An ecological protection red line division method applied to ecological foundation investigation

Abstract

The application relates to the technical field of ecological environment protection, in particular to an ecological protection red line division method applied to ecological foundation investigation, which comprises the following steps: through ecological foundation data collection and processing, the service function and stability of an ecological unit are evaluated in combination with an ecological model, and then an ecological protection red line region is demarcated. Through spatial superposition analysis and conflict analysis of a land use status, the boundary of the red line region is optimized, and real-time adjustment is carried out based on ecological risk evaluation and a dynamic monitoring mechanism. In combination with a deep learning and a reinforcement learning algorithm, dynamic monitoring and flexible adjustment of the red line region are realized, the sustainability and safety of an ecological system are guaranteed, through GIS technology and an early warning mechanism, intelligent management of the ecological protection red line is realized, the scientificity and effectiveness of the ecological protection red line region are ensured, and reliable guarantee is provided for long-term stable development of the ecological system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ecological environment protection, and particularly relates to an ecological protection red line division method applied to ecological foundation investigation. BACKGROUND

[0002] With the continuous enhancement of ecological environment protection consciousness, as an important measure of ecological environment protection, the ecological protection red line refers to a regional protection range determined based on scientific assessment of ecological function, ecological service and ecological sensitivity.

[0003] However, the division of the ecological protection red line not only involves large-scale ecological data collection and processing, but also needs to comprehensively consider the natural characteristics and social and economic factors of the region. The traditional red line division method often relies on static ecological function assessment, and lacks real-time monitoring and dynamic adjustment capability for regional ecological risk changes. In the prior art, most of the fixed red line boundaries lack real-time updating and mechanism for responding to sudden ecological risks, which leads to the inability to timely adjust the red line range when facing natural disasters, climate change and human activity interference, affecting the flexibility and accuracy of ecological protection. In addition, due to the single ecological function assessment method, the stability of the regional ecological system, the intensity of ecological service and the ecological sensitivity cannot be comprehensively considered, resulting in the possibility of blind spots or over-protection in the ecological protection red line division process, and it is difficult to achieve the balance between ecological protection and social and economic development. SUMMARY

[0004] Based on the above purpose, the present application provides an ecological protection red line division method applied to ecological foundation investigation.

[0005] An ecological protection red line division method applied to ecological foundation investigation, comprising the following steps:

[0006] S1, ecological foundation data collection: collecting ecological foundation data in the target region, including vegetation coverage, soil erosion intensity, surface water distribution, land use status data, climate data, human activity distribution data, historical disaster records and remote sensing image data, and performing spatial matching and standardization processing through a geographic information system;

[0007] S2, ecological function assessment and classification: based on the collected ecological foundation data, using an ecological model to assess the stability, ecological service function intensity (water conservation, carbon sink, soil conservation) and ecological sensitivity of the ecological unit, and dividing the ecological service function level;

[0008] S3, regional ecological function division and red line framework design: according to the ecological service function level, combining the land use status and the boundary of the nature reserve, the ecological protection red line region is divided, and the protection target and the development restriction type are clarified;

[0009] S4, ecological risk assessment and early warning: based on the assessment results of S2, an ecological risk model is constructed to assess the risks of natural disasters, climate change and human disturbance factors in the red line area, and a dynamic early warning mechanism is designed;

[0010] S5, dynamic monitoring and adjustment mechanism: using real-time ecological basic data of S1, through machine learning algorithm combined with ecological service function level and risk warning level, dynamically adjusting the red line range, responding to the risk warning results of S4.

[0011] Optionally, the S1 comprises:

[0012] S11, multi-source data acquisition and classification: through satellite remote sensing platform, multi-temporal, multi-spectral remote sensing image data of target area is obtained, through ground monitoring station, vegetation coverage, soil erosion intensity, surface water distribution and climate data (including precipitation, temperature, wind speed) are collected, through satellite remote sensing interpretation and national land survey database, land use status data (including spatial distribution and area proportion of cultivated land, forest land, grassland, construction land, unused land) are obtained, through social and economic statistical database and field investigation, human activity distribution data (including spatial distribution of residential area, industrial land, transportation network) are obtained, through local disaster management department database and historical remote sensing image inversion, historical disaster records (including time, spatial distribution and impact range of flood, landslide, debris flow and other events) are obtained;

[0013] S12, data preprocessing and format standardization: radiation correction, atmospheric correction and geometric precision correction are performed on remote sensing image data to generate standard false color composite image, missing value filling, outlier removal and time series smoothing processing are performed on ground monitoring data and human activity data, and are uniformly converted into geographic information system (GIS) compatible vector or raster format (such as Shapefile, GeoTIFF);

[0014] S13, spatial reference system unification: all data are projected to the same geographic coordinate system (such as WGS84 coordinate system) and set a unified spatial resolