Land degradation condition evaluation method and system

Abstract

The invention discloses a land degradation condition evaluation method and system, and relates to the technical field of image processing, and the method comprises the steps: collecting a land image through multi-source remote sensing, and classifying land organisms through multi-level extraction of remote sensing spatial features; constructing a space-time coupled dynamic particle evolution model based on the land organism distribution map, and performing dynamic particle evolution prediction on land organisms; establishing a non-biological value quantitative model, performing weight distribution according to historical data and a machine learning algorithm, and dynamically calculating a multi-dimensional value index system; and evaluating the land degradation condition according to the land abiotic value historical value and the dynamic particle evolution prediction of the land organisms. According to the method, adaptive feature extraction is carried out through the combination of deformable convolution and transfer learning, the classification precision under a complex terrain is improved, land degradation is evaluated by constructing a particle evolution model to quantify the space-time response of a biocenosis and constructing a multi-dimensional non-biological value index system at the same time, and the credibility of a block chain is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for assessing land degradation status. Background Art

[0002] Land degradation not only includes soil erosion, salinization, desertification and other phenomena, but also covers land desertification, biodiversity loss and soil structure degradation. In order to effectively assess the land degradation status and take corresponding protection measures, traditional assessment methods rely on ground surveys and field sampling. These methods are usually costly, time-consuming and unable to cover large areas. With the advancement of remote sensing technology, multi-source remote sensing data (such as satellite remote sensing, drone remote sensing, etc.) has become an important tool for assessing land degradation. Remote sensing technology can quickly and accurately obtain a wide range of land degradation information by analyzing the reflection and scattering information of different bands on the surface, providing support for the rational management and protection of land resources.

[0003] At present, the Chinese invention patent with application number CN2019103876513 discloses a method and system for evaluating land degradation by integrating multi-source remote sensing indicators. The present invention estimates the index of land degradation degree based on remote sensing, obtains a comprehensive land degradation index by integrating multiple indicators, and realizes rapid identification of land degradation from remote sensing images. However, the existing technology cannot perform adaptive feature extraction by combining deformable convolution with transfer learning, cannot improve classification accuracy under complex terrain, cannot quantify the spatiotemporal response of biological communities by constructing particle evolution models, and simultaneously construct a multidimensional abiotic value indicator system to evaluate land degradation, and cannot achieve data transparency and support cross-institutional collaborative governance. Summary of the invention

[0004] The technical problem solved by the present invention is that the existing technology cannot perform adaptive feature extraction through the combination of deformable convolution and transfer learning, cannot improve the classification accuracy under complex terrain, cannot quantify the spatiotemporal response of biological communities by constructing particle evolution models and simultaneously construct a multidimensional abiotic value indicator system to evaluate land degradation, and cannot achieve data transparency and support cross-institutional collaborative governance.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for assessing land degradation, comprising the following steps: Step S1: multi-source remote sensing is used to collect land images, and land organisms are classified by extracting remote sensing spatial features at multiple levels; Step S2: constructing a spatiotemporal coupled dynamic particle evolution model based on the land organism distribution map, and predicting the dynamic particle evolution of land organisms; Step S3: Establish a quantitative model for abiotic value, calculate the historical value of abiotic value of land, assign weights based on historical data and machine learning algorithms, and dynamically calculate a multi-dimensional value indicator system; Step S4: Assess the land degradation status based on the historical value of the land non-living things and the dynamic particle evolution prediction of the land organisms.

[0006] Preferably, remote sensing images of the target land are collected by multi-source remote sensing equipment, and the remote sensing images include multispectral images, thermal infrared images, lidar point cloud data, normalized difference vegetation index NDVI and Sentinel-1 SAR dual-polarization data, and the multispectral images include more than 11 spectral bands, and the spectral bands include 3 near-infrared narrowband channels dedicated to chlorophyll fluorescence detection.

[0007] Preferably, geometric correction, radiation correction and spatiotemporal alignment operations are performed on the remote sensing image, and a deformable convolution model is used to extract a first remote sensing spatial feature, wherein the first remote sensing spatial feature includes a spectral feature, a texture feature and a structural feature; Performing cross-modal feature alignment on the first remote sensing spatial features through a transfer learning pre-training model to obtain a second remote sensing spatial feature that is aligned in time and space; ResNet is used to extract low-level features of the second remote sensing spatial features, and the low-level features are secondary mined into global dependencies and high-level features through Transformer. The global dependencies and high-level features are classified through a random forest model to obtain a classification of land biological cover types. The land biological cover type classification is plotted into a particle distribution structure diagram through statistical software, and different types of organisms are represented on the same land biological distribution map through different colors and shapes.

[0008] Preferably, a spatiotemporally coupled dynamic particle evolution model is constructed based on the land biological distribution map, and big data is used to collect the number or area loss rate of the current land biological community, meteorological data and soil moisture time series data, wherein the meteorological data includes temperature, precipitation and wind speed, and each biological community is mapped into a particle unit with adaptive quality parameters, and the meteorological data is used to obtain abnormal values ​​through random forests, and the abnormal values ​​are compared with time to obtain an abnormal index; A spatiotemporal feature matrix is ​​constructed based on the land biological distribution map, wherein the columns of the spatiotemporal feature matrix represent time series and the rows represent biological types. The unit feature matrix of the spatiotemporal feature matrix is ​​solved by matrix basic operations, and the node data corresponding to the unit feature matrix is ​​standardized to obtain a solution space probability matrix of the spatiotemporal feature matrix. The solution space probability matrix and the second remote sensing spatial feature are weightedly merged by sliding window in the column direction to obtain a spatiotemporal feature probability distribution matrix. The spatiotemporal feature probability distribution matrix is ​​aligned with the time resolution of multi-source data by sliding window method to generate a standardized spatiotemporal data set.

[0009] Preferably, each biome in the land biological distribution map is mapped as a dynamic particle unit carrying gene entropy value, energy metabolism rate and environmental response function, wherein the gene entropy value is obtained by calculating the species genetic diversity index, and the environmental response function is obtained by integrating the multi-dimensional characteristics of the number or area loss rate of the current land biological community, meteorological data and soil moisture time series data; The gene entropy value, energy metabolism rate and environmental response function are used as particle parameters, the variance of each particle parameter of the dynamic particle unit corresponding to each biological community is calculated, and the F statistic of each particle parameter is calculated based on the variance.

[0010] Preferably, the F statistics of each particle parameter corresponding to each dynamic particle unit and the standardized spatiotemporal data set are subjected to spatiotemporal weighted fusion and input into the LSTM-Transformer hybrid neural network, wherein the LSTM layer is used to process the meteorological data and the soil moisture time series data, extract the long-range dependency features, and the Transformer multi-head attention mechanism is used to fuse the spatial distribution features through the multi-head attention mechanism, capture the spatial correlation of cross-regional biological migration, and use residual connection to bridge the output data of the macro or micro model to generate the particle group evolution trajectory corresponding to the dynamic particle unit in the future time window; The probability cloud map of the particle swarm evolution trajectory in the future time window is output, and the prediction reliability is double-verified by using Brier score and KL divergence. When the prediction value is lower than 85%, the online update of the model based on transfer learning is triggered.

[0011] Preferably, step S3 comprises: The value indicators of the historical value of the abiotic value of the land include the monetary value created on the same piece of land, the ecological environment status and the stability of the ecosystem and the protection area of ​​the specific biological environment; Establish a non-biological value quantification model, obtain the historical economic operation data of the target land through the blockchain distributed ledger, simultaneously obtain the satellite remote sensing ecological index and ecosystem service value equivalent database, adopt a multi-objective optimization algorithm empowered by the attention mechanism, and dynamically calculate the multi-dimensional value indicator system.

[0012] Preferably, the multidimensional value indicator system includes economic value indicators, ecological stability indicators and biological protection intensity indicators. The economic value indicators include GDP output per unit area, land transfer transaction price and agricultural product market value. The ecological stability indicators include biodiversity index, soil and water conservation coefficient and carbon sink capacity. The biological protection intensity indicators include the coverage rate of endangered species habitats, the proportion of nature reserves and the area of ​​ecological red line areas. The weight distribution adopts the improved AdaBoost integrated learning framework, uses the SMOTE-Tomek joint sampling algorithm to deal with the category imbalance problem of the multi-dimensional value indicator system data, and extracts the principal component features with a cumulative contribution rate ≥ 85% through principal component analysis PCA; Integrating a cost-sensitive learning mechanism into the improved AdaBoost ensemble learning framework, defining a misclassification cost matrix according to the improved AdaBoost ensemble learning framework incorporating the cost-sensitive learning mechanism, including constructing a multi-head cross-attention mechanism module and using the improved AdaBoost ensemble learning framework for weight allocation; The modules for building a multi-head cross attention mechanism include: The nonlinear correlation between economic value indicators and ecological stability indicators is calculated through the graph neural network GNN, and the dynamic changes of time series data are captured through the gated temporal attention unit GTAU.

[0013] The weight allocation using the improved AdaBoost ensemble learning framework includes: AdaBoost ensemble learning framework is used to train multiple weak classifiers, and all outputs of the weak classifiers are weighted and summed into a strong classifier. When the strong classifier is trained iteratively, the weight is adjusted according to the error rate of the strong classifier. The adjustment logic includes: training the next strong classifier, when the output of the next strong classifier focuses on the data point that was misclassified by the previous strong classifier, the current weight is output as the final weight distribution, and the weighted economic value index and ecological stability index are obtained; The empowered economic value index and ecological stability index are input into the blockchain smart contract, and the inter-period discount calculation is performed in combination with the time value factor. The time value factor includes the discount rate and the inflation rate. The inter-period discount mathematical expression is: ; in, is the discounted value at time t, is the value at the current moment, is the discount rate and t is the time.

[0014] Preferably, the step S4 comprises: The particle swarm evolution trajectory and the multi-dimensional value indicator system are used as sub-models for local training through differential privacy protection technology. The central server aggregates the degradation features of each region through an adaptive knowledge distillation algorithm to build a degradation assessment model including: The modified universal soil loss equation is used as the physical loss function, and its mathematical expression is: A = R × K × LS × C × P; Among them, A is the average annual soil loss, R is the rainfall erosion factor, K is the soil erodibility factor, LS is the terrain factor, C is the vegetation cover factor, and P is the soil and water conservation measures factor.

[0015] The Neural Radiation Field (NeRF) technology is used to model the land degradation process in a spatiotemporal continuous manner, and a continuous spatiotemporal remote sensing land degradation model is obtained. A convolutional neural network (CNN) is used to extract features from the continuous spatiotemporal remote sensing land degradation model, a U-Net architecture containing 64 convolution kernels is constructed, a spatial probability prediction of degradation hotspot areas is obtained, and a risk level is output. The risk level includes a first risk level, a second risk level, and a third risk level. The first risk level includes a degradation probability value of the spatial probability prediction being less than 0.2, the second risk level includes a degradation probability value of the spatial probability prediction being between 0.2 and 0.5, and the third risk level includes a degradation probability value of the spatial probability prediction being greater than 0.5; The continuous spatiotemporal remote sensing land degradation model was deployed on the Google Earth Engine platform. Multi-temporal Landsat and Sentinel data stacks were used to extract the boundaries of objects through object-oriented segmentation technology, and the three-level classification of wetlands, woodlands and cultivated land was achieved in combination with decision tree classification rules.

[0016] A land degradation status assessment system, which is used to implement a land degradation status assessment method, comprising a biological classification module, a biological evolution module, a value evolution module and a degradation assessment module; The biological classification module is used to collect land images through multi-source remote sensing, and classify land organisms by extracting remote sensing spatial features at multiple levels; The biological evolution module is used to construct a spatiotemporal coupled dynamic particle evolution model based on the land biological distribution map, and to predict the dynamic particle evolution of land organisms; The value evolution module is used to establish a quantitative model for abiotic value, calculate the historical value of abiotic value of land, assign weights based on historical data and machine learning algorithms, and dynamically calculate a multi-dimensional value indicator system; The degradation assessment module is used to assess the land degradation status based on the historical value of the land non-biological class and the dynamic particle evolution prediction of the land organisms.

[0017] The beneficial effects of the present invention are as follows: adaptive feature extraction is performed through the combination of deformable convolution and transfer learning to improve the classification accuracy under complex terrain, land degradation is evaluated by constructing a particle evolution model to quantify the spatiotemporal response of biological communities and simultaneously constructing a multidimensional abiotic value indicator system, blockchain is enhanced in credibility, distributed ledgers ensure data transparency, and cross-institutional collaborative governance is supported. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A basic flow chart of a land degradation status assessment method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0020] Reference Figure 1 , as an embodiment of the present invention, provides a method for assessing land degradation status, comprising the following steps: Step S1: multi-source remote sensing is used to collect land images, and land organisms are classified by extracting remote sensing spatial features at multiple levels; Step S2: constructing a spatiotemporal coupled dynamic particle evolution model based on the land organism distribution map, and predicting the dynamic particle evolution of land organisms; Step S3: Establish a quantitative model for abiotic value, calculate the historical value of abiotic value of land, assign weights based on historical data and machine learning algorithms, and dynamically calculate a multi-dimensional value indicator system; Step S4: Assess the land degradation status based on the historical value of the land non-living things and the dynamic particle evolution prediction of the land organisms.

[0021] This solution innovatively integrates multi-source data fusion of deep learning, biological evolution modeling of dynamic particle systems, and cutting-edge ecological value quantification technology enabled by blockchain to form a land degradation assessment system that is technologically advanced and practical.

[0022] Remote sensing images of the target land are collected through multi-source remote sensing equipment. The remote sensing images include multispectral images, thermal infrared images, lidar point cloud data, normalized difference vegetation index NDVI and Sentinel-1 SAR dual-polarization data. The multispectral images include more than 11 spectral bands, and the spectral bands include 3 near-infrared narrow-band channels dedicated to chlorophyll fluorescence detection.

[0023] The remote sensing images are geometrically corrected, radiometrically corrected, and aligned in time and space. The deformable convolution model is used to extract more representative first remote sensing spatial features, which can effectively improve the model performance, especially when the image has non-rigid deformation or geometric changes. The first remote sensing spatial features include spectral features, texture features, and structural features. The first remote sensing spatial feature is aligned across modal features through a transfer learning pre-training model to obtain a second remote sensing spatial feature that is aligned in time and space; ResNet is used to extract the low-level features of the second remote sensing spatial features, and the low-level features are secondary mined into global dependencies and high-level features through Transformer. In this way, we can not only extract rich local features, but also capture global spatial information. The global dependencies and high-level features are classified through the random forest model to obtain the land biological cover type classification. The land biological cover type classification is plotted into a particle distribution structure diagram through statistical software, and different types of organisms are represented on the same land biological distribution map through different colors and shapes.

[0024] Colors include the three primary colors, and shapes include squares, triangles, and circles.

[0025] Deformable convolution is a convolution method that introduces an offset mechanism based on traditional convolution, which enables the convolution operation to adapt to objects or image areas with large shape changes. In land biological classification, the targets in remote sensing images may have irregular shapes and different scales. Therefore, the use of deformable convolution can effectively enhance the robustness of the network and improve the ability to recognize complex land features.

[0026] Based on the land biological distribution map, a spatiotemporal coupled dynamic particle evolution model is constructed. Big data is used to collect the number or area loss rate of the current land biological community, meteorological data and soil moisture time series data. The meteorological data includes temperature, precipitation and wind speed. Each biological community is mapped into a particle unit with adaptive quality parameters. The meteorological data is used to obtain outliers through random forests. The outliers are compared with time to obtain an anomaly index. A spatiotemporal feature matrix is ​​constructed based on the land biological distribution map. The columns of the spatiotemporal feature matrix represent time series and the rows represent biological types. The unit feature matrix of the spatiotemporal feature matrix is ​​solved through basic matrix operations. The node data corresponding to the unit feature matrix is ​​standardized to obtain the solution space probability matrix of the spatiotemporal feature matrix. The solution space probability matrix and the second remote sensing spatial feature are weightedly merged by sliding window in the column direction to obtain the spatiotemporal feature probability distribution matrix. The spatiotemporal feature probability distribution matrix is ​​aligned with the time resolution of multi-source data through the sliding window method to generate a standardized spatiotemporal dataset.

[0027] Each biome in the land biomass distribution map is mapped into a dynamic particle unit carrying gene entropy value, energy metabolism rate and environmental response function, where the gene entropy value is obtained by calculating the species genetic diversity index, and the environmental response function is obtained by integrating the multi-dimensional characteristics of the current land biome number or area loss rate, meteorological data and soil moisture time series data; The gene entropy value reflects the level of genetic diversity, the environmental response function represents the sensitivity to temperature and humidity fluctuations, and the energy metabolism rate is calculated based on NDVI and photosynthetically active radiation; The gene entropy, energy metabolic rate and environmental response function are used as particle parameters, and the variance of each particle parameter of the dynamic particle unit corresponding to each biological community is calculated. The F statistic of each particle parameter is calculated based on the variance, and the high potential search area is identified through the gradient boosting decision tree to enhance the local convergence efficiency.

[0028] The F statistics of each particle parameter corresponding to each dynamic particle unit and the standardized spatiotemporal data set are weightedly fused in spatiotemporal correspondence and input into the LSTM-Transformer hybrid neural network, where the LSTM layer is used to process meteorological data and soil moisture time series data to extract long-range dependency features, and the Transformer multi-head attention mechanism is used to fuse spatial distribution features through the multi-head attention mechanism to capture the spatial correlation of cross-regional biological migration, and use residual connections to bridge the output data of the macro or micro model to generate the particle group evolution trajectory corresponding to the dynamic particle unit in the future time window; The probability cloud map of the particle swarm evolution trajectory in the future time window is output, and the prediction reliability is double-verified by using Brier score and KL divergence. When the prediction value is lower than 85%, the online update of the model based on transfer learning is triggered.

[0029] Step S3 includes: The value indicators of the historical value of the abiotic value of land include the monetary value created on the same piece of land, the ecological environment status and the stability of the ecosystem and the protection area of ​​specific biological environments; Establish a non-biological value quantification model, obtain the historical economic operation data of the target land through the blockchain distributed ledger, simultaneously obtain the satellite remote sensing ecological index and ecosystem service value equivalent database, adopt a multi-objective optimization algorithm empowered by the attention mechanism, and dynamically calculate the multi-dimensional value indicator system.

[0030] The multi-dimensional value indicator system includes economic value indicators, ecological stability indicators and biological protection intensity indicators. Economic value indicators include GDP output per unit area, land transfer transaction price and agricultural product market value. Ecological stability indicators include biodiversity index, soil and water conservation coefficient and carbon sink capacity. Biological protection intensity indicators include habitat coverage of endangered species, proportion of nature reserves and area of ​​ecological red line areas. The weight distribution adopts the improved AdaBoost integrated learning framework, uses the SMOTE-Tomek joint sampling algorithm to deal with the category imbalance problem of the multi-dimensional value indicator system data, and extracts the principal component features with a cumulative contribution rate ≥ 85% through principal component analysis PCA; Incorporating a cost-sensitive learning mechanism into the improved AdaBoost ensemble learning framework, defining a misclassification cost matrix based on the improved AdaBoost ensemble learning framework incorporating the cost-sensitive learning mechanism, including constructing a multi-head cross-attention mechanism module and using the improved AdaBoost ensemble learning framework for weight allocation; The modules for building a multi-head cross attention mechanism include: The nonlinear correlation between economic value indicators and ecological stability indicators is calculated through the graph neural network GNN, and the dynamic changes of time series data are captured through the gated temporal attention unit GTAU. The gating mechanism can adjust the contribution of each time step by learning the weight of the sequence, and the self-attention mechanism is used to capture the lag effect and mutation characteristics.

[0031] The weight allocation using the improved AdaBoost ensemble learning framework includes: Use the AdaBoost ensemble learning framework to train multiple weak classifiers, and add all the outputs of the weak classifiers to form a strong classifier. When the strong classifier is trained iteratively, the weight is adjusted according to the error rate of the strong classifier. The adjustment logic includes: training the next strong classifier, when the output of the next strong classifier focuses on the data point that was misclassified by the previous strong classifier, output the current weight as the final weight distribution, and obtain the weighted economic value index and ecological stability index; The empowered economic value index and ecological stability index are input into the blockchain smart contract, and the inter-period discount calculation is performed in combination with the time value factor. The time value factor includes the discount rate and the inflation rate. The discount rate at each time point is considered to estimate the future economic and ecological value. The inter-period discount mathematical expression is: ; in, is the discounted value at time t, is the value at the current moment, is the discount rate and t is the time.

[0032] Step S4 includes: The particle swarm evolution trajectory and multi-dimensional value indicator system are used as sub-models for local training through differential privacy protection technology. The central server aggregates the degradation features of each region through an adaptive knowledge distillation algorithm to build a degradation assessment model including: The modified universal soil loss equation is used as the physical loss function, and its mathematical expression is: A = R × K × LS × C × P; Among them, A is the average annual soil loss, R is the rainfall erosion factor, K is the soil erodibility factor, LS is the terrain factor, C is the vegetation cover factor, and P is the soil and water conservation measures factor.

[0033] The Neural Radiation Field (NeRF) technology is used to model the land degradation process in a spatiotemporal continuous manner, and a continuous spatiotemporal remote sensing land degradation model is obtained. Convolutional neural network (CNN) was used to extract features from the continuous spatiotemporal remote sensing land degradation model, and a U-Net architecture containing 64 convolution kernels was constructed to obtain spatial probability predictions of degradation hotspots and output risk levels. The risk levels included the first risk level, the second risk level, and the third risk level. The first risk level included a degradation probability value of less than 0.2 predicted by the spatial probability prediction, the second risk level included a degradation probability value between 0.2 and 0.5 predicted by the spatial probability prediction, and the third risk level included a degradation probability value of greater than 0.5 predicted by the spatial probability prediction. The continuous spatiotemporal remote sensing land degradation model was deployed on the Google Earth Engine platform. The multi-temporal Landsat and Sentinel data stacks were used to extract the boundaries of land objects through object-oriented segmentation technology, and the three-level classification of wetlands, forests and cultivated land was achieved by combining decision tree classification rules.

[0034] A land degradation status assessment system, which is used to implement a land degradation status assessment method, comprising a biological classification module, a biological evolution module, a value evolution module and a degradation assessment module; The biological classification module is used to collect land images through multi-source remote sensing, and classify land organisms by extracting remote sensing spatial features at multiple levels; The biological evolution module is used to build a spatiotemporal coupled dynamic particle evolution model based on the land biological distribution map, and to predict the dynamic particle evolution of land organisms; The value evolution module is used to establish a quantitative model for abiotic value, calculate the historical value of abiotic value of land, assign weights based on historical data and machine learning algorithms, and dynamically calculate a multi-dimensional value indicator system; The degradation assessment module is used to assess the land degradation status based on the historical values ​​of land abiotic values ​​and the dynamic particle evolution prediction of land organisms.

[0035] The present invention combines deformable convolution with transfer learning to perform adaptive feature extraction, improves classification accuracy under complex terrain, quantifies the spatiotemporal response of biological communities by constructing a particle evolution model, and simultaneously constructs a multidimensional abiotic value indicator system to evaluate land degradation, thereby enhancing the credibility of blockchain, ensuring data transparency with a distributed ledger, and supporting cross-institutional collaborative governance.

[0036] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0037] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for assessing land degradation, characterized in that: The following steps are involved: Step S1: multi-source remote sensing is used to collect land images, and land organisms are classified by extracting remote sensing spatial features at multiple levels; Step S2: constructing a spatiotemporal coupled dynamic particle evolution model based on the land organism distribution map, and predicting the dynamic particle evolution of land organisms; Step S3: Establish a quantitative model for abiotic value, calculate the historical value of abiotic value of land, assign weights based on historical data and machine learning algorithms, and dynamically calculate a multi-dimensional value indicator system; Step S4: Assess the land degradation status based on the historical value of the land non-living things and the dynamic particle evolution prediction of the land organisms.

2. The land degradation status assessment method according to claim 1, characterized in that: Remote sensing images of the target land are collected by multi-source remote sensing equipment, and the remote sensing images include multispectral images, thermal infrared images, lidar point cloud data, normalized difference vegetation index NDVI and Sentinel-1 SAR dual-polarization data. The multispectral images include more than 11 spectral bands, and the spectral bands include 3 near-infrared narrowband channels dedicated to chlorophyll fluorescence detection.

