A method and system for monitoring and predicting alpine grassland degradation

Abstract

The present invention discloses a method and system for monitoring and predicting the degradation of alpine grasslands, which relates to the technical field of data processing. This method and system for monitoring and predicting the degradation of alpine grasslands determine the grazing monitoring areas and rodent hole monitoring areas of alpine grasslands based on the grazing monitoring data and rodent hole monitoring data of each monitoring area of alpine grasslands and the analysis of historical regional ground data of alpine grasslands; monitor the grazing monitoring areas and rodent hole monitoring areas of alpine grasslands to obtain the ground data of the selected monitoring areas; based on the meteorological altitude factors in alpine regions, analyze the data acquisition situations of multiple remote sensing devices, select the first-rank remote sensing representative data of alpine grasslands, and combine the ground data of the monitoring areas to evaluate the grassland vegetation conditions of the monitoring areas, so as to realize the prediction of the degradation of alpine grasslands. By comprehensively analyzing and predicting the grassland degradation situation, it is expected to improve the accuracy of alpine grassland degradation monitoring and provide a scientific basis for grassland resource management and protection.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for monitoring and predicting alpine grassland degradation. Background Art

[0002] Grassland degradation refers to phenomena such as a decline in grassland productivity, a change in vegetation structure, and a decline in soil quality, resulting in a weakening of grassland functions, a reduction in biodiversity, and even the evolution of grasslands into desertification or bare land.

[0003] Currently, remote sensing technology has broad application prospects in grassland degradation monitoring and can provide the ability to obtain data over a large range and throughout the entire time period. However, when using remote sensing equipment to obtain data in alpine regions, due to meteorological and altitude factors in alpine regions, such as snow cover, atmospheric interference, and complex terrain, data errors may occur, resulting in inaccurate grassland degradation prediction.

[0004] On the other hand, the grassland degradation problem in alpine regions is closely related to grazing and ecological balance. Ground data is expected to provide important information such as grassland utilization and grassland ecological status, and combining remote sensing data can more comprehensively analyze and predict the trend of grassland degradation. Therefore, combining multiple data sources, comprehensively analyzing and predicting grassland degradation conditions is expected to improve the accuracy and reliability of alpine grassland degradation monitoring and provide a scientific basis for grassland resource management and protection.

[0005] Therefore, in view of the above problems, there is an urgent need for a method and system for monitoring and predicting alpine grassland degradation. Summary of the Invention

[0006] Aiming at the deficiencies of the prior art, the present invention provides a method and system for monitoring and predicting alpine grassland degradation, which solves the problems that remote sensing equipment in alpine regions has detection errors resulting in inaccurate grassland monitoring and the lack of multiple data sources for predicting alpine grassland degradation.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: perform similarity analysis on the regional ground data of alpine grasslands in each monitoring area of alpine grasslands and the overall historical regional ground data of alpine grasslands, and number each monitoring area of alpine grasslands in descending order of the similarity between the regional ground data of alpine grasslands in each monitoring area and the overall historical regional ground data of alpine grasslands;

[0008] Determine the optimal number of monitoring areas in each monitoring area of alpine grasslands through the Monte Carlo algorithm, and select monitoring areas as the selected monitoring areas in descending order of the similarity between each monitoring area and the overall historical regional ground data of alpine grasslands, and perform monitoring to obtain the ground data of the selected monitoring areas;

[0009] Based on the meteorological and altitude factors in alpine regions, analyze the data collection of multiple remote sensing devices, select the first-order remote sensing representative data of alpine grasslands, and combine the ground data of the selected monitoring area to evaluate the grassland degradation status of the monitoring area, so as to realize the prediction of alpine grassland degradation;

[0010] The monitoring area includes a grazing monitoring area and a rodent hole monitoring area.

[0011] Further, the specific analysis for determining the selected grazing monitoring area and the selected rodent hole monitoring area in alpine regions is as follows: Divide and number the alpine grasslands according to geographical location coordinates: AGH1, AGH2, AGH3,..., AGHn; Extract the historical grazing monitoring data and rodent hole monitoring data of each monitoring area from the database of alpine grasslands, and preprocess and extract features from the grazing monitoring data and rodent hole monitoring data to obtain the grazing feature data sets and rodent hole feature data sets of each monitoring area respectively, and further obtain the mean values of the grazing feature data and the mean values of the rodent hole feature data of each monitoring area; Extract the historical ground data of alpine grasslands from the database of alpine grasslands. The historical ground data includes the historical overall grazing data and the historical overall rodent hole data of alpine grasslands. Preprocess and extract features from the historical overall grazing data and the historical overall rodent hole data to obtain the historical overall grazing feature data set and the historical overall rodent hole feature data set of alpine grasslands respectively, and further obtain the mean values of the historical overall grazing feature data and the mean values of the historical overall rodent hole feature data of alpine grasslands; Cluster the mean values of the grazing feature data, the mean values of the rodent hole feature data of each monitoring area, the mean values of the historical overall grazing feature data, and the mean values of the historical overall rodent hole feature data of alpine grasslands based on the Euclidean distance, and re-number each monitoring area according to the similarity value size: AGH1’, AGH2’, AGH3’,..., AGHn’; Determine the optimal regional sampling quantity in alpine regions based on the Monte Carlo sampling algorithm, and then mark the selected monitoring areas of alpine grasslands according to the number ranking. The selected monitoring areas include the selected grazing monitoring area and the selected rodent hole monitoring area.

[0012] Further, the grazing feature data set of each selected monitoring area is specifically the grazing growth rate set of each selected monitoring area; the rodent hole feature data set of each selected monitoring area is specifically the rodent hole quantity reduction rate set of each selected monitoring area.

[0013] Further, sampling the ground data of the selected monitoring area specifically includes the grazing monitoring data of the selected grazing monitoring area and the rodent hole monitoring data of the selected rodent hole monitoring area; the grazing monitoring data is specifically the number of grazing livestock.

[0014] Further, the specific analysis of selecting the first-rank remote sensing representative data of alpine grasslands is as follows: The meteorological altitude factors in alpine regions specifically include the highest altitude, the highest wind speed, and the lowest temperature in alpine regions; preprocess the highest altitude, the highest wind speed, and the lowest temperature in alpine regions, and then determine the minimum support threshold, number the remote sensing devices in alpine regions, and obtain the data acquisition information of each remote sensing device based on the historical data acquisition situation of the remote sensing devices stored in the database. The data acquisition information of each remote sensing device specifically includes the optimal adaptation altitude, the optimal adaptation wind speed, and the optimal adaptation temperature of each remote sensing device; based on the confidence and support analysis of the optimal adaptation altitude, the optimal adaptation wind speed, and the optimal adaptation temperature of each remote sensing device and the highest altitude, the highest wind speed, and the lowest temperature in alpine regions, select the remote sensing device with the best comprehensive ranking of confidence and support as the first-rank remote sensing device of alpine grasslands, and the monitoring data of the first-rank remote sensing device of alpine grasslands is used as the first-rank remote sensing representative data.

[0015] Further, the specific analysis process of obtaining the data acquisition information of each remote sensing device is as follows: Based on the historical data of each remote sensing device collected in the database, including the device working environment parameters and the collected data; screen the historical data according to the parameter targets of the altitude, temperature, and wind speed of the remote sensing device, and retain the working environment parameters and the corresponding collected data under the parameter target requirements; statistically analyze the retained working environment parameters and the corresponding collected data under the parameter target requirements, and select the working environment parameters with the smallest data acquisition error of each remote sensing device as the data acquisition information of each remote sensing device.

[0016] Further, the specific analysis of realizing the prediction of alpine grassland degradation is as follows: Obtain the first-rank remote sensing representative data and the sampled ground data of the selected monitoring area for each monitoring time period of the first-rank remote sensing device; use the time series model to perform predictive analysis on the first-rank remote sensing representative data and the ground data of the selected monitoring area, predict the future vegetation coverage of the selected monitoring area, and comprehensively average the future predicted vegetation coverage of each sampling area to obtain the alpine grassland degradation prediction coefficient. The alpine grassland degradation prediction coefficient is used to quantify the alpine grassland degradation prediction situation.

[0017] Further, the time series model adopts the ARIMAX model. The specific steps for predicting and analyzing the first-rank remote sensing representative data and the ground data of the sampled selected monitoring area through the time series model are as follows: Obtain the first-rank remote sensing representative data and the ground data of the sampled selected monitoring area as the data for prediction, and clean and preprocess the first-rank remote sensing representative data and the ground data of the sampled selected monitoring area; establish the ARIMAX model, and use the historical remote sensing data and historical ground data of the alpine grassland to perform maximum likelihood estimation fitting on the ARIMAX model to estimate the model parameters; use the residual analysis method to diagnose the fitted ARIMAX model to check whether the residuals of the model conform to the white noise hypothesis; use the fitted ARIMAX model to predict the future alpine grassland monitoring data.

[0018] Further, the first-rank remote sensing representative data specifically includes vegetation coverage. The exogenous variables in the ARIMAX model include the number of grazing livestock and the number of rodent holes. The ARIMAX model formula is:

[0019] y t = β0 + β1y t-1 + α1Δy t-1 + γ1ε t + γ2ε t-1 + γ3θ t + γ4θ t-1 + ε t ; In the formula, y t represents the vegetation coverage at time point t, y t-1 represents a lag term of the vegetation coverage, Δy t-1 represents a difference term of the vegetation coverage, ε t represents the number of grazing livestock at time point t, ε t-1 represents a difference term of the number of grazing livestock, θ t represents the number of rodent holes at time point t, θ t-1 represents a difference term of the number of rodent holes, β0 and β1 represent the coefficients of the autoregressive part, representing the autocorrelation of the vegetation coverage, α1 represents the coefficient of the difference part, representing the stationarity of the vegetation coverage, γ1, γ2, γ3, and γ4 represent the coefficients of the exogenous variables, representing the influence of the grazing number and the number of rodent holes on the vegetation coverage, and ε t represents the error term of the ARIMAX model, representing the random fluctuation that cannot be explained by the ARIMAX model.

[0020] An alpine grassland degradation monitoring and prediction system, which applies the above-mentioned alpine grassland degradation monitoring and prediction method, includes: a selected monitoring area module, which is used to determine the grazing selected monitoring area and the rodent hole selected monitoring area of the alpine grassland based on the grazing monitoring data, rodent hole monitoring data of each selected monitoring area of the alpine grassland and the analysis of the historical regional ground data of the alpine grassland; a ground data acquisition module, which is used to monitor the grazing selected monitoring area and the rodent hole selected monitoring area of the alpine grassland to obtain the ground data of the sampled selected monitoring area; a degradation prediction module, which is used to analyze the data collection situation of multiple remote sensing devices based on the meteorological and altitude factors in the alpine region, select the first-rank remote sensing representative data of the alpine grassland, and combine the ground data of the sampled selected monitoring area to evaluate whether the grassland in the sampled selected monitoring area is degraded and its degradation degree, so as to realize the prediction of alpine grassland degradation.

[0021] The present invention has the following beneficial effects:

[0022] (1) The alpine grassland degradation monitoring and prediction method and system can provide more accurate and reliable monitoring results by combining the grazing monitoring data, rodent hole monitoring data and historical ground data of the alpine grassland, as well as the analysis of meteorological and altitude factors. The comprehensive utilization of data can improve the monitoring accuracy of the alpine grassland degradation situation, help to detect problems early and take corresponding management measures; considering multiple factors, including grazing conditions, the situation of rodent holes and environmental factors such as meteorology and altitude, comprehensively considers various factors affecting the degradation of alpine grassland, so it can more comprehensively evaluate the health status of the grassland and the potential degradation risk; by adopting the method of combining remote sensing data and ground monitoring data, as well as the analysis of meteorological and altitude factors, this method is scientific and can improve the credibility of monitoring and prediction, making it an important tool for scientific management of alpine grassland; by combining historical data and environmental factors, the degradation of alpine grassland is predicted. This predictability can help relevant departments and managers take measures early to prevent the further degradation of alpine grassland and protect the ecological environment and the stability of the ecosystem.

[0023] (2) The alpine grassland degradation monitoring and prediction method and system can help ecological environment managers better understand and predict the changes in the alpine grassland ecosystem by predicting the future vegetation coverage. It helps to detect early signs of vegetation degradation or ecological balance imbalance and take corresponding management measures to protect and maintain the health of the grassland ecosystem. By monitoring and predicting the vegetation coverage, grazing activities can be better planned. If the prediction shows a decrease in vegetation coverage, managers can adjust the grazing strategy in a timely manner to avoid overgrazing leading to grassland degradation, which helps to achieve the sustainability of grazing activities and protect the integrity of the grassland ecosystem. Based on the prediction of vegetation coverage, resources can be better allocated, policies can be formulated, and projects can be planned to promote the effective implementation of grassland management and protection. Using time series analysis and vegetation coverage prediction can provide important data and cases for scientific research and education, which helps to enhance the understanding of the dynamic changes in the alpine grassland ecosystem and promote the development of related disciplines and the enrichment of educational resources.

[0024] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. Brief Description of the Drawings

[0025] Figure 1 It is a flowchart of a method for monitoring and predicting alpine grassland degradation according to the present invention.

[0026] Figure 2 It is a structural diagram of a system for monitoring and predicting alpine grassland degradation according to the present invention. Detailed Embodiments

[0027] In the embodiments of the present application, a method and system for monitoring and predicting alpine grassland degradation are used to solve the problems that the remote sensing equipment in alpine regions has detection errors, resulting in inaccurate grassland monitoring, and there is a lack of multiple data sources for predicting alpine grassland degradation.

[0028] The general idea for the problems in the embodiments of the present application is as follows:

[0029] Collect the grazing monitoring data, rodent hole monitoring data, and historical ground data of each monitoring area in alpine grasslands. These data contain descriptions of different aspects of the grassland ecosystem: grazing intensity, vegetation coverage and composition, and soil conditions. Analyze these data to understand the grassland conditions and change trends in different areas. Based on the analysis, determine the grazing monitoring areas and rodent hole monitoring areas. Then, conduct ground monitoring on these monitoring areas to obtain real-time ground data, including the number of grazing livestock and the number of rodent holes. Combine the meteorological and altitude factors in alpine regions to analyze the data collection situations of multiple remote sensing devices. Select the representative remote sensing data suitable for alpine grasslands, which can provide a wider coverage range and more frequent monitoring cycles. Finally, combine the ground data of the monitoring areas with the remote sensing data to comprehensively evaluate the grassland monitoring status of the monitoring areas. Through the analysis of grassland conditions and the consideration of environmental factors, predict the degradation of alpine grasslands so as to take timely measures for intervention and protection.

[0030] Please refer to Figure 1 , an embodiment of the present invention provides a technical solution: a method for monitoring and predicting the degradation of alpine grasslands, including the following steps: perform a similarity analysis on the regional ground data of alpine grasslands in each monitoring area and the overall historical regional ground data of alpine grasslands, and number each monitoring area of alpine grasslands in descending order according to the similarity between the regional ground data of alpine grasslands in each monitoring area and the overall historical regional ground data of alpine grasslands;

[0031] Determine the optimal number of monitoring areas among multiple monitoring areas in alpine grasslands through the Monte Carlo algorithm, and select monitoring areas as the selected monitoring areas in descending order according to the similarity between each monitoring area and the overall historical regional ground data of alpine grasslands, and conduct monitoring to obtain the ground data of the selected monitoring areas;

[0032] Based on the meteorological and altitude factors in alpine regions, analyze the data collection situations of multiple remote sensing devices, select the first-rank representative remote sensing data of alpine grasslands, and combine the ground data of the selected monitoring areas to evaluate the grassland degradation status of the monitoring areas, thereby realizing the prediction of the degradation of alpine grasslands;

[0033] The monitoring areas include grazing monitoring areas and rodent hole monitoring areas.

