-livestock management and providing crucial evidence for assessing changes in grassland carrying capacity and grassland-livestock balance pressure.

[0116] Please refer to Figure 8 , Figure 8 This is a schematic diagram of the structure of a grass-livestock balance assessment device provided in one embodiment of this application. The device can be implemented entirely or partially through software, hardware, or a combination of both. The device 8 includes:

[0117] The data acquisition module 81 is used to obtain environmental variable data of several categories of several grid cells of the target grassland within a target time period, wherein the environmental variable data includes several environmental variables;

[0118] The data regression module 82 is used to input the environmental variable data of several categories of several grid cells of the target grassland within a target time period into the preset corresponding category of grassland-livestock balance random forest regression model for regression, so as to obtain grassland-livestock balance correlation regression data of several categories of several grid cells of the target grassland within a target time period.

[0119] The grass-livestock carrying capacity index calculation module 83 is used to calculate the grass-livestock carrying capacity index of the corresponding category based on the grass-livestock balance correlation regression data of several categories, and obtain the grass-livestock carrying capacity index of several categories of several grid units of the target grassland in the target time period.

[0120] The theoretical grass-livestock carrying capacity calculation module 84 is used to calculate the theoretical grass-livestock carrying capacity based on the grass-livestock carrying capacity index of several categories of several grid units of the target grassland within the target time period, so as to obtain the theoretical grass-livestock carrying capacity of the target grassland within the target time period.

[0121] The grass-livestock balance assessment module 85 is used to obtain the actual grass-livestock carrying capacity of the target grassland within the target time period; and to conduct a grass-livestock balance assessment based on the theoretical grass-livestock carrying capacity and the actual grass-livestock carrying capacity of the target grassland within the target time period, thereby obtaining the grass-livestock balance assessment result of the target grassland within the target time period.

[0122] In this embodiment, a data acquisition module obtains environmental variable data for several categories of several grid cells of the target grassland within a target time period, wherein the environmental variable data includes several environmental variables; a data regression module inputs the environmental variable data for several categories of several grid cells of the target grassland within the target time period into a preset corresponding category of grassland-livestock balance random forest regression model for regression, obtaining grassland-livestock balance association regression data for several categories of several grid cells of the target grassland within the target time period; a grassland-livestock carrying capacity index calculation module calculates the corresponding category of grassland carrying capacity index based on the grassland-livestock balance association regression data for several categories. The livestock carrying capacity index is calculated to obtain the grass-livestock carrying capacity index for several categories of several grid cells of the target grassland within a target time period. The theoretical grass-livestock carrying capacity is calculated using a theoretical grass-livestock carrying capacity calculation module based on the grass-livestock carrying capacity index for several categories of several grid cells of the target grassland within the target time period, yielding the theoretical grass-livestock carrying capacity for the target grassland within the target time period. The actual grass-livestock carrying capacity of the target grassland within the target time period is obtained using a grass-livestock balance assessment module. A grass-livestock balance assessment is performed based on the theoretical and actual grass-livestock carrying capacities of the target grassland within the target time period, yielding the grass-livestock balance assessment result for the target grassland within the target time period. Regression is performed based on the environmental variable data of the grid cells of the target grassland and the corresponding categories of grass-livestock balance random forest regression models to obtain grass-livestock balance correlation regression data for the grid cells. Based on the grass-livestock balance correlation regression data, the grass-livestock carrying capacity for the corresponding categories is calculated to obtain the grass-livestock carrying capacity index, dynamically monitoring the grass-livestock balance status of the target grassland at the grid cell scale. Theoretical grassland carrying capacity is calculated based on the grassland carrying capacity index to obtain the theoretical grassland carrying capacity. Combined with the actual grassland carrying capacity, grassland-livestock balance assessment is conducted to obtain the grassland-livestock balance assessment results. This can effectively reflect changes in grassland productivity patterns and carrying capacity pressure, further improve the accuracy and timeliness of grassland-livestock management, and provide an important basis for assessing changes in grassland carrying capacity and grassland-livestock balance pressure.