3. The land degradation status assessment method according to claim 2, characterized in that: Performing geometric correction, radiation correction and spatiotemporal alignment operations on the remote sensing image, and extracting a first remote sensing spatial feature using a deformable convolution model, wherein the first remote sensing spatial feature includes a spectral feature, a texture feature and a structural feature; Performing cross-modal feature alignment on the first remote sensing spatial features through a transfer learning pre-training model to obtain a second remote sensing spatial feature that is aligned in time and space; ResNet is used to extract low-level features of the second remote sensing spatial features, and the low-level features are secondary mined into global dependencies and high-level features through Transformer. The global dependencies and high-level features are classified through a random forest model to obtain a classification of land biological cover types. The land biological cover type classification is plotted into a particle distribution structure diagram through statistical software, and different types of organisms are represented on the same land biological distribution map through different colors and shapes.

4. The land degradation status assessment method according to claim 3, characterized in that: Based on the land biological distribution map, a spatiotemporal coupled dynamic particle evolution model is constructed, and the number or area loss rate of the current land biological community, meteorological data and soil moisture time series data are collected using big data. The meteorological data includes temperature, precipitation and wind speed. Each biological community is mapped into a particle unit with adaptive quality parameters. The meteorological data is used to obtain abnormal values ​​through random forests, and the abnormal values ​​are compared with time to obtain an abnormal index. A spatiotemporal feature matrix is ​​constructed based on the land biological distribution map, wherein the columns of the spatiotemporal feature matrix represent time series and the rows represent biological types. The unit feature matrix of the spatiotemporal feature matrix is ​​solved by matrix basic operations, and the node data corresponding to the unit feature matrix is ​​standardized to obtain a solution space probability matrix of the spatiotemporal feature matrix. The solution space probability matrix and the second remote sensing spatial feature are weightedly merged by sliding window in the column direction to obtain a spatiotemporal feature probability distribution matrix. The spatiotemporal feature probability distribution matrix is ​​aligned with the time resolution of multi-source data by sliding window method to generate a standardized spatiotemporal data set.

5. The land degradation status assessment method according to claim 4, characterized in that: Each biome in the land biomass distribution map is mapped into a dynamic particle unit carrying gene entropy value, energy metabolism rate and environmental response function, where the gene entropy value is obtained by calculating the species genetic diversity index, and the environmental response function is obtained by integrating the multi-dimensional characteristics of the current land biome number or area loss rate, meteorological data and soil moisture time series data; The gene entropy value, energy metabolism rate and environmental response function are used as particle parameters, the variance of each particle parameter of the dynamic particle unit corresponding to each biological community is calculated, and the F statistic of each particle parameter is calculated based on the variance.

6. The land degradation status assessment method according to claim 5, characterized in that: The F statistics of each particle parameter corresponding to each dynamic particle unit and the standardized spatiotemporal data set are weightedly fused in spatiotemporal correspondence and input into the LSTM-Transformer hybrid neural network, where the LSTM layer is used to process meteorological data and soil moisture time series data to extract long-range dependency features, and the Transformer multi-head attention mechanism is used to fuse spatial distribution features through the multi-head attention mechanism to capture the spatial correlation of cross-regional biological migration, and use residual connections to bridge the output data of the macro or micro model to generate the particle group evolution trajectory corresponding to the dynamic particle unit in the future time window; The probability cloud map of the particle swarm evolution trajectory in the future time window is output, and the prediction reliability is double-verified by using Brier score and KL divergence. When the prediction value is lower than 85%, the online update of the model based on transfer learning is triggered.

7. The land degradation status assessment method according to claim 6, characterized in that: The step S3 comprises: The value indicators of the historical value of the abiotic value of the land include the monetary value created on the same piece of land, the ecological environment status and the stability of the ecosystem and the protection area of ​​the specific biological environment; Establish a non-biological value quantification model, obtain the historical economic operation data of the target land through the blockchain distributed ledger, simultaneously obtain the satellite remote sensing ecological index and ecosystem service value equivalent database, adopt a multi-objective optimization algorithm empowered by the attention mechanism, and dynamically calculate the multi-dimensional value indicator system.

