GIS-based ecological environment space diagnosis method and system

Abstract

The invention discloses a GIS-based ecological environment space diagnosis method and system, and belongs to the technical field of geographic information systems. The method comprises the following steps: acquiring multi-source spatial data, and generating a standardized spatial data layer; generating hydrological factor data by using the spatial data layer; the remote sensing image data and the hydrological factor data are utilized, a CASA model is adopted to analyze the spatial coupling relation between hydrological factors and vegetation growth, and vegetation net primary productivity spatial distribution data are generated; the hydrological factor data and the vegetation net primary productivity spatial distribution data are utilized, fractal dimensions of ecological factors are calculated by adopting a fractal theory, and fractal dimension distribution data are generated; according to the fractal dimension distribution data, constructing a spatial ecological factor conduction chain by using a Markov model, and generating a spatial distribution diagram of a future ecological state; and generating an ecological environment diagnosis result according to the spatial distribution diagram of the future ecological state. According to the invention, the precision and prediction capability of ecological environment space analysis are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geographic information systems and watershed ecological management, and particularly relates to an ecological environment spatial diagnosis method and system based on GIS. BACKGROUND

[0002] Water conservancy and hydropower engineering construction has an adverse impact on the ecological environment of the watershed, and as human activities intensify, ecological environmental problems are becoming increasingly prominent. The complex interaction between the hydrological process, vegetation growth and soil properties of the watershed has an important influence on the stability of the ecological environment. Existing ecological environment diagnosis methods are mostly based on a single data source or simple models, and are difficult to comprehensively analyze the coupling relationship between multi-source spatial data, and have deficiencies in spatial heterogeneity analysis and future ecological state prediction. The ecological environment spatial diagnosis method based on the GIS platform can integrate multi-source data and perform spatial modeling, providing a scientific basis for ecological environment management. However, the existing technology still has limitations in precision and efficiency in terms of data preprocessing, spatial heterogeneity analysis and ecological factor transmission chain construction.

[0003] Therefore, there is an urgent need for a comprehensive, high-precision and future ecological state prediction diagnosis method. SUMMARY

[0004] The present application provides an ecological environment spatial diagnosis method based on GIS, which improves the precision and prediction ability of ecological environment spatial analysis and provides a scientific basis for ecological restoration and management.

[0005] The present application provides the following solutions: According to a first aspect, an ecological environment spatial diagnosis method based on GIS is provided, comprising the following steps: Obtaining multi-source spatial data, and preprocessing the multi-source spatial data through a GIS platform to generate standardized spatial data layers; Using the spatial data layers, simulating the hydrological process of the watershed using a soil and water evaluation tool model to generate hydrological factor data, the hydrological factor data including spatial distribution data of runoff, evapotranspiration and soil moisture; Using the remote sensing image data and the hydrological factor data, analyzing the spatial coupling relationship between the hydrological factor and the vegetation growth using a CASA model to generate vegetation net primary productivity spatial distribution data; Using the hydrological factor data and the vegetation net primary productivity spatial distribution data, calculating the fractal dimension of the ecological factor using fractal theory to generate fractal dimension distribution data, and generating a spatial heterogeneity distribution map according to the fractal dimension distribution data; According to the fractal dimension distribution data, a spatial ecological factor transmission chain containing hydrological, vegetation and soil factors is constructed by using a Markov model, and a spatial distribution map of a future ecological state is generated according to the spatial ecological factor transmission chain; According to the spatial distribution map of the future ecological state, an ecological environment diagnosis result is generated.

[0006] According to an implementable manner in the embodiments of the present application, the preprocessing includes: performing dimension noise reduction and feature enhancement on the multi-source spatial data by using principal component analysis.

[0007] According to an implementable manner in the embodiments of the present application, the multi-source spatial data includes remote sensing image data, meteorological data, soil attribute data and a digital elevation model.

[0008] According to an implementable manner in the embodiments of the present application, the fractal dimension distribution data is generated by using the hydrological factor data and the vegetation net primary productivity spatial distribution data to calculate the fractal dimension of the ecological factor by using the fractal theory, and the step of generating the spatial heterogeneity distribution map according to the fractal dimension distribution data includes: The hydrological factor data and the vegetation net primary productivity spatial distribution data are converted into a grid format to generate a spatial distribution matrix containing runoff, soil moisture and vegetation net primary productivity; a box dimension method is used to perform multi-scale grid covering on the spatial distribution matrix to calculate the number of covered grids at different grid scales; a log-log curve is fitted according to the grid scale and the number of covered grids to calculate a slope to determine the fractal dimension, thereby generating fractal dimension distribution data of the runoff, soil moisture and vegetation net primary productivity; and the fractal dimension distribution data is subjected to spatial interpolation on a GIS platform to generate a continuous spatial heterogeneity distribution map.

[0009] According to an implementable manner in the embodiments of the present application, the step of generating the spatial distribution map of the future ecological state according to the fractal dimension distribution data by using the Markov model to construct the spatial ecological factor transmission chain containing the hydrological, vegetation and soil factors includes: According to the fractal dimension distribution data, an ecological factor state space is divided; and based on the state space and historical data, a state transition probability matrix is calculated; A Markov chain is used to predict the dynamic evolution trend of the ecological factor based on the state transition probability matrix, thereby generating the spatial distribution map of the future ecological state.

[0010] According to an implementable manner in the embodiments of the present application, the step of dividing the ecological factor state space according to the fractal dimension distribution data includes: The fractal dimension distribution data is subjected to statistical analysis to calculate statistical distribution characteristics of the fractal dimension, including mean value and standard deviation. Based on the statistical distribution characteristics, a fractal dimension threshold is set, and the fractal dimension distribution data is divided into multiple discrete intervals, each interval corresponding to an ecological factor state; Using spatial clustering analysis, the fractal dimension distribution data is divided into regions, generating state regions with spatial continuity; According to the discrete intervals and the spatial clustering results, each grid cell is assigned a discrete state of a hydrological, vegetation, or soil factor, generating an ecological factor state space.

[0011] According to an implementable manner in the embodiments of the present application, the calculation of the state transition probability matrix based on the state space and historical data includes: According to the ecological factor state space and historical data, the transition frequency between states is counted, and an initial state transition probability matrix is generated; For each row of the initial state transition probability matrix, the transition uncertainty from the current state to the next state is calculated, and the uncertainty is obtained by summing the product of each transition probability and the negative value of the logarithm of each transition probability; According to the occurrence frequency of each state in the state space in the historical data, a weighted average of all state transition uncertainties is calculated, and the transition uncertainty of the entire system is obtained; According to the transition uncertainty, state transition paths below a preset threshold are screened out, and state transitions with low probability or high uncertainty are removed; Based on the screened state transition paths, an optimized state transition probability matrix is reconstructed.

[0012] According to an implementable manner in the embodiments of the present application, the generation of an ecological environment diagnosis result according to the spatial distribution map of the future ecological state includes: Based on the spatial distribution map of the future ecological state, spatial analysis is performed to identify regions with abnormal ecological states; The hydrological factor data, the net primary productivity of vegetation data, and the future ecological state data of the abnormal regions are weighted and scored to generate an ecological health index, and regions with an ecological health index below a preset threshold are determined as high-risk regions; The high-risk regions are assigned geographical coordinates or grid ranges, and a risk distribution map is generated; According to the ecological factor state of the high-risk regions, targeted ecological restoration suggestions are generated, including vegetation restoration or soil and water conservation measures; The risk distribution map and ecological restoration suggestions are integrated on a GIS platform to generate an ecological environment diagnosis report, and the visualization of the risk distribution is realized on a WebGIS interface.

[0013] According to a second aspect, a GIS-based ecological environment space diagnosis system is provided, the system comprising: a data acquisition and preprocessing module configured to acquire multi-source spatial data and preprocess the multi-source spatial data through a GIS platform to generate standardized spatial data layers, the multi-source spatial data comprising remote sensing image data, meteorological data, soil property data and a digital elevation model; a hydrological model module configured to simulate a watershed hydrological process using a soil and water assessment tool model by utilizing the spatial data layers to generate hydrological factor data, the hydrological factor data comprising spatial distribution data of runoff, evapotranspiration and soil moisture; a vegetation growth model module configured to analyze a spatial coupling relationship between hydrological factors and vegetation growth using a CASA model by utilizing the remote sensing image data and the hydrological factor data to generate vegetation net primary productivity spatial distribution data; a fractal analysis module configured to calculate fractal dimensions of ecological factors using a fractal theory by utilizing the hydrological factor data and the vegetation net primary productivity spatial distribution data to generate fractal dimension distribution data and generate a spatial heterogeneity distribution map according to the fractal dimension distribution data; a Markov model module configured to construct a spatial ecological factor conduction chain comprising hydrological, vegetation and soil factors using a Markov model according to the fractal dimension distribution data and generate a spatial distribution map of a future ecological state according to the spatial ecological factor conduction chain; a diagnosis result generation module configured to generate an ecological environment diagnosis result according to the spatial distribution map of the future ecological state.

[0014] According to a third aspect, a computer readable storage medium having a computer program stored thereon is provided, the program being executed by a processor to implement the steps of the method of any one of the above first aspect.

[0015] According to a fourth aspect, an electronic device is provided, comprising: one or more processors; and a memory associated with the one or more processors, the memory being configured to store program instructions, the program instructions being executed by the one or more processors to perform the steps of the method of any one of the above first aspect.

[0016] Compared with the prior art, the present application has the following advantages and beneficial effects: The application integrates multi-source spatial data, uses a Soil and Water Assessment Tool (SWAT) model, a Carnegie-Ames-Stanford Approach (CASA) model, a fractal theory and a Markov model, constructs a spatial ecological factor transmission chain of hydrology, vegetation and soil factors, generates a spatial distribution map of a future ecological state, and further generates an ecological environment diagnosis result. The application can improve the accuracy and prediction ability of ecological environment spatial analysis, and provides a scientific basis for ecological restoration and management.

[0017] Of course, implementing any product of the present application does not necessarily require achieving all the advantages described above at the same time. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A system architecture diagram suitable for embodiments of the present application; Figure 2 A flowchart of a GIS-based ecological environment spatial diagnosis method provided by embodiments of the present application; Figure 3 A structural block diagram of a GIS-based ecological environment spatial diagnosis system provided by embodiments of the present application; Figure 4 A schematic block diagram of an electronic device provided by embodiments of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art belong to the scope of protection of the present application.

[0020] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "an" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0021] It should be understood that the term "and / or" used herein is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects.

[0022] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to determining" or "in response to detecting." Similarly, the phrase "if it is determined" or "if [a stated condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon detecting [the stated condition or event]" or "in response to detecting [the stated condition or event]."

[0023] Currently, there are some spatial diagnosis techniques, for example, using the InVEST model (Integrated Valuation of Ecosystem Services and Tradeoffs) for spatial diagnosis, but the InVEST model is limited in terms of spatial heterogeneity analysis and future ecological state prediction, and the coupling relationship between hydrological factors and vegetation growth is not analyzed in depth.

[0024] Therefore, the present application provides a new idea. In order to facilitate the understanding of the present application, first, the system architecture based on the present application is described. Figure 1 An exemplary system architecture to which embodiments of the present application can be applied is shown, as shown in Figure 1 The system architecture can include a user device and a GIS-based ecological environment spatial diagnosis system located at the server end.

[0025] The user can input multi-source spatial data through the user device, and the user device sends it to the spatial diagnosis system at the server end. The spatial diagnosis system can use the method provided in the embodiments of the present application to obtain the ecological environment diagnosis result. The server end can send the ecological environment diagnosis result to the user terminal.

[0026] The user device can include, but is not limited to, such as: smart mobile terminal, smart home device, wearable device, PC (Personal Computer), etc. The smart mobile device can include, such as: mobile phone, tablet computer, notebook computer, PDA (Personal Digital Assistant), Internet car, etc. The smart home device can include smart TV, smart refrigerator, etc. The wearable device can include, such as: smart watch, smart glasses, virtual reality device, augmented reality device, mixed reality device, etc.

[0027] The GIS-based ecological environment spatial diagnosis system can be set as an independent server, a server group, or a cloud server. The cloud server, also known as a cloud computing server or a cloud host, is a host product in the cloud computing service system, which solves the defects of large management difficulty and weak service scalability in traditional physical hosts and virtual private server (VPS, Virtual Private Server) services. In addition to the architecture shown in Figure 1 In addition to the architecture shown in

[0028] It should be understood that Figure 1 The user equipment and the GIS-based ecological environment spatial diagnosis system in

[0029] Figure 2 The GIS-based ecological environment spatial diagnosis method flowchart provided by the embodiments of the present application is shown in Figure 2 The method can include the following steps: Step 201: Obtain multi-source spatial data, and preprocess the multi-source spatial data through a GIS platform to generate standardized spatial data layers, wherein the multi-source spatial data includes remote sensing image data, meteorological data, soil property data, and a digital elevation model.

[0030] Step 202: Simulate a watershed hydrological process by using a soil and water evaluation tool model with the spatial data layers to generate hydrological factor data, wherein the hydrological factor data includes spatial distribution data of runoff, evapotranspiration, and soil moisture.

[0031] Step 203: Analyze the spatial coupling relationship between hydrological factors and vegetation growth by using a CASA model with the remote sensing image data and the hydrological factor data to generate spatial distribution data of vegetation net primary productivity.

[0032] Step 204: Calculate the fractal dimension of ecological factors by using fractal theory with the hydrological factor data and the spatial distribution data of vegetation net primary productivity to generate fractal dimension distribution data, and generate a spatial heterogeneity distribution map according to the fractal dimension distribution data.

[0033] Step 205: Construct a spatial ecological factor conduction chain containing hydrological, vegetation, and soil factors by using a Markov model according to the fractal dimension distribution data, and generate a spatial distribution map of future ecological states according to the spatial ecological factor conduction chain.

[0034] Step 206: Generate an ecological environment diagnosis result according to the spatial distribution map of future ecological states.

[0035] As can be seen from the above flow, the application generates a spatial distribution map of the future ecological state by integrating multi-source spatial data, using the soil and water evaluation tool model, the CASA model, the fractal theory and the Markov model, constructing a spatial ecological factor transmission chain of hydrology, vegetation and soil factors, and further generating an ecological environment diagnosis result. The application can improve the accuracy and prediction ability of ecological environment spatial analysis, and provide a scientific basis for ecological restoration and management.

[0036] Firstly, the above step 201, i.e., "obtaining multi-source spatial data, and preprocessing the multi-source spatial data through a GIS platform to generate standardized spatial data layers, the multi-source spatial data including remote sensing image data, meteorological data, soil property data and a digital elevation model", is described in detail in combination with an embodiment.

[0037] Firstly, multi-source spatial data is obtained. Multi-source spatial data refers to a data set with spatial properties derived from different data collection methods or devices. These data cover key information required for ecological environment analysis, specifically including remote sensing image data, meteorological data, soil property data and a digital elevation model (DEM). The sources and characteristics of these data are different. For example, remote sensing image data is usually obtained through satellites or drones and contains information such as surface vegetation coverage and land use types; meteorological data includes time series data such as rainfall, temperature and humidity, reflecting regional climate characteristics; soil property data describes soil types, texture and organic matter content, affecting hydrological processes and vegetation growth; and a digital elevation model provides elevation and slope information of the terrain for simulating water flow paths and surface runoff. By integrating these multi-source data, the ecological environment characteristics of the study area can be fully described, providing a multi-dimensional perspective for subsequent analysis.