[0123] Please refer to Figure 9 , Figure 9 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. The computer device 9 includes: a processor 91, a memory 92, and a computer program 93 stored in the memory 92 and executable on the processor 91; the computer device can store multiple instructions, which are adapted to be loaded and executed by the processor 91. Figures 1 to 7 The method steps of the illustrated embodiment can be found in the following documentation for detailed execution. Figures 1 to 7 The specific details of the illustrated embodiments will not be elaborated here.

[0124] The processor 91 may include one or more processing cores. The processor 91 connects to various parts of the server using various interfaces and lines, and executes various functions and processes data of the livestock balance assessment device 8 by running or executing instructions, programs, code sets, or instruction sets stored in the memory 92, and by calling data stored in the memory 92. Optionally, the processor 91 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 91 may integrate one or a combination of several of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required to be displayed on the touch screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 91 and may be implemented as a separate chip.

[0125] The memory 92 may include random access memory (RAM) or read-only memory. Optionally, the memory 92 may include a non-transitory computer-readable storage medium. The memory 92 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 92 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions), instructions for implementing the various method embodiments described above, etc.; the data storage area may store data involved in the various method embodiments described above, etc. Optionally, the memory 92 may also be at least one storage device located remotely from the aforementioned processor 91.

[0126] This application embodiment also provides a storage medium that can store multiple instructions, which are adapted to be loaded and executed by a processor as described above. Figures 1 to 7 The method steps of the illustrated embodiment can be found in the following documentation for detailed execution. Figures 1 to 7 The specific details of the illustrated embodiments will not be elaborated here.

[0127] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0128] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0129] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the algorithm. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0130] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0131] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0132] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0133] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms.

[0134] This invention is not limited to the above-described embodiments. If any modifications or variations to this invention do not depart from the spirit and scope of this invention, and if such modifications and variations fall within the scope of the claims and equivalent technologies of this invention, then this invention also intends to include such modifications and variations.

Claims

1. A method of grass-livestock balance evaluation, characterized by, Includes the following steps: Obtain environmental variable data for several categories of several raster cells of the target grassland within a target time period, wherein the environmental variable data includes several environmental variables; The environmental variable data of several categories of several grid cells of the target grassland within the target time period are input into the preset corresponding category of grassland-livestock balance random forest regression model for regression, to obtain grassland-livestock balance correlation regression data of several categories of several grid cells of the target grassland within the target time period, wherein the grassland-livestock balance correlation regression data includes aboveground biomass regression data, crude protein regression data and net energy regression data. Obtain grass and livestock demand data for several grid cells of the target grassland within a target time period, wherein the grass and livestock demand data includes the daily dry matter demand, the daily crude protein demand, and the daily net energy demand of a standard livestock unit. Based on the grass-livestock demand, several categories of grass-livestock balance correlation regression data, and a preset grass-livestock carrying capacity index calculation algorithm, the grass-livestock carrying capacity index for each category is calculated to obtain several categories of grass-livestock carrying capacity indices for several grid cells of the target grassland within a target time period. The grass-livestock carrying capacity index includes aboveground biomass grass-livestock carrying capacity index, crude protein grass-livestock carrying capacity index, and net energy grass-livestock carrying capacity index. The grass-livestock carrying capacity index calculation algorithm is as follows: In the formula, The aboveground biomass grass-livestock carrying capacity index. The crude protein grass-livestock carrying capacity index. The net energy carrying capacity index for grass and livestock. For aboveground biomass regression data, This refers to the daily dry matter requirement per standard livestock unit. For crude protein regression data, This represents the daily crude protein requirement per standard livestock unit. For net energy regression data, This refers to the net energy requirement per standard livestock unit per day. U To improve the utilization rate of forage, H This refers to the proportion of edible feed. The number of days in the target time period; The theoretical grass-livestock carrying capacity is calculated based on the grass-livestock carrying capacity index of several categories of several grid units of the target grassland within the target time period, so as to obtain the theoretical grass-livestock carrying capacity of the target grassland within the target time period. Obtain the actual grass-livestock carrying capacity of the target grassland within the target time period; conduct a grass-livestock balance assessment based on the theoretical and actual grass-livestock carrying capacity of the target grassland within the target time period, and obtain the grass-livestock balance assessment result of the target grassland within the target time period.