8. The land degradation status assessment method according to claim 7, characterized in that: The multi-dimensional value indicator system includes economic value indicators, ecological stability indicators and biological protection intensity indicators. The economic value indicators include GDP output per unit area, land transfer transaction price and agricultural product market value. The ecological stability indicators include biodiversity index, soil and water conservation coefficient and carbon sink capacity. The biological protection intensity indicators include the coverage rate of endangered species habitats, the proportion of nature reserves and the area of ​​ecological red line areas. The weight distribution adopts the improved AdaBoost integrated learning framework, uses the SMOTE-Tomek joint sampling algorithm to deal with the category imbalance problem of the multi-dimensional value indicator system data, and extracts the principal component features with a cumulative contribution rate ≥ 85% through principal component analysis PCA; Integrating a cost-sensitive learning mechanism into the improved AdaBoost ensemble learning framework, defining a misclassification cost matrix according to the improved AdaBoost ensemble learning framework incorporating the cost-sensitive learning mechanism, including constructing a multi-head cross-attention mechanism module and using the improved AdaBoost ensemble learning framework for weight allocation; The modules for building a multi-head cross attention mechanism include: The nonlinear correlation between economic value indicators and ecological stability indicators is calculated through the graph neural network GNN, and the dynamic changes of time series data are captured through the gated temporal attention unit GTAU; The weight allocation using the improved AdaBoost ensemble learning framework includes: AdaBoost ensemble learning framework is used to train multiple weak classifiers, and all outputs of the weak classifiers are weighted and summed into a strong classifier. When the strong classifier is trained iteratively, the weight is adjusted according to the error rate of the strong classifier. The adjustment logic includes: training the next strong classifier, when the output of the next strong classifier focuses on the data point that was misclassified by the previous strong classifier, the current weight is output as the final weight distribution, and the weighted economic value index and ecological stability index are obtained; The empowered economic value index and ecological stability index are input into the blockchain smart contract, and the inter-period discount calculation is performed in combination with the time value factor. The time value factor includes the discount rate and the inflation rate. The inter-period discount mathematical expression is: ； in, is the discounted value at time t, is the value at the current moment, is the discount rate, For time.

9. The land degradation status assessment method according to claim 8, characterized in that: The step S4 comprises: The particle swarm evolution trajectory and the multi-dimensional value indicator system are used as sub-models for local training through differential privacy protection technology. The central server aggregates the degradation features of each region through an adaptive knowledge distillation algorithm to build a degradation assessment model including: The modified universal soil loss equation is used as the physical loss function, and its mathematical expression is: A = R × K × LS × C × P; Among them, A is the average annual soil loss, R is the rainfall erosivity factor, K is the soil erodibility factor, LS is the topographic factor, C is the vegetation cover factor, and P is the soil and water conservation measures factor; The Neural Radiation Field (NeRF) technology is used to model the land degradation process in a spatiotemporal continuous manner, and a continuous spatiotemporal remote sensing land degradation model is obtained. A convolutional neural network (CNN) was used to extract features from the continuous spatiotemporal remote sensing land degradation model, and a U-Net architecture containing 64 convolution kernels was constructed to obtain spatial probability predictions of degradation hotspot areas, and output risk levels. The risk levels included a first risk level, a second risk level, and a third risk level. The first risk level included a degradation probability value of the spatial probability prediction of less than 0.2, the second risk level included a degradation probability value of the spatial probability prediction of between 0.2 and 0.5, and the third risk level included a degradation probability value of the spatial probability prediction of greater than 0.5: The continuous spatiotemporal remote sensing land degradation model was deployed on the Google Earth Engine platform. Multi-temporal Landsat and Sentinel data stacks were used to extract the boundaries of objects through object-oriented segmentation technology, and the three-level classification of wetlands, woodlands and cultivated land was achieved in combination with decision tree classification rules.

10. A land degradation status assessment system, the system being used to implement a land degradation status assessment method, characterized in that: Including biological classification module, biological evolution module, value evolution module and degradation assessment module: The biological classification module is used to collect land images through multi-source remote sensing, and classify land organisms by extracting remote sensing spatial features at multiple levels; The biological evolution module is used to construct a spatiotemporal coupled dynamic particle evolution model based on the land biological distribution map, and to predict the dynamic particle evolution of land organisms; The value evolution module is used to establish a quantitative model for abiotic value, calculate the historical value of abiotic value of land, assign weights based on historical data and machine learning algorithms, and dynamically calculate a multi-dimensional value indicator system; The degradation assessment module is used to assess the land degradation status based on the historical value of the land non-biological class and the dynamic particle evolution prediction of the land organisms.

Images