[0034] Specifically, the specific analysis for determining the grazing sampling selected monitoring areas and the rodent hole sampling selected monitoring areas in alpine regions is as follows: The alpine grasslands are divided into regions and numbered according to geographical location coordinates: AGH1, AGH2, AGH3,..., AGHn; Based on the database of alpine grasslands, the historical grazing monitoring data and rodent hole monitoring data of each monitoring area are extracted, and the grazing monitoring data and rodent hole monitoring data are preprocessed and feature extracted to obtain the grazing feature data sets and rodent hole feature data sets of each monitoring area respectively, and further obtain the grazing feature data means and rodent hole feature data means of each monitoring area; Based on the database of alpine grasslands, the historical regional ground data of alpine grasslands are extracted. The historical ground data include the historical overall grazing data and historical overall rodent hole data of alpine grasslands. The historical overall grazing data and historical overall rodent hole data are preprocessed and feature extracted to obtain the historical overall grazing feature data set and historical overall rodent hole feature data set of alpine grasslands respectively, and further obtain the historical overall grazing feature data mean and historical overall rodent hole feature data mean of alpine grasslands; Based on the Euclidean distance, the grazing feature data means, rodent hole feature data means of each monitoring area and the historical overall grazing feature data mean, historical overall rodent hole feature data mean of alpine grasslands are clustered respectively. The monitoring areas are renumbered according to the similarity value size: AGH1’, AGH2’, AGH3’,..., AGHn’; Based on the Monte Carlo sampling algorithm, the optimal regional sampling quantity in alpine regions is determined, and then the selected monitoring areas of alpine grasslands are marked according to the numbering order. The selected monitoring areas include the grazing selected monitoring areas and the rodent hole selected monitoring areas.

[0035] In this implementation plan, the grazing feature data set of each monitoring area is specifically the grazing growth rate set of each monitoring area; the rodent hole feature data set of each monitoring area is specifically the rodent hole quantity reduction rate set of each monitoring area. The calculation formula for the grazing growth rate is: In the formula, Δε represents the grazing growth rate, and ε t represents the number of grazing livestock at the current monitoring time point, and ε t-1 represents the number of grazing livestock at the previous monitoring time point; the calculation formula for the rodent hole quantity reduction rate is: In the formula, Δθ represents the rodent hole quantity reduction rate, and θ t represents the number of rodent holes at the current monitoring time point, and θ t-1 represents the number of rodent holes at the previous monitoring time point.

[0036] The specific analysis for clustering the grazing feature data means, rodent hole feature data means of each monitoring area and the historical overall grazing feature data mean, historical overall rodent hole feature data mean of alpine grasslands respectively based on the Euclidean distance is as follows: The clustering algorithm formula is:

[0037] Where A represents the number of area A, B represents the number of area B, C represents the number of alpine grasslands, and d(A,C) FM represents the Euclidean distance between the mean of the grazing characteristic data of area A and the mean of the overall historical grazing characteristic data of the alpine grasslands, G A represents the mean of the grazing characteristic data of area A, G C represents the mean of the overall historical grazing characteristic data of the alpine grasslands, d(B,C) ST represents the Euclidean distance between the mean of the rodent hole characteristic data of area B and the mean of the overall historical rodent hole characteristic data of the alpine grasslands, H B represents the mean of the rodent hole characteristic data of area B, H C represents the mean of the overall historical rodent hole characteristic data of the alpine grasslands; furthermore, the specific algorithm formula for the similarity value is: sim(A,C) FM represents the similarity value between the mean of the grazing characteristic data of area A and the mean of the overall historical grazing characteristic data of the alpine grasslands, sim(B,C) ST represents the similarity value between the mean of the rodent hole characteristic data of area B and the mean of the overall historical rodent hole characteristic data of the alpine grasslands, sim(A,C) FM and sim(B,C) ST both range from 0 to 1, and the larger the similarity value, the higher the similarity. Compare the similarity between the regional ground data of the alpine grasslands in all monitoring areas and the overall historical regional ground data of the alpine grasslands with the similarity threshold, and number the monitoring areas of the alpine grasslands in descending order of the similarity between the regional ground data of the alpine grasslands in each monitoring area and the overall historical regional ground data of the alpine grasslands.

[0038] Specifically, to determine the optimal regional sampling quantity in the alpine region based on the Monte Carlo sampling algorithm is to simulate the situations under different sampling quantities through random sampling, and evaluate the performance indicators of each situation, and finally determine the optimal sampling quantity. Specifically, use the Monte Carlo method to randomly generate different numbers of sampling area quantities and conduct sampling. For each sampling area quantity, use the sampling points to estimate the target indicators, and the target indicators include the mean and variance of the resource distribution. According to the estimated target indicators, evaluate the performance corresponding to each sampling area quantity, and then determine the optimal regional sampling quantity.

[0039] Specifically, the sampled selected monitoring area ground data specifically includes the grazing monitoring data of the sampled selected monitoring area for grazing and the rodent hole monitoring data of the sampled selected monitoring area for rodent holes; the grazing monitoring data is specifically the number of grazing livestock.