2. The method for assessing grass-livestock balance according to claim 1, characterized in that, Before inputting the environmental variable data of several categories of several grid cells of the target grassland within the target time period into the preset corresponding category of grassland-livestock balance random forest regression model for regression to obtain grassland-livestock balance correlation regression data of several categories of several grid cells of the target grassland within the target time period, the method further includes the step of training the corresponding category of grassland-livestock balance random forest regression model. The training of the corresponding category of grass-livestock balance random forest regression model includes the following steps: The initial environmental variable data of the target grassland within the sample time period and the measured data of the grassland-livestock balance association of several categories are obtained; correlation analysis is performed between the measured data of the grassland-livestock balance association of several categories and several initial environmental variables in the initial environmental variable data to obtain the correlation analysis results between the measured data of the grassland-livestock balance association of several categories and several initial environmental variables. Based on the correlation analysis results, intermediate environmental variable data corresponding to the measured data of grass-livestock balance correlation in several categories are constructed; using a feature selection method based on random forest, several target environmental variables are selected from the intermediate environmental variable data corresponding to the measured data of grass-livestock balance correlation in several categories, and target environmental variable data corresponding to the measured data of grass-livestock balance correlation in several categories are constructed. Based on the measured data of grass-livestock balance associations for several categories and the corresponding target environmental variable data, a sample dataset is constructed to obtain grass-livestock balance sample datasets for several categories; the random forest method is used to train the grass-livestock balance sample datasets for several categories to construct a random forest regression model for grass-livestock balance for several categories.

3. The grass-livestock balance assessment method according to claim 2, characterized in that, The step of calculating the theoretical grass-livestock carrying capacity based on the grass-livestock carrying capacity index of several categories of several grid cells of the target grassland within a target time period, to obtain the theoretical grass-livestock carrying capacity of the target grassland within the target time period, includes the following steps: The grass-livestock carrying capacity index of several categories of several grid cells of the target grassland within a target time period is standardized to obtain the standardized grass-livestock carrying capacity index of several categories of several grid cells of the target grassland within a target time period. Based on the standardized grassland carrying capacity index of several categories in several grid cells within the target time period, the weights and entropy values ​​are calculated to obtain the weight parameters and entropy values ​​of the grassland carrying capacity index of several categories in several grid cells. Based on the standardized grass-livestock carrying capacity index of several categories of several grid cells of the target grassland within the target time period, the weight parameters of the grass-livestock carrying capacity index of several categories of several grid cells, the entropy value of the grass-livestock carrying capacity index of several categories, and a preset carrying capacity calculation algorithm, the theoretical grass-livestock carrying capacity of the target grassland within the target time period is obtained. The carrying capacity calculation algorithm is as follows: In the formula, Theoretical carrying capacity for grass and livestock. For the first i Aboveground biomass carrying capacity index of each grid cell For the first i Crude protein grass-livestock carrying capacity index of each grid cell For the first i Net energy carrying capacity index of each grid cell For the first i The weighting parameters of the aboveground biomass grass-livestock carrying capacity index for each grid cell. For the first i The weighting parameters of the crude protein forage-livestock carrying capacity index for each grid cell. For the first i The weighting parameters of the crude protein forage-livestock carrying capacity index for each grid cell. For the first i The entropy value of the aboveground biomass carrying capacity index of each grid cell. For the first i The entropy value of the crude protein grass-livestock carrying capacity index of each grid cell. For the first i The entropy value of the crude protein grass-livestock carrying capacity index of each grid cell.