[0038] Secondly, preprocessing multi-source spatial data through a GIS platform is a key link to ensure data consistency and usability. Since the formats, resolutions, coordinate systems and time scales of multi-source data are often different, direct use may lead to analysis errors. Therefore, the preprocessing process aims to convert these heterogeneous data into spatial data layers in a unified format. Specific operations include data cleaning, format conversion, coordinate system registration and spatial resolution unification, etc. For example, remote sensing image data may need to be radiometrically and geometrically corrected to eliminate sensor or atmospheric interference; meteorological data may need to be interpolated to generate continuous spatial distribution; soil property data and DEM need to be projected onto the same geographic coordinate system. Through these preprocessing steps, the data is consistent in space and attributes, ensuring the accuracy and reliability of subsequent model input.

[0039] Finally, generating standardized spatial data layers is to organize the pre-processed data into layer forms that can be directly used on GIS platforms. Spatial data layers refer to geographic information datasets stored in raster or vector forms with spatial references, each layer represents a specific ecological environmental factor, such as vegetation cover, soil moisture or terrain slope. These layers are not only the carriers of data storage, but also the basis of subsequent analysis. Through the overlay, query and visualization functions of GIS platforms, standardized spatial data layers can support complex hydrological simulation, vegetation productivity analysis and spatial heterogeneity assessment. For example, remote sensing image data can generate vegetation index layers, DEM can generate slope layers, which provide necessary data support for the input of SWAT and CASA models.

[0040] As a real-time approach, preprocessing includes dimensionality reduction and feature enhancement of the multi-source spatial data using principal component analysis.

[0041] Principal component analysis is a commonly used statistical method for processing high-dimensional and complex datasets. In this application, multi-source spatial data usually has high dimensionality and multivariate characteristics. For example, remote sensing image data may contain multiple spectral bands, meteorological data involves rainfall, temperature, humidity and other variables, and soil property data may include organic matter content, soil texture and other indicators. There is often correlation between these variables, and direct use may result in data redundancy or high computational complexity. Principal component analysis converts the original high-dimensional data into a set of new orthogonal variables, i.e. principal components, through linear transformation, which retains most of the variance information of the data, thereby achieving dimensionality reduction and reducing data processing complexity.

[0042] Dimensionality reduction is one of the main functions of principal component analysis. Multi-source spatial data has high dimensionality and may contain a large amount of redundant information or noise, such as the signal of some bands in remote sensing images may be disturbed by clouds or atmosphere, and some properties in soil data may be highly correlated. Through principal component analysis, the principal components that contribute most to the data can be identified, usually the first few principal components can explain most of the variance of the data, and the principal components with smaller contribution can be removed, thereby reducing the dimensionality of the data. For example, in remote sensing image processing, principal component analysis can compress multiple spectral bands into a few principal components, retaining key vegetation or surface information while removing noise interference. This noise reduction process not only reduces the computational burden of subsequent models such as SWAT or CASA, but also improves the robustness and stability of data analysis.

[0043] Feature enhancement is another important role of principal component analysis. By transforming the original data into principal components, the key features of the data are amplified, which helps to highlight important information in ecological environment analysis. For example, when analyzing the relationship between vegetation growth and hydrological factors, principal component analysis can combine key variables such as vegetation index in remote sensing images and rainfall in meteorological data into new principal components, enhancing the spatial expression ability of these variables on ecological processes. Feature enhancement can also improve the interpretability of data, enabling subsequent models to more accurately capture the spatial coupling relationship between hydrological, vegetation and soil factors. For example, through the generation of feature enhancement layers by principal component analysis, the spatial distribution of vegetation cover and soil moisture within the watershed can be more clearly reflected, providing more reliable input for spatial heterogeneity analysis.

[0044] The implementation of principal component analysis for dimension noise reduction and feature enhancement in the GIS platform makes full use of the spatial analysis capabilities of GIS. The GIS platform can store and visualize the results of principal component analysis in the form of spatial data layers, such as generating spatial distribution maps reflecting principal components. These layers not only retain the geographical reference information of the data, but also seamlessly connect with subsequent SWAT models, CASA models and fractal theory analysis. For example, the noise-reduced remote sensing image layer can be directly used for CASA model calculation of vegetation net primary productivity, and the feature-enhanced hydrological factor layer provides high-quality input for SWAT model hydrological simulation. This integrated processing method based on GIS ensures the continuity and consistency of data from preprocessing to analysis.

[0045] The following describes the step 202, i.e., "using spatial data layers, using the SWAT model to simulate the hydrological process of the watershed, and generating hydrological factor data, including the spatial distribution data of runoff, evapotranspiration and soil moisture", in detail in combination with an embodiment.

[0046] The spatial data layers provide comprehensive spatial data support for the input of the SWAT model, ensuring that the simulation results accurately reflect the hydrological characteristics of the watershed. The SWAT model is a physical model applied to the simulation of watershed hydrological processes, which can consider factors such as climate, soil, topography and land use to simulate various aspects of water cycle. The SWAT model divides the watershed into multiple hydrological response units and integrates information from spatial data layers into these units to calculate key parameters of hydrological processes.

[0047] In this application, the SWAT model uses information such as rainfall, soil permeability and terrain slope in spatial data layers to simulate the hydrological cycle in the watershed, including rainfall distribution, surface runoff, groundwater flow and evapotranspiration. This physical mechanism-based simulation can accurately capture the spatial and temporal variations of watershed hydrological processes, providing a reliable data foundation for ecological environment analysis.

[0048] The output of the SWAT model is the spatial distribution of hydrological factor data, including runoff, evapotranspiration, and soil moisture. These factors are key indicators for ecological environment diagnosis, reflecting the allocation and utilization of water resources within the watershed. Runoff data describes the distribution and intensity of surface water flow, revealing regional differences in flood risk or water supply; evapotranspiration data reflect the loss of surface water through plant transpiration and soil evaporation, which is closely related to vegetation growth; soil moisture data represent the distribution of available water in the soil, directly affecting vegetation growth and soil stability. These hydrological factors are generated in the form of spatial layers, retaining geographic coordinate information and enabling visualization and further analysis on the GIS platform.

[0049] In addition, the generated hydrological factor data is presented in the form of spatial distribution maps on the GIS platform, with high spatial resolution and geographic reference. For example, the spatial distribution map of runoff can show which areas in the watershed are prone to surface runoff accumulation, identifying potential flood risk areas; the soil moisture distribution map can reveal the distribution of dry or wet areas, providing a basis for vegetation restoration or soil and water conservation measures. These spatial distribution data not only provide input for subsequent CASA model analysis, but also lay the foundation for ecological factor analysis using fractal theory and Markov models. The powerful spatial analysis capabilities of the GIS platform enable seamless integration of these hydrological factor data with other ecological factor data, supporting complex spatial coupling analysis.

[0050] The following describes the step 203, i.e., "using the remote sensing image data and the hydrological factor data, using the CASA model to analyze the spatial coupling relationship between hydrological factors and vegetation growth, and generating vegetation net primary productivity spatial distribution data", in detail with reference to the embodiments.

[0051] The CASA model is an ecological productivity model based on remote sensing data, used to estimate the net primary productivity (NPP) of vegetation. Net primary productivity is the net amount of carbon fixed by plants through photosynthesis, and is a key indicator for measuring vegetation growth and ecosystem productivity. The CASA model combines vegetation index in remote sensing image data and hydrological factor data to calculate light use efficiency, photosynthetically active radiation absorbed by vegetation, and water and temperature limiting factors, thereby estimating the net primary productivity of vegetation at different spatial locations. In this application, the CASA model uses NDVI in remote sensing image data to calculate the greenness of vegetation, and combines soil moisture and evapotranspiration data in hydrological factor data to analyze the limiting effect of hydrological conditions on vegetation growth, thereby generating spatial distribution data reflecting vegetation productivity.