[0040] In this implementation plan, the number of grazing livestock refers to the number of animals grazing in the selected monitoring area obtained through remote sensing equipment, including high-resolution satellite imagery or drone aerial photography technology, for livestock such as cattle, sheep, and horses. By regularly monitoring the selected monitoring area, the number and distribution of grazing livestock are counted and obtained; an excessive number of rodent holes usually indicates a decrease in the productivity of grassland vegetation. This is because excessive rodent activities may cause damage to the vegetation, thereby affecting the productivity of the grassland. In alpine grasslands, remote sensing monitoring of the grassland is carried out through remote sensing equipment, including high-resolution satellite imagery or drone aerial photography technology. Through image analysis, rodent holes on the grassland can be identified, and their number and distribution can be calculated; by monitoring the number of grazing livestock, the intensity and frequency of grazing on the grassland can be understood, and then the carrying capacity and damage degree of the grassland can be evaluated; monitoring the number of rodent holes can help evaluate the complexity and stability of the ecosystem, so as to better understand the functional state and ecological balance of the ecosystem; the monitoring data of the number of grazing livestock and the number of rodent holes can be used as input variables for the grassland degradation prediction model, reflecting the health status of the grassland ecosystem and the changes in ecological processes, and helping to predict the trend of grassland degradation and possible influencing factors.

[0041] Specifically, the specific analysis of selecting the first-rank remote sensing representative data for alpine grasslands is as follows: The meteorological altitude factors in alpine regions specifically include the highest altitude, the highest wind speed, and the lowest temperature in alpine regions; the highest altitude, the highest wind speed, and the lowest temperature in alpine regions are preprocessed, and the minimum support threshold is determined based on the distribution characteristics and statistical indicators. The remote sensing equipment in alpine regions is numbered, and the data collection information of each remote sensing equipment is obtained based on the historical data collection situation of the remote sensing equipment stored in the database. The data collection information of each remote sensing equipment specifically includes the optimal adaptation altitude, the optimal adaptation wind speed, and the optimal adaptation temperature of each remote sensing equipment; based on the confidence level and support degree analysis of the optimal adaptation altitude, the optimal adaptation wind speed, and the optimal adaptation temperature of each remote sensing equipment and the highest altitude, the highest wind speed, and the lowest temperature in alpine regions, the remote sensing equipment with the optimal ranking of the mean value of the confidence level and support degree is selected as the first-rank remote sensing equipment for alpine grasslands, and the monitoring data of the first-rank remote sensing equipment for alpine grasslands is used as the first-rank remote sensing representative data.

[0042] The database of this solution is built based on historical data collection. There are various types and quantities of remote sensing devices, which are used to monitor data multiple times. In this embodiment, the remote sensing device can be a drone equipped with a high-resolution optical camera or a multispectral camera, which can finely monitor a small area, so as to accurately monitor the number and location of livestock in a smaller area. The drone can fly low to take real-time images, which is suitable for small-scale and short-term monitoring. At the same time, the remote sensing device can also be a high-resolution satellite such as WorldView-3 or Pleiades, which can provide images with a resolution of 0.5 meters to 1 meter. Through image analysis technology (such as target recognition algorithms), the activity trajectories and distributions of livestock can be identified on a large-scale grassland, and the fine structure of mouse holes on the ground surface can be captured, which will not be elaborated here.

[0043] In this implementation plan, the specific analysis process for obtaining the data collection information of each remote sensing device is as follows: Based on the historical data of each remote sensing device collected in the database, including the device working environment parameters and the collected data; according to the parameter targets of the altitude, temperature and wind speed of the remote sensing device, screen the historical data, and retain the working environment parameters and the corresponding collected data under the parameter target requirements; perform statistics and analysis on the retained working environment parameters and the corresponding collected data under the parameter target requirements, and select the working environment parameters with the smallest data collection error of each remote sensing device as the data collection information of each remote sensing device.

[0044] Selecting the first-order remote sensing representative data of alpine grasslands is based on the Apriori algorithm. Specifically: The altitude, temperature and wind speed can be used as sub-criteria to construct a judgment matrix, compare the relative importance between various factors, and then assign weights to the altitude, temperature and wind speed according to the judgment matrix, and perform weighted analysis on the altitude, temperature and wind speed to obtain the environmental characteristic value. The specific formula is:

[0045] In the formula, HJ represents the environmental characteristic value, μ1 represents the altitude after dimensionless numerical extraction, μ2 represents the temperature after dimensionless numerical extraction, μ3 represents the wind speed after dimensionless numerical extraction, ω1 represents the weight coefficient of altitude, ω2 represents the weight coefficient of temperature, ω3 represents the weight coefficient of wind speed; based on the calculation logic of the environmental characteristic value, continuously adjust the weight coefficient to obtain the set of environmental characteristic values of each remote sensing device and the set of environmental characteristic values of the alpine region, and its support In the formula, M represents the remote sensing device number, N represents the alpine region number, Num(MN) represents the number of the same environmental characteristic values between the remote sensing device M and the alpine region N, Num(As) represents the total number of samples in the set of environmental characteristic values, and confidence Where Support(M∩N) represents the probability that the environmental characteristic values between the remote sensing device M and the alpine region N are the same, and Support(M) represents the probability of the occurrence of the environmental characteristic values of the remote sensing device M in the total number of all data.