4. The method for assessing grass-livestock balance according to claim 3, characterized in that, The step of calculating the weights and entropy values ​​of the grass-livestock carrying capacity index of several categories in several grid cells of the target grassland within a target time period after standardization, to obtain the weight parameters and entropy values ​​of the grass-livestock carrying capacity index of several categories in several grid cells, includes the following steps: Based on the standardized grassland carrying capacity index of several categories in several grid cells within a target time period and a preset correlation coefficient calculation algorithm, the correlation coefficients between the several categories of grassland carrying capacity indices are obtained. The correlation coefficient calculation algorithm is as follows: In the formula, For the first j The grass-livestock carrying capacity index of each category and the first category k Correlation coefficients among the grass-livestock carrying capacity indices of each category For the standardized process of the first i The first grid cell j The grass-livestock carrying capacity index for each category, For the standardized process j The average of the grass-livestock carrying capacity index for each category, For the standardized process i The first grid cell k The grass-livestock carrying capacity index for each category, For the standardized process k The average of the grass-livestock carrying capacity index for each category, n The number of grid cells; The standard deviation of the grass-livestock carrying capacity index of several categories in several grid cells of the target grassland within a target time period after standardization is calculated to obtain the standard deviation of the grass-livestock carrying capacity index of several categories in several grid cells. Based on the standard deviation of the grass-livestock carrying capacity index of several categories in several grid cells, the correlation coefficient between the grass-livestock carrying capacity indices of several categories, and a preset weight calculation algorithm, the weight parameters of the grass-livestock carrying capacity index of several categories in several grid cells are obtained. The weight calculation algorithm is as follows: In the formula, For the first i The first grid cell j The weighting parameters of the grass-livestock carrying capacity index for each category, For the first i The first grid cell j Standard deviation of the grass-livestock carrying capacity index for each category for j The grass-livestock carrying capacity index of each category and the first category j Correlation coefficients among the grass-livestock carrying capacity indices of each category; Based on the standardized grassland carrying capacity index of several categories in several grid cells within a target time period and a preset entropy calculation algorithm, the entropy values ​​of several categories of grassland carrying capacity indices are obtained. The entropy calculation algorithm is as follows: In the formula, For the first j The entropy value of the grass-livestock carrying capacity index for each category.

5. The grass-livestock balance assessment method according to claim 4, characterized in that: The actual grass-grazing carrying capacity includes the grazing grass-grazing carrying capacity and the wild grass-grazing carrying capacity. Obtaining the actual grass-livestock carrying capacity of the target grassland within the target time period includes the following steps: The area data of the target grassland, the grazing livestock stock of the target grassland during the target time period, the wild livestock stock, the duration of the grassland growing season, and the duration of the grassland non-growing season are obtained. The grazing livestock stock includes the mid-term grazing livestock stock and the late-term grazing livestock stock. Based on the area data of the target grassland, the grazing livestock stock of the target grassland during the target time period, the duration of the grassland growing season, the duration of the grassland non-growing season, and a preset grazing livestock carrying capacity calculation algorithm, the grazing livestock carrying capacity of the target grassland during the target time period is obtained. The grazing livestock carrying capacity calculation algorithm is as follows: In the formula, For grazing livestock carrying capacity, For medium-term grazing livestock stock, For the duration of the grassland growing season, The area data for the target grassland. This represents the remaining stock of grazing livestock at the end of the period. The duration of the non-growing season for grassland; Based on the area data of the target grassland, the wild grass-livestock stock of the target grassland during the target time period, and a preset wild grass-livestock carrying capacity calculation algorithm, the wild grass-livestock carrying capacity of the target grassland during the target time period is obtained. The wild grass-livestock carrying capacity calculation algorithm is as follows: In the formula, This refers to the carrying capacity of wild grass-fed livestock. For wild grass-fed livestock stock, The duration of the target time period.