[0052] Analyzing the spatial coupling between hydrological factors and vegetation growth is the core application of the CASA model in this method. Spatial coupling refers to the interaction and dependence of hydrological factors such as soil moisture, runoff, and evapotranspiration on vegetation growth in space. For example, in areas with sufficient soil moisture, the net primary productivity of vegetation is usually high, while in arid or areas with excessive runoff, vegetation growth may be limited. The CASA model quantifies these relationships through mathematical modeling, linking the spatial distribution of hydrological factors to the net primary productivity of vegetation, generating spatial distribution data. This spatial coupling analysis can reveal the ecological and environmental characteristics of different regions in the watershed, such as identifying areas of vegetation degradation caused by water resource shortages, providing a basis for subsequent ecological restoration.

[0053] The spatial distribution of vegetation net primary productivity data is an important output result in the GIS-based ecological environment spatial diagnosis method, derived from the analysis of remote sensing image data and hydrological factor data by the CASA model. This data reflects the spatial distribution characteristics of the amount of carbon fixed by vegetation through photosynthesis, and is a core indicator for assessing the productivity and health of the ecosystem. The content of the spatial distribution of vegetation net primary productivity data mainly includes the net primary productivity (NPP) value of each spatial unit and its geographic location information. Specifically, this data records the net primary productivity value of each grid cell in the watershed, usually in units of grams of carbon per square meter per year. These values reflect the photosynthetic efficiency and biomass accumulation capacity of vegetation in a particular region. For example, areas with high NPP values may correspond to dense vegetation such as wetlands or forests, indicating that sufficient water and nutrients support vigorous vegetation growth; while areas with low NPP values may correspond to arid regions or degraded land, indicating low ecosystem productivity. In addition, the data may also contain auxiliary information related to NPP, such as vegetation type, soil moisture limiting factors, or the distribution of photosynthetically active radiation, which helps to explain the reasons for the spatial variation of NPP.

[0054] The vegetation net primary productivity spatial distribution data is stored in a grid format supported by a GIS platform, which is a spatial data layer based on a geographic coordinate system. The grid format divides the study area into regular grids, and each grid cell, i.e., grid, corresponds to an NPP value and is associated with a specific geographic coordinate. Common grid data formats include GeoTIFF, NetCDF, or ESRI Grid, etc. These formats can efficiently store high-resolution spatial data and are compatible with GIS software such as ArcGIS or QGIS. The size of each grid cell, i.e., spatial resolution, is determined by the precision of the input data. For example, a 30-meter resolution remote sensing image may generate 30-meter x 30-meter grid cells. The data layer retains geographic reference information such as the projection coordinate system and spatial range, ensuring that the NPP values can be overlaid with other spatial data such as hydrological factor layers for superposition analysis. In addition, the data may be accompanied by metadata, recording information such as generation time, data source, model parameters, etc., to support data tracing and verification.

[0055] Further, the spatial characteristics of vegetation net primary productivity spatial distribution data enable powerful visualization and analysis potential on the GIS platform. Through GIS software, these data can be presented as continuous distribution maps, using color gradients to represent NPP values, such as green for high NPP areas and yellow or red for low NPP areas. This visualization method can intuitively show the spatial heterogeneity of vegetation productivity within the watershed, such as identifying high productivity ecological protection areas or low productivity degradation areas. In addition, the data support spatial statistical analysis, such as calculating the mean, standard deviation, or spatial autocorrelation of NPP, to further quantify the distribution of vegetation productivity. These analysis results provide key inputs for subsequent fractal dimension calculation, ecological factor conduction chain construction, and ecological environment diagnosis.

[0056] The following describes the step 204, i.e., "using hydrological factor data and vegetation net primary productivity spatial distribution data, calculating the fractal dimension of ecological factors using fractal theory, generating fractal dimension distribution data, and generating a spatial heterogeneity distribution map based on the fractal dimension distribution data", in detail with examples.

[0057] Fractal theory is a mathematical approach to describe and quantify the spatial structure and heterogeneity of complex systems. In ecological and environmental research, the spatial distribution of ecological factors often exhibits non-uniform and self-similar characteristics. For example, the distribution of runoff or vegetation productivity at different scales may exhibit fractal characteristics. Fractal dimension is a core indicator of fractal theory, used to measure the complexity and heterogeneity of ecological factors in space. Higher fractal dimension usually indicates more complex and irregular distribution, while lower fractal dimension indicates more uniform distribution. In this application, fractal theory is applied to the spatial distribution of hydrological factors and vegetation net primary productivity data to calculate their fractal dimensions and reveal the spatial heterogeneity characteristics of ecological factors in the watershed.

[0058] The core operation of this step is to calculate the fractal dimension of ecological factors and generate fractal dimension distribution maps. The specific process includes converting hydrological factor data and vegetation net primary productivity data into raster format to form a spatial distribution matrix; then using the box dimension method, the number of covered grids at different grid scales is calculated through multi-scale grid coverage; according to the grid scale and the number of coverage, the log-log curve is fitted, and the slope is calculated to determine the fractal dimension. For example, for runoff data, the fractal dimension can reflect the spatial complexity of water flow distribution, such as the degree of river network bending or the heterogeneity of runoff concentration. Finally, fractal dimension distribution maps are generated for runoff, soil moisture and vegetation net primary productivity, respectively. These layers are stored in raster format, with each raster cell corresponding to a fractal dimension value, reflecting the complexity of ecological factors in that area.

[0059] In addition, generating spatial heterogeneity distribution maps from fractal dimension distribution maps is a further processing and optimization step. Fractal dimension distribution maps provide information on the complexity of ecological factors in space, but they may exhibit discrete or discontinuous characteristics. In order to generate continuous spatial heterogeneity distribution maps, this application performs spatial interpolation on fractal dimension distribution maps on the GIS platform. Spatial interpolation estimates the fractal dimension values of unobserved areas through mathematical methods such as Kriging interpolation or inverse distance weighting, thus generating smooth distribution maps. This spatial heterogeneity distribution map can visually display the spatial variation of ecological factors in the watershed, for example, high heterogeneity areas may correspond to complex terrain or diverse vegetation types, while low heterogeneity areas may represent a more homogeneous or degraded ecosystem.

[0060] Finally, the generated spatial heterogeneity distribution maps were presented in a visualized form on a GIS platform, providing important input for subsequent analysis. These layers not only quantified the spatial complexity of ecological factors but also provided data support for constructing ecological factor transmission chains in Markov models and predicting future ecological states. For example, spatial heterogeneity distribution maps can help identify vulnerable areas of the ecosystem; regions with high fractal dimensions may indicate complex distributions of ecological factors and susceptibility to external disturbances. This information provides a scientific basis for the formulation of ecological environment diagnosis and restoration strategies, demonstrating the unique advantages of fractal theory in capturing the spatial characteristics of complex ecosystems.

[0061] Specifically, the input data is a two-dimensional raster matrix M with a size of N×N, where each element M(i,j) represents the ecological factor value at the coordinate, such as the NPP value or runoff value.

[0062] The raster matrix is ​​divided into grids of different scales, with grid side lengths of... The value is usually taken as =2 k (e.g., 2, 4, 8, 16 pixels, etc.) to cover the entire matrix. For each scale Count the number of grids N covering non-empty data. Non-empty grids refer to grids that contain valid ecological factor values. For example, for NPP data, non-empty grids might refer to areas where the NPP value is greater than 0.

[0063] The core formula of the box dimension method is based on the logarithmic relationship between the grid scale and the number of covering grids. The fractal dimension is defined as:

[0064] In actual calculations, It cannot approach 0, therefore it is achieved through multiple scales. i (e.g., calculations under 2, 4, 8, 16) N ( i ), to estimate by fitting a log-log curve. D .

[0065] The specific formula is as follows:

[0066] Where C is a constant, D is the fractal dimension, and logN( is fitted by linear regression) i ) for log(1 / i The slope is obtained from the slope.