[0046] Specifically, the specific analysis for predicting the degradation of alpine grasslands is as follows: Obtain the first-rank remote sensing representative data and the ground data of the sampled and selected monitoring areas during each monitoring time period of the first-rank remote sensing device; Use the time series model to conduct predictive analysis on the first-rank remote sensing representative data and the ground data of the sampled and selected monitoring areas, predict the future vegetation coverage of the selected monitoring areas, and comprehensively average the future predicted vegetation coverages of each sampled area to obtain the degradation prediction coefficient of alpine grasslands: Where ξ represents the degradation prediction coefficient of alpine grasslands, which is used to quantify the degradation prediction status of alpine grasslands, j represents the number of the sampled and selected monitoring areas, j = 1, 2, 3,..., j′, and j′ represents the total number of the sampled and selected monitoring areas.

[0047] In this implementation plan, the prediction of the degradation of alpine grasslands also includes real-time monitoring of the operating status of the first-rank remote sensing device. For the fault status of the first-rank remote sensing device detected in real time, based on the above confidence and support analysis, select the second-rank remote sensing device as the second-rank remote sensing device for alpine grasslands. The monitoring data of the second-rank remote sensing device for alpine grasslands is used as the second-rank remote sensing representative data. Conduct predictive analysis through the second-rank remote sensing representative data and the ground data of the sampled and selected monitoring areas to predict the future vegetation coverage of the sampled and selected monitoring areas. When a fault status is detected by the second-rank remote sensing device, switch to the third-rank remote sensing device in the same way as above.

[0048] Specifically, the time series model uses the ARIMAX model. The specific steps for conducting predictive analysis on the first-rank remote sensing representative data and the ground data of the sampled and selected monitoring areas through the time series model are as follows: Obtain the first-rank remote sensing representative data and the ground data of the sampled and selected monitoring areas as the data for prediction, and clean and preprocess the first-rank remote sensing representative data and the ground data of the sampled and selected monitoring areas; Establish the ARIMAX model, and use the historical remote sensing data and historical ground data of alpine grasslands to perform maximum likelihood estimation fitting on the ARIMAX model to estimate the model parameters; Use the residual analysis method to diagnose the fitted ARIMAX model to check whether the residuals of the model conform to the white noise hypothesis; Use the fitted ARIMAX model to predict the future alpine grassland monitoring data.

[0049] In this implementation plan, the first-rank remote sensing representative data specifically includes vegetation coverage. The exogenous variables in the ARIMAX model include the number of grazing livestock and the number of rodent holes. The ARIMAX model formula is: yt = β0 + β1y t-1 + α1Δy t-1 + γ1ε t + γ2ε t-1 + γ3θ t + γ4θ t-1 + ∈ t ; where y t represents the vegetation coverage at time point t, y t-1 represents a lag term of the vegetation coverage, Δy t-1 represents a difference term of the vegetation coverage, ε t represents the number of grazing livestock at time point t, ε t-1 represents a difference term of the number of grazing livestock, θ t represents the number of rodent holes at time point t, θ t-1 represents a difference term of the number of rodent holes, β0 and β1 represent the coefficients of the autoregressive part, representing the autocorrelation of the vegetation coverage, α1 represents the coefficient of the difference part, representing the stationarity of the vegetation coverage, γ1, γ2, γ3, γ4 represent the coefficients of the exogenous variables, representing the influence of the grazing quantity and the number of rodent holes on the vegetation coverage, ∈ t represents the error term of the ARIMAX model, representing the random fluctuation that cannot be explained by the ARIMAX model.

[0050] The specific analysis for obtaining the model parameters (β0, β1, α1, γ1, γ2, γ3, γ4) through maximum likelihood estimation fitting is as follows: The error term ∈ t follows a normal distribution with a mean of 0 and a variance of σ 2 . The specific formula of the likelihood function is: where T represents the number of samples, ψ represents the model parameters (β0, β1, α1, γ1, γ2, γ3, γ4), y t represents the vegetation coverage monitored by the remote sensing device, x t represents the exogenous variables (the number of grazing livestock and the number of rodent holes); By taking the logarithm of the likelihood function, the log-likelihood function is obtained:

[0051] Maximizing the log-likelihood function is equivalent to minimizing the sum of the squares of the errors. Therefore, by maximizing the log-likelihood function, β0, β1, α1, γ1, γ2, γ3, γ4 are obtained.

[0052] The specific analysis of diagnosing the fitted ARIMAX model using the residual analysis method is as follows: The ARIMAX model is fitted using the historical remote sensing data and historical ground data of alpine grasslands to obtain parameter estimates, and then the residual sequence of the model is calculated, that is, the difference between the observed values and the model predicted values. By observing the autocorrelation function and partial autocorrelation function plots of the residual sequence, it is checked whether there is significant autocorrelation or partial autocorrelation. If there is autocorrelation or partial autocorrelation in the residual sequence, it means there is a problem with the ARIMAX model and further adjustment or improvement is needed. By performing residual analysis on the ARIMAX model, it helps to determine the applicability and reliability of the model, thereby improving the accuracy and credibility of alpine grassland degradation prediction.