6. The grass-livestock balance assessment method according to claim 5, characterized in that, The step of conducting a grass-livestock balance assessment based on the theoretical and actual grass-livestock carrying capacity of the target grassland within a target time period, and obtaining the grass-livestock balance assessment result of the target grassland within the target time period, includes the following steps: Based on the theoretical carrying capacity of the target grassland within the target time period, the carrying capacity of pasture within the actual carrying capacity, the carrying capacity of wild grassland, and a preset grassland-livestock balance index calculation algorithm, the grassland-livestock balance index of the target grassland within the target time period is obtained. The grassland-livestock balance index calculation algorithm is as follows: In the formula, The grass-livestock balance index. PCC To comprehensively measure the carrying capacity of grass and livestock; Based on the grass-livestock balance index of the target grassland within the target time period and several preset threshold intervals, the threshold interval in which the grass-livestock balance index is located is determined, and the grass-livestock balance assessment result corresponding to the threshold interval in which the grass-livestock balance index is located is obtained, which serves as the grass-livestock balance assessment result of the target grassland within the target time period.

7. A grass-livestock balance assessment device, characterized in that, include: The data acquisition module is used to obtain environmental variable data of several categories of several grid cells of the target grassland within a target time period, wherein the environmental variable data includes several environmental variables; The data regression module is used to input the environmental variable data of several categories of several grid cells of the target grassland within a target time period into a preset corresponding category of grassland-livestock balance random forest regression model for regression, and obtain grassland-livestock balance correlation regression data of several categories of several grid cells of the target grassland within a target time period, wherein the grassland-livestock balance correlation regression data includes aboveground biomass regression data, crude protein regression data and net energy regression data. The grass-livestock carrying capacity index calculation module is used to obtain grass-livestock demand data for several grid units of the target grassland within a target time period. The grass-livestock demand data includes the daily dry matter demand, daily crude protein demand, and daily net energy demand of a standard livestock unit. Based on the grass-livestock demand, several categories of grass-livestock balance correlation regression data, and a preset grass-livestock carrying capacity index calculation algorithm, the grass-livestock carrying capacity index for each category is calculated to obtain several categories of grass-livestock carrying capacity indices for several grid cells of the target grassland within a target time period. The grass-livestock carrying capacity index includes aboveground biomass grass-livestock carrying capacity index, crude protein grass-livestock carrying capacity index, and net energy grass-livestock carrying capacity index. The grass-livestock carrying capacity index calculation algorithm is as follows: In the formula, The aboveground biomass grass-livestock carrying capacity index. The crude protein grass-livestock carrying capacity index. The net energy carrying capacity index for grass and livestock. For aboveground biomass regression data, This refers to the daily dry matter requirement per standard livestock unit. For crude protein regression data, This represents the daily crude protein requirement per standard livestock unit. For net energy regression data, This refers to the net energy requirement per standard livestock unit per day. U To improve the utilization rate of forage, H This refers to the proportion of edible feed. The number of days in the target time period; The theoretical grass-livestock carrying capacity calculation module is used to calculate the theoretical grass-livestock carrying capacity based on the grass-livestock carrying capacity index of several categories of several grid units of the target grassland within a target time period, and to obtain the theoretical grass-livestock carrying capacity of the target grassland within the target time period. The grass-livestock balance assessment module is used to obtain the actual grass-livestock carrying capacity of the target grassland within a target time period; and to conduct a grass-livestock balance assessment based on the theoretical and actual grass-livestock carrying capacity of the target grassland within the target time period, thereby obtaining the grass-livestock balance assessment result of the target grassland within the target time period.

8. A computer device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor; the computer program, when executed by the processor, implements the steps of the grass-livestock balance assessment method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a computer program that, when executed by a processor, implements the steps of the grass-livestock balance assessment method as described in any one of claims 1 to 6.

Images