[0067] To generate the fractal dimension distribution map, the local fractal dimension needs to be calculated for each grid cell or sub-region. A sliding window (e.g., an m x m sub-matrix) centered on the target grid cell is selected, and the box-counting method is applied within the window. For each sliding window, the above steps are repeated to calculate the fractal dimension D local within the window and assign the value to the grid cell at the center of the window.

[0068]

[0069] Finally, the local fractal dimension D local of each grid cell is stored as a new raster layer, forming the fractal dimension distribution map. On the GIS platform, the fractal dimension distribution map is smoothed using spatial interpolation methods such as Kriging interpolation or inverse distance weighting, generating a continuous spatial heterogeneity distribution map.

[0070] The above step 205, i.e., "constructing a spatial ecological factor transmission chain containing hydrological, vegetation, and soil factors using a Markov model based on the fractal dimension distribution data, and generating a spatial distribution map of future ecological states based on the spatial ecological factor transmission chain," is described in detail below with reference to an embodiment.

[0071] A Markov model is a stochastic process model based on state transition probabilities, suitable for simulating the dynamic process of system evolution over time. In this application, the Markov model is used to construct a spatial ecological factor transmission chain, i.e., to describe the dynamic interaction of hydrological, vegetation, and soil factors in space and time. The spatial ecological factor transmission chain refers to how these factors influence each other through state transitions, for example, changes in soil moisture may affect vegetation growth, and changes in vegetation cover may in turn affect runoff distribution. The Markov model simulates the spatial distribution changes of these factors at future time points by defining the state space and transition probabilities of ecological factors, thereby predicting the ecological state of the watershed.

[0072] As an implementable way, the present application divides the ecological factor state space according to the fractal dimension distribution map; calculates the state transition probability matrix based on the state space and historical data; uses a Markov chain to predict the dynamic evolution trend of ecological factors based on the state transition probability matrix, and generates a spatial distribution map of future ecological states.

[0073] Specifically, the first step of constructing a spatial ecological factor transmission chain is to divide the ecological factor state space according to the fractal dimension distribution map. The division rules of the ecological factor state space can be pre-set or adjusted in real time according to the changes in data.

[0074] Preferably, according to the fractal dimension distribution map, the division of the ecological factor state space comprises: performing statistical analysis on the fractal dimension distribution map, calculating the statistical distribution characteristics of the fractal dimension, including the mean and standard deviation; based on the statistical distribution characteristics, setting a fractal dimension threshold, dividing the fractal dimension distribution map into multiple discrete intervals, each interval corresponding to an ecological factor state; using spatial clustering analysis, the region of the fractal dimension distribution map is divided to generate a state region with spatial continuity; according to the discrete interval and the spatial clustering result, each grid cell is assigned a discrete state of hydrological, vegetation or soil factors, and an ecological factor state space is generated.

[0075] Specifically, this involves statistical analysis of fractal dimension data, calculation of its mean and standard deviation, and setting a threshold to divide the data into multiple discrete state intervals. For example, the fractal dimension can be divided into high, medium and low states, corresponding to complex, transitional and uniform ecological factor distribution, respectively. Then, through spatial clustering analysis, the fractal dimensions of adjacent regions are classified into continuous state regions, ensuring the spatial continuity of the state space. Finally, each grid cell is assigned a discrete state, such as a high soil moisture state or a low vegetation productivity state, forming a state space containing hydrological, vegetation and soil factors.

[0076] Further, based on the state space and historical data, calculating the state transition probability matrix is the key to building the transmission chain. The state transition probability matrix describes the probability of ecological factors transitioning from the current state to the next state, such as the probability of transitioning from a high soil moisture state to a medium soil moisture state. The calculation process includes: calculating the transition frequency between states in historical data to form an initial transition probability matrix; then evaluating the transition uncertainty through information entropy and other methods, eliminating low-probability or high-uncertainty transition paths; finally, optimizing the matrix to ensure that it accurately reflects the dynamic evolution of ecological factors. This matrix not only captures the state changes of a single factor, but also models the interactions between hydrological, vegetation and soil factors through joint probabilities.

[0077] Subsequently, the Markov chain is used to predict the dynamic evolution trend of ecological factors based on the state transition probability matrix, generating a spatial distribution map of future ecological states. The Markov chain simulates the state distribution of ecological factors at future time points through iterative calculations. For example, assuming the current soil moisture state is high, based on the transition probability matrix, it can be predicted that it will transition to a medium or low state at the next time step. Apply this process to each grid cell to generate a future ecological state distribution map for the entire watershed. This map is stored in a grid format, with each cell representing the predicted ecological factor state, such as high vegetation productivity or low runoff area, preserving geographic reference information to support GIS platform analysis and visualization.

[0078] Preferably, calculating the state transition probability matrix based on the state space and historical data includes: statistically analyzing the transition frequencies between states according to the ecological factor state space and historical data to generate an initial state transition probability matrix; calculating the transition uncertainty from the current state to the next state for each row of the initial state transition probability matrix, wherein the uncertainty is obtained by summing the results after multiplying each transition probability by the negative of its logarithm; calculating the weighted average of all state transition uncertainties based on the occurrence frequency of each state in the state space in the historical data to obtain the transition uncertainty of the entire system; filtering state transition paths below a preset threshold based on the transition uncertainty, and eliminating state transitions with low probability or high uncertainty; and reconstructing the optimized state transition probability matrix based on the filtered state transition paths.

[0079] Specifically, by analyzing historical data, the number of transitions for each state between consecutive time steps is counted. For example, if a grid cell... t In a state of high soil moisture, over time t +1 represents a transition from high to medium soil moisture state, thus recording a shift from high to medium. Assume the state space contains... n There are several states, and the initial state transition probability matrix P is an n×n matrix, where each element represents the probability of transitioning from state to state . The calculation formula is as follows:

[0080] Where, N ij Let Σ be the number of transitions from state i to state j. n k=1 N ik Let be the total number of transitions to state i. Each row of this matrix sums to 1, ensuring probability normalization.

[0081] Secondly, the transition uncertainty is calculated for each row of the initial state transition probability matrix to assess the reliability and stability of the state transition. The transition uncertainty is calculated using the information entropy formula, reflecting the degree of disorder in the probability distribution from the current state to the next state. For the i-th row of matrix P, the transition uncertainty H... i Defined as:

[0082] Among them, P ij Let logP be the transition probability from state i to state j. ijFor its natural logarithm, the negative sign ensures that the entropy value is non-negative. If the transition probability distribution of a certain state is uniform, for example, the probability from state to all possible states is equal, then the entropy value is higher, indicating that the transition uncertainty is large; if a certain state mainly transitions to a specific state, then the entropy value is lower, indicating that the transition is more certain. For example, if the high soil moisture state has an 80% probability of remaining in the high state and a 20% probability of transitioning to the medium state, then its entropy value is lower, and the transition path is more stable. This process is calculated row by row to generate the transition uncertainty value of each state, which is used for subsequent screening.

[0083] Subsequently, according to the frequency of each state in the state space in the historical data, the weighted average value of the transition uncertainty of all states is calculated to obtain the transition uncertainty of the entire system. The frequency of a state reflects its proportion in the historical data, for example, a high vegetation productivity state may dominate in forest areas, and a low productivity state may be more common in desert areas. Assuming that the frequency of state i is, the calculation formula is:

[0084] where C i is the number of occurrences of state i in the historical data, and Σ n k=1 C k is the total number of occurrences of all states. The total transition uncertainty H total of the system is the weighted average of the uncertainty of each state:

[0085] This index quantifies the overall uncertainty of the state transition of the entire ecosystem. If H total is high, it means that the system state changes are complex, and the prediction is difficult; if it is low, it means that the state transition is more regular, and the prediction result is more reliable.

[0086] Further, according to the transition uncertainty, the state transition path with a lower preset threshold is screened out, and the transition with a low probability or high uncertainty is removed to optimize the state transition probability matrix. The preset threshold is usually determined according to the specific application scenario, for example, the probability threshold θ p is set to 0.05 and the uncertainty threshold θ h is set to 0.5. For each element P ij of the matrix P, if P ij < θ p , then the corresponding H i > θ h , it is considered that the transition path is unreliable, and its probability is set to 0, and the matrix is re-normalized:

[0087] where is an indicator function that takes the value 1 when the condition is satisfied and 0 otherwise. This screening process eliminates unstable or low-probability transition paths, such as the rare transition from a high runoff state directly to a low runoff state, thereby improving the predictive ability of the matrix.

[0088] Finally, based on the screened state transition paths, an optimized state transition probability matrix P' is reconstructed. This matrix retains high-probability and low-uncertainty transition paths, reflecting the stable dynamic relationship between ecological factor states. For example, the optimized matrix may show that the high soil moisture state is more likely to remain or transition to the medium state, but less likely to directly transition to the low state. The optimized matrix is used for subsequent Markov chain prediction to generate spatial distribution maps of future ecological states. The entire process is implemented on a GIS platform, combining the spatial properties of historical data to ensure that the transition probability matrix can reflect the spatial heterogeneity of ecological factors within the watershed.

[0089] The step 206, i.e., "generating ecological environment diagnosis results based on the spatial distribution map of future ecological states", will be described in detail below in conjunction with an embodiment.

[0090] This step is the final link of the entire method, aiming to comprehensively analyze the predicted ecological state, identify potential ecological risk areas, propose targeted restoration suggestions, and generate a visual diagnosis report, providing a scientific basis for ecological environment management and decision-making. Among them, generating ecological environment diagnosis results based on the spatial distribution map of future ecological states can be achieved through various methods, for example, a simple method is to set a threshold for ecological state, classify the spatial distribution map of future ecological states, directly generate a risk distribution map and propose diagnosis results; for another example, use the hot spot analysis function of the GIS platform to identify ecological abnormal areas based on the spatial distribution map of future ecological states to generate diagnosis results.

[0091] As an implementable way, generating ecological environment diagnosis results based on the spatial distribution map of future ecological states includes: performing spatial analysis based on the spatial distribution map of future ecological states to identify areas with abnormal ecological states; performing weighted scoring on the hydrological factor data, net primary productivity data of vegetation, and future ecological state data of the abnormal areas to generate an ecological health index, and areas with an ecological health index below a preset threshold are determined as high-risk areas; assigning geographic coordinates or grid ranges to the high-risk areas to generate a risk distribution map; generating targeted ecological restoration suggestions based on the ecological factor states of the high-risk areas, including vegetation restoration or soil and water conservation measures; integrating the risk distribution map and ecological restoration suggestions on the GIS platform to generate an ecological environment diagnosis report, and realizing the visual display of risk distribution on the WebGIS interface.

[0092] Specifically, the first step to generate the ecological environment diagnosis result is to conduct spatial analysis based on the spatial distribution map of future ecological status, identifying areas with abnormal ecological status. Spatial analysis can utilize the overlay, statistical, and clustering functions of the GIS platform to detect areas where ecological factor status deviates from the normal range. For example, if the predicted value of net primary productivity of vegetation in a certain area is significantly lower than the historical average, or the soil moisture status remains low, it may be marked as an abnormal area. The identification of abnormal areas may also combine multi-factor analysis, such as considering areas with increased runoff and decreased vegetation productivity, which may indicate the risk of soil erosion. The spatial query and hotspot analysis functions supported by the GIS platform can efficiently locate these abnormal areas and record them in the form of geographic coordinates or grid ranges, providing accurate spatial positioning for subsequent evaluation.

[0093] Subsequently, the hydrological factor data, net primary productivity of vegetation data, and future ecological status data of the abnormal areas are weighted scored to generate an ecological health index. This index comprehensively reflects the health status of the regional ecosystem and is the core quantitative indicator of the diagnosis result. The weighted scoring method assigns weights according to the ecological importance of each factor, for example, soil moisture may have a greater impact on vegetation growth, so it is given a higher weight. The calculation formula can be expressed as:

[0094] where EHI is the ecological health index, S hydro , S npp , and S future are the standardized scores of hydrological factors, net primary productivity of vegetation, and future ecological status, respectively, and w1, w2, and w3 are weights that satisfy w1 + w2 + w3 = 1. By setting a threshold, such as EHI < 0.5, areas with scores below the threshold are determined as high-risk areas. These areas may face problems such as vegetation degradation, water resource shortage, or soil erosion, and need priority attention.

[0095] Further, geographic coordinates or grid ranges are assigned to high-risk areas to generate a risk distribution map. The risk distribution map is presented in the form of a GIS grid layer, using color coding to visually display the spatial distribution of high-risk areas, such as red for high risk and green for healthy areas. This visualization method facilitates decision-makers to quickly identify problem areas, such as erosion high-risk areas formed in the downstream of a watershed due to concentrated runoff. The risk distribution map also supports spatial statistical analysis, such as calculating the area proportion or spatial clustering degree of high-risk areas, providing quantitative basis for ecological management. In addition, the risk distribution map retains geographic reference information and can be overlaid with other layers such as land use or topographic maps, further analyzing the causes of risk.

[0096] Next, targeted ecological restoration suggestions are generated based on the ecological factor status of high-risk areas. These suggestions are based on the specific ecological problems of abnormal areas, for example, low vegetation productivity areas may require afforestation or irrigation measures, and high runoff areas may require the construction of soil and water conservation projects such as terraces or vegetation buffer zones. Restoration suggestions combine the predicted status of hydrological, vegetation, and soil factors to ensure the targeted and feasibility of measures. For example, if an area is predicted to have low soil moisture and high runoff, it may be recommended to plant drought-tolerant plants and build a diversion ditch. These suggestions are organized in the form of text or tables, clearly outlining the implementation location, priority, and expected effect of restoration measures, providing direct guidance for ecological restoration planning.

[0097] Finally, the risk distribution map and ecological restoration suggestions are integrated on the GIS platform to generate an ecological environment diagnosis report, and the visualization of risk distribution is realized on the WebGIS interface. The diagnosis report summarizes the analysis results in a structured form, including the geographic location of high-risk areas, ecological health index, risk distribution map, and restoration suggestions. The WebGIS interface displays the risk distribution through an interactive map, and users can zoom in and query the ecological status and suggested measures of specific areas. For example, decision-makers can click on a high-risk area to view its ecological factor status and recommended vegetation restoration scheme. This visualization improves the accessibility and practicality of diagnosis results, supporting multi-party collaboration and public participation.

[0098] The above-mentioned method provided by the embodiments of the present application can be applied to various application scenarios, including but not limited to: first, in the management of watershed water resources, the method can predict future hydrological and vegetation states, identify high-risk areas such as soil erosion areas, and propose targeted restoration measures such as vegetation restoration or soil and water conservation projects, to help sustainable development of the watershed. Second, in urban ecological planning, the health status of urban green space can be evaluated by analyzing the distribution of vegetation productivity and soil moisture, and the layout and irrigation strategy of green space can be optimized to improve the ecological livability of the city. In addition, in nature reserve monitoring, the method can predict the evolution trend of ecological factors, identify risk areas of degradation, and develop protection measures such as restrictions on development or ecological restoration to ensure biodiversity protection. These scenarios utilize the dynamic prediction and spatial analysis capabilities of the method to provide scientific basis for ecological environment management.

[0099] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in an order different than the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing are additionally or alternatively possible or advantageous.

[0100] According to another aspect, embodiments provide a GIS-based ecological environment spatial diagnosis system. Figure 3 A schematic block diagram of the GIS-based ecological environment spatial diagnosis system according to an embodiment is shown. As shown, Figure 3 The system 300 includes: A data acquisition and preprocessing module 301 configured to acquire multi-source spatial data and preprocess the multi-source spatial data through a GIS platform to generate standardized spatial data layers; the multi-source spatial data includes remote sensing image data, meteorological data, soil attribute data, and a digital elevation model.