[0053] See Figure 2 , an alpine grassland degradation monitoring and prediction system, including: a sampling and selected monitoring area module, used to determine the grazing sampling and selected monitoring area and the rodent hole sampling and selected monitoring area of the alpine grassland based on the grazing monitoring data, rodent hole monitoring data of each monitoring area of the alpine grassland, and the historical area ground data of the alpine grassland; a ground data acquisition module, used to monitor the grazing sampling and selected monitoring area and the rodent hole sampling and selected monitoring area of the alpine grassland to obtain the ground data of the sampling and selected monitoring area; a degradation prediction module, used to analyze the data collection situations of multiple remote sensing devices based on the meteorological and altitude factors in alpine regions, select the first-rank remote sensing representative data of the alpine grassland, and evaluate the grassland monitoring status of the sampling and selected monitoring area in combination with the ground data of the sampling and selected monitoring area, and then realize the prediction of alpine grassland degradation

[0054] In summary, this application has at least the following effects:

[0055] By comprehensively analyzing the grazing monitoring data, rodent hole monitoring data, and historical ground data of alpine grasslands, as well as using the data collection situations of multiple remote sensing devices, it can provide comprehensive and accurate alpine grassland monitoring information; using the ground data of the grazing sampling and selected monitoring area and the rodent hole sampling and selected monitoring area, and combining with remote sensing data for evaluation, it can more effectively monitor the status and changes of alpine grasslands; combining meteorological and altitude factors and selecting the first-rank remote sensing representative data can timely obtain high-quality monitoring data, providing timely support for the prediction of alpine grassland degradation. By evaluating the grassland monitoring status of the sampling and selected monitoring area, combining historical data and meteorological factors, it can realize the prediction of the degradation trend of alpine grasslands and help take corresponding protection and management measures.

[0056] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods and systems. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0057] The present invention is described with reference to the flowcharts and structural diagrams of methods and systems according to the embodiments of the present invention. It should be understood that each process and module combination in the flowcharts and structural diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and structures Figure 1 one module or multiple modules.

[0058] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one process or multiple processes and structures Figure 1 one module or multiple modules.

[0059] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one process or multiple processes and structures Figure 1 one module or multiple modules.

[0060] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0061] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for monitoring and predicting the degradation of alpine grasslands, characterized in that, Including the following steps: Perform similarity analysis on the regional ground data of alpine grasslands in all monitoring areas based on the historical regional ground data of alpine grasslands, and number each monitoring area of alpine grasslands in descending order according to the similarity between the regional ground data of alpine grasslands in each monitoring area and the historical regional ground data of alpine grasslands; Determine the optimal number of monitoring areas among multiple monitoring areas for each monitoring area of alpine grasslands through the Monte Carlo algorithm, and then mark the selected monitoring areas of alpine grasslands according to the number ranking; and select monitoring areas as selected monitoring areas in descending order according to the similarity between each monitoring area and the historical regional ground data of alpine grasslands, and conduct monitoring to obtain the ground data of the selected monitoring areas; Based on the meteorological and altitude factors in alpine regions, analyze the data collection situation of multiple remote sensing devices, select the first-rank remote sensing representative data of alpine grasslands, and combine the ground data of the selected monitoring areas to evaluate the grassland degradation status of the monitoring areas, thereby realizing the prediction of alpine grassland degradation; The monitoring areas include grazing monitoring areas and rodent hole monitoring areas; The specific analysis of selecting the first-rank remote sensing representative data of alpine grasslands is as follows: The meteorological and altitude factors in alpine regions specifically include the highest altitude, the highest wind speed, and the lowest temperature in alpine regions; Preprocess the highest altitude, the highest wind speed, and the lowest temperature in alpine regions, and then determine the minimum support threshold, number the remote sensing devices in alpine regions, and obtain the data collection information of each remote sensing device based on the historical data collection situation of the remote sensing devices stored in the database. The data collection information of each remote sensing device specifically includes the optimal adaptation altitude, the optimal adaptation wind speed, and the optimal adaptation temperature of each remote sensing device; Based on the confidence level and support level analysis of the optimal adaptation altitude, the optimal adaptation wind speed, and the optimal adaptation temperature of each remote sensing device and the highest altitude, the highest wind speed, and the lowest temperature in alpine regions, select the remote sensing device with the best comprehensive ranking based on the confidence level and support level as the first-rank remote sensing device of alpine grasslands, and the monitoring data of the first-rank remote sensing device of alpine grasslands as the first-rank remote sensing representative data.

2. The method for monitoring and predicting alpine grassland degradation according to claim 1, characterized in that The regional ground data of the alpine grasslands includes grazing monitoring data and rodent hole monitoring data. The specific analysis of determining the grazing selected monitoring areas and rodent hole selected monitoring areas in alpine regions is as follows: Divide and number the alpine grasslands according to geographical location coordinates: AGH1, AGH2, AGH3,..., AGHn; Extract the historical grazing monitoring data and rodent hole monitoring data of each monitoring area from the database of alpine grasslands, preprocess and extract features from the grazing monitoring data and rodent hole monitoring data to obtain the grazing feature data set and rodent hole feature data set of each monitoring area respectively, and further obtain the grazing feature data mean and rodent hole feature data mean of each monitoring area; Extract the ground data of the historical area of alpine grassland from the database. The historical ground data includes the overall grazing data and the overall data of rodent holes in alpine grassland. Preprocess and extract features from the historical overall grazing data and the historical overall data of rodent holes to obtain the historical overall grazing feature data set and the historical overall rodent hole feature data set of alpine grassland respectively, and further obtain the mean value of the historical overall grazing feature data and the mean value of the historical overall rodent hole feature data of alpine grassland; Based on the Euclidean distance, cluster the mean value of grazing feature data, the mean value of rodent hole feature data in each monitoring area, the mean value of the historical overall grazing feature data of alpine grassland, and the mean value of the historical overall rodent hole feature data of alpine grassland respectively. Re-number each monitoring area according to the magnitude of the similarity value: AGH1 ’ , AGH2 ’ , AGH3 ’ ,..., AGHn ’ ; Determine the optimal number of monitoring areas in alpine regions based on the Monte Carlo sampling algorithm, and then mark the selected monitoring areas of alpine grassland according to the number ranking. The selected monitoring areas include the selected grazing monitoring areas and the selected rodent hole monitoring areas.