[0101] A hydrological model module 302 configured to simulate a watershed hydrological process using a soil and water assessment tool model using the spatial data layers to generate hydrological factor data, including spatial distribution data of runoff, evapotranspiration, and soil moisture.

[0102] A vegetation growth model module 303 configured to analyze the spatial coupling relationship between hydrological factors and vegetation growth using a CASA model using the remote sensing image data and the hydrological factor data to generate vegetation net primary productivity spatial distribution data.

[0103] A fractal analysis module 304 configured to calculate the fractal dimension of ecological factors using fractal theory using the hydrological factor data and the vegetation net primary productivity spatial distribution data to generate a fractal dimension distribution map and a spatial heterogeneity distribution map according to the fractal dimension distribution map.

[0104] A Markov model module 305 configured to construct a spatial ecological factor transmission chain including hydrological, vegetation, and soil factors using a Markov model according to the fractal dimension distribution data and generate a spatial distribution map of future ecological states according to the spatial ecological factor transmission chain.

[0105] A diagnosis result generation module 306 configured to generate ecological environment diagnosis results according to the spatial distribution map of future ecological states.

[0106] As an implementable way, the data acquisition and preprocessing module 301 can be configured to preprocess, including using principal component analysis for dimension noise reduction and feature enhancement of the multi-source spatial data.

[0107] As an implementable manner, the fractal analysis module 304 can be configured to, when calculating the fractal dimension of the ecological factor by using the hydrological factor data and the vegetation net primary productivity spatial distribution data, generating fractal dimension distribution data, and generating a spatial heterogeneity distribution map according to the fractal dimension distribution data, convert the hydrological factor data and the vegetation net primary productivity spatial distribution data into a grid format to generate a spatial distribution matrix containing runoff, soil moisture, and vegetation net primary productivity; use a box dimension method to perform multi-scale grid covering on the spatial distribution matrix to calculate the number of covered grids at different grid scales; fit a log-log curve according to the grid scale and the number of covered grids to calculate a slope to determine the fractal dimension, and generate fractal dimension distribution data of runoff, soil moisture, and vegetation net primary productivity; and perform spatial interpolation on the fractal dimension distribution data on a GIS platform to generate a continuous spatial heterogeneity distribution map.

[0108] As an implementable manner, the Markov model module 305 can be configured to, when constructing a spatial ecological factor conduction chain containing hydrological, vegetation, and soil factors by using a Markov model according to the fractal dimension distribution data, and generating a spatial distribution map of a future ecological state according to the spatial ecological factor conduction chain, divide an ecological factor state space according to the fractal dimension distribution data; calculate a state transition probability matrix based on the state space and historical data; predict a dynamic evolution trend of the ecological factor based on the state transition probability matrix by using a Markov chain to generate a spatial distribution map of a future ecological state.

[0109] As an implementable manner, the Markov model module 305 can be configured to, when dividing an ecological factor state space according to the fractal dimension distribution data, perform statistical analysis on the fractal dimension distribution data to calculate statistical distribution characteristics of the fractal dimension, including a mean value and a standard deviation; set a fractal dimension threshold based on the statistical distribution characteristics to divide the fractal dimension distribution data into a plurality of discrete intervals, each interval corresponding to an ecological factor state; perform regional division on the fractal dimension distribution data by using spatial clustering analysis to generate a state region with spatial continuity; and assign a discrete state of a hydrological, vegetation, or soil factor to each grid cell according to the discrete intervals and the spatial clustering result to generate an ecological factor state space.

[0110] As an implementable manner, the Markov model module 305 can be configured to: according to the ecological factor state space and the historical data, count the transition frequency between states to generate an initial state transition probability matrix; for each row of the initial state transition probability matrix, calculate the transition uncertainty from the current state to the next state, which is obtained by summing the product of each transition probability and the negative value of the logarithm thereof; according to the frequency of each state in the state space in the historical data, calculate the weighted average of the transition uncertainty of all states to obtain the transition uncertainty of the entire system; according to the transition uncertainty, filter the state transition paths below the preset threshold to eliminate low-probability or high-uncertainty state transitions; and reconstruct an optimized state transition probability matrix based on the filtered state transition paths.

[0111] As an implementable manner, the diagnosis result generation module 306 can be configured to: based on the spatial distribution map of the future ecological state, perform spatial analysis to identify the abnormal area of the ecological state; perform weighted scoring on the hydrological factor data, the net primary productivity data of the vegetation, and the future ecological state data of the abnormal area to generate an ecological health index, and the area with the ecological health index below the preset threshold is determined as a high-risk area; assign geographic coordinates or grid ranges to the high-risk area to generate a risk distribution map; generate targeted ecological restoration suggestions including vegetation restoration or soil and water conservation measures according to the ecological factor state of the high-risk area; integrate the risk distribution map and the ecological restoration suggestions on the GIS platform to generate an ecological environment diagnosis report, and realize the visual display of the risk distribution on the WebGIS interface.

[0112] Each of the embodiments in the specification is described in a progressive manner, and the same and similar parts of each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, it is described more simply, and the related parts can be referred to the part of the method embodiment. The above-described system and system embodiment are only illustrative, and the units described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0113] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0114] In addition, the embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the steps of the method in any one of the preceding method embodiments.

[0115] And an electronic device, comprising: one or more processors; and a memory associated with the one or more processors, the memory being configured to store program instructions that, when executed by the one or more processors, perform the steps of the method in any one of the preceding method embodiments.

[0116] The present application also provides a computer program product, comprising a computer program, which, when executed by a processor, realizes the steps of the method in any one of the preceding method embodiments.

[0117] Among them, Figure 4 An exemplary electronic device architecture is shown, which can specifically include a processor 410, a video display adapter 411, a disk drive 412, an input / output interface 413, a network interface 414, and a memory 420. The above-mentioned processor 410, video display adapter 411, disk drive 412, input / output interface 413, network interface 414, and memory 420 can be connected by a communication bus 430.

[0118] Among them, the processor 410 can be implemented by a general-purpose CPU, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., for executing related programs to realize the technical solutions provided by the present application.

[0119] The memory 420 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 420 can store an operating system 421 for controlling the operation of the electronic device 400, a basic input / output system (BIOS) 422 for controlling the low-level operation of the electronic device 400. In addition, a web browser 423, a data storage management system X24, and a GIS-based ecological environment space diagnosis system 425, etc. can also be stored. The GIS-based ecological environment space diagnosis system 425 described above can be an application program for implementing the operations of the above steps in the embodiments of the present application. In summary, when the technical solutions provided by the present application are implemented by software or firmware, the relevant program codes are stored in the memory 420 and executed by the processor 410.

[0120] The input / output interface 413 is configured to connect an input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0121] The network interface 414 is configured to connect a communication module (not shown in the figure) to realize the communication interaction between the device and other devices. The communication module can realize communication through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).

[0122] The bus 430 includes a path for transmitting information between various components (such as the processor 410, the video display adapter 411, the disk drive 412, the input / output interface 413, the network interface 414, and the memory 420) of the device.

[0123] It should be noted that although the above device only shows the processor 410, the video display adapter 411, the disk drive 412, the input / output interface 413, the network interface 414, the memory 420, and the bus 430, etc., in the specific implementation process, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also only contain the components necessary for implementing the solutions of the present application, and does not necessarily contain all the components shown in the figure.

[0124] Those skilled in the art can clearly understand the application by the description of the above embodiments that the application can be implemented by means of software and the necessary universal hardware platform. Based on such an understanding, the technical solutions of the application can be embodied in the form of a computer program product, which can be stored in a storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and include a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in various embodiments or some parts of the embodiments of the application.

[0125] The technical solutions provided by the application are described in detail above, and the principles and implementation manners of the application are described by applying specific examples. The above description of the embodiments is only used to help understand the methods and core ideas of the application. Meanwhile, for those skilled in the art, the specific implementation manners and application ranges can be changed according to the ideas of the application. In conclusion, the content of the specification should not be understood as a limitation of the application.