3. A method for monitoring and predicting the degradation of alpine grasslands according to claim 2, characterized in that, The grazing feature data set of each selected monitoring area is specifically the grazing growth rate set of each selected monitoring area; the rodent hole feature data set of each selected monitoring area is specifically the rodent hole number reduction rate set of each selected monitoring area.

4. A method for monitoring and predicting the degradation of alpine grasslands according to claim 1, characterized in that, The grazing monitoring data is specifically the number of grazing livestock.

5. A method for monitoring and predicting the degradation of alpine grasslands according to claim 1, characterized in that, The specific analysis process for obtaining the data acquisition information of each remote sensing device is as follows: Collect the historical data of each remote sensing device from the database, including the equipment working environment parameters and the collected data; according to the parameter targets of the altitude, temperature and wind speed of the remote sensing device, screen the historical data and retain the working environment parameters and the corresponding collected data under the parameter target requirements; Statistically analyze the working environment parameters and the corresponding collected data retained under the parameter target requirements, and select the working environment parameters with the smallest data acquisition error of each remote sensing device as the data acquisition information of each remote sensing device.

6. The method for monitoring and predicting alpine grassland degradation according to claim 1, characterized in that The specific analysis for realizing the prediction of alpine grassland degradation is as follows: Obtain the first-rank remote sensing representative data and the ground data of the selected monitoring areas of the first-rank remote sensing device in each monitoring time period; Use the time series model to conduct predictive analysis on the first-rank remote sensing representative data and the ground data of the selected monitoring areas, predict the future vegetation coverage of the selected monitoring areas, and comprehensively average the future predicted vegetation coverage of each selected monitoring area to obtain the degradation prediction coefficient of alpine grassland. The degradation prediction coefficient of alpine grassland is used to quantify the degradation prediction status of alpine grassland.

7. A method for monitoring and predicting the degradation of alpine grasslands according to claim 6, characterized in that, The time series model adopts the ARIMAX model. The specific steps for conducting predictive analysis on the first-rank remote sensing representative data and the ground data of the selected monitoring areas through the time series model are as follows: Obtain the first-rank remote sensing representative data and the ground data of the selected monitoring areas as the data for prediction, and clean and preprocess the first-rank remote sensing representative data and the ground data of the selected monitoring areas; Establish an ARIMAX model, and use the historical remote sensing data and historical ground data of alpine grassland to perform maximum likelihood estimation fitting on the ARIMAX model to estimate the model parameters; Use the residual analysis method to diagnose the fitted ARIMAX model and check whether the residuals of the model conform to the white noise hypothesis; Use the fitted ARIMAX model to predict future alpine grassland monitoring data.

8. A method for monitoring and predicting alpine grassland degradation according to claim 7, characterized in that The first-order remote sensing representative data specifically includes vegetation coverage. The exogenous variables in the ARIMAX model include the number of grazing livestock and the number of rodent holes. The ARIMAX model formula is: ； In the formula, represents the vegetation coverage at time point , represents a lag term of the vegetation coverage, represents a difference term of the vegetation coverage, represents the number of grazing livestock at time point , represents a difference term of the number of grazing livestock, represents the number of rodent holes at time point , represents a difference term of the number of rodent holes, , represents the coefficient of the autoregressive part, indicating the autocorrelation of the vegetation coverage, represents the coefficient of the difference part, indicating the stationarity of the vegetation coverage, , , , represent the coefficients of the exogenous variables, indicating the impacts of the grazing amount and the number of rodent holes on the vegetation coverage, represents the error term of the ARIMAX model, indicating the random fluctuations that the ARIMAX model cannot explain.

9. A monitoring and prediction system for alpine grassland degradation, which applies the monitoring and prediction method for alpine grassland degradation described in any one of claims 1-8, is characterized in that, Include: Select the monitoring area module, which is used to determine the grazing selected monitoring area and the rodent hole selected monitoring area of the alpine grassland based on the grazing monitoring data and rodent hole monitoring data of each selected monitoring area of the alpine grassland and the historical area ground data analysis of the alpine grassland; The ground data acquisition module is used to monitor the grazing selected monitoring area and the rodent hole selected monitoring area of the alpine grassland to obtain the ground data of the selected monitoring area; The degradation prediction module is used to analyze the data collection situation of multiple remote sensing devices based on the meteorological altitude factors in the alpine region, select the first-order remote sensing representative data of the alpine grassland, and evaluate whether the grassland in the selected monitoring area is degraded and the degree of its degradation in combination with the ground data of the selected monitoring area.

Images