Claims

1. A GIS-based ecological environment space diagnosis method, characterized in that, The method comprises the following steps: obtaining multi-source spatial data, and preprocessing the multi-source spatial data through a GIS platform to generate standardized spatial data layers; using the spatial data layers, simulating a watershed hydrological process by using a soil and water evaluation tool model to generate hydrological factor data, the hydrological factor data comprising spatial distribution data of runoff, evapotranspiration and soil moisture; using the remote sensing image data and the hydrological factor data, analyzing the spatial coupling relationship between hydrological factors and vegetation growth by using a CASA model to generate spatial distribution data of vegetation net primary productivity; using the hydrological factor data and the spatial distribution data of vegetation net primary productivity, calculating the fractal dimension of ecological factors by using fractal theory to generate fractal dimension distribution data, and generating a spatial heterogeneity distribution map according to the fractal dimension distribution data; according to the fractal dimension distribution data, constructing a spatial ecological factor transmission chain containing hydrological, vegetation and soil factors by using a Markov model, and generating a spatial distribution map of future ecological states according to the spatial ecological factor transmission chain; generating an ecological environment diagnosis result according to the spatial distribution map of future ecological states.

2. The GIS-based ecological environment space diagnostic method according to claim 1, characterized in that, The preprocessing comprises using principal component analysis to perform dimension noise reduction and feature enhancement on the multi-source spatial data; the multi-source spatial data comprises remote sensing image data, meteorological data, soil property data and a digital elevation model. 3.The GIS-based ecological environment space diagnosis method according to claim 1, characterized in that, The step of using the hydrological factor data and the spatial distribution data of vegetation net primary productivity, calculating the fractal dimension of ecological factors by using fractal theory to generate fractal dimension distribution data, and generating a spatial heterogeneity distribution map according to the fractal dimension distribution data comprises: converting the hydrological factor data and the spatial distribution data of vegetation net primary productivity into a grid format to generate a spatial distribution matrix containing runoff, soil moisture and vegetation net primary productivity; using a box dimension method, performing multi-scale grid covering on the spatial distribution matrix to calculate the number of covered grids at different grid scales; according to the grid scale and the number of covered grids, fitting a log-log curve, calculating a slope to determine the fractal dimension, and generating fractal dimension distribution data of runoff, soil moisture and vegetation net primary productivity; performing spatial interpolation on the fractal dimension distribution data on the GIS platform to generate a continuous spatial heterogeneity distribution map.

4. The GIS-based ecological environment space diagnostic method according to claim 1, characterized in that, The step of according to the fractal dimension distribution data, constructing a spatial ecological factor transmission chain containing hydrological, vegetation and soil factors by using a Markov model, and generating a spatial distribution map of future ecological states according to the spatial ecological factor transmission chain comprises: dividing an ecological factor state space according to the fractal dimension distribution data; calculating a state transition probability matrix based on the state space and historical data; using a Markov chain, predicting the dynamic evolution trend of ecological factors based on the state transition probability matrix to generate a spatial distribution map of future ecological states. 5.The GIS-based ecological environment space diagnosis method according to claim 4, characterized in that, The step of dividing an ecological factor state space according to the fractal dimension distribution data comprises: performing statistical analysis on the fractal dimension distribution data to calculate statistical distribution characteristics of the fractal dimension, including mean and standard deviation; Based on the statistical distribution characteristics, a fractal dimension threshold is set, and the fractal dimension distribution data is divided into multiple discrete intervals, each interval corresponding to an ecological factor state; Using spatial clustering analysis, the fractal dimension distribution data is divided into regions to generate state regions with spatial continuity; According to the discrete intervals and spatial clustering results, the discrete state of the hydrological, vegetation, or soil factor is assigned to each grid cell to generate an ecological factor state space. 6.The GIS-based ecological environment space diagnosis method according to claim 4, characterized in that, The calculation of the state transition probability matrix based on the state space and historical data includes: According to the ecological factor state space and historical data, the transition frequency between states is counted to generate an initial state transition probability matrix; For each row of the initial state transition probability matrix, the transition uncertainty from the current state to the next state is calculated, which is obtained by summing the product of each transition probability and the negative value of the logarithm of each transition probability; According to the frequency of each state in the state space in the historical data, the weighted average of the transition uncertainty of all states is calculated to obtain the transition uncertainty of the entire system; According to the transition uncertainty, state transition paths below a preset threshold are screened out, and state transitions with low probability or high uncertainty are removed; Based on the screened state transition paths, an optimized state transition probability matrix is reconstructed.

7. The GIS-based ecological environment space diagnostic method according to claim 1, characterized in that, The generation of ecological environment diagnosis results according to the spatial distribution map of the future ecological state includes: Based on the spatial distribution map of the future ecological state, spatial analysis is performed to identify areas with abnormal ecological states; The hydrological factor data, the net primary productivity of vegetation data, and the future ecological state data of the abnormal areas are weighted and scored to generate an ecological health index, and areas with an ecological health index below a preset threshold are determined as high-risk areas; The high-risk areas are assigned geographic coordinates or grid ranges to generate a risk distribution map; According to the ecological factor state of the high-risk areas, targeted ecological restoration suggestions are generated, including vegetation restoration or soil and water conservation measures; The risk distribution map and ecological restoration suggestions are integrated on the GIS platform to generate an ecological environment diagnosis report, and the visualization of the risk distribution is realized on the WebGIS interface.

8. A GIS-based ecological environment space diagnostic system, characterized in that, The system includes: A data acquisition and preprocessing module configured to acquire multi-source spatial data and preprocess the multi-source spatial data through a GIS platform to generate standardized spatial data layers, the multi-source spatial data including remote sensing image data, meteorological data, soil property data, and a digital elevation model; A hydrological model module configured to simulate the hydrological process of a watershed using the SWAP model based on the spatial data layers to generate hydrological factor data, including the spatial distribution data of runoff, evapotranspiration, and soil moisture; A vegetation growth model module configured to analyze the spatial coupling relationship between hydrological factors and vegetation growth using the CASA model based on the remote sensing image data and the hydrological factor data to generate net primary productivity spatial distribution data of vegetation; A data acquisition and preprocessing module configured to acquire multi-source spatial data and preprocess the multi-source spatial data through a GIS platform to generate standardized spatial data layers, the multi-source spatial data including remote sensing image data, meteorological data, soil property data, and a digital elevation model; A hydrological model module configured to simulate the hydrological process of a watershed using the SWAP model based on the spatial data layers to generate hydrological factor data, including the spatial distribution data of runoff, evapotranspiration, and soil moisture; A vegetation growth model module configured to analyze the spatial coupling relationship between hydrological factors and vegetation growth using the CASA model based on the remote sensing image data and the hydrological factor data to generate net primary productivity spatial distribution data of vegetation; The fractal analysis module is configured to use the hydrological factor data and the vegetation net primary productivity spatial distribution data to calculate a fractal dimension of an ecological factor by using a fractal theory, generate fractal dimension distribution data, and generate a spatial heterogeneity distribution map according to the fractal dimension distribution data. The Markov model module is configured to use a Markov model to construct a spatial ecological factor transmission chain containing hydrological, vegetation, and soil factors according to the fractal dimension distribution data, and generate a spatial distribution map of a future ecological state according to the spatial ecological factor transmission chain. The diagnosis result generation module is configured to generate an ecological environment diagnosis result according to the spatial distribution map of the future ecological state.

9. An electronic device, comprising: The method comprises: one or more processors; and a memory associated with the one or more processors, the memory being configured to store program instructions that, when executed by the one or more processors, perform the steps of the GIS-based ecological environment spatial diagnosis method according to any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the GIS-based ecological environment spatial diagnosis method according to any one of claims 1-7.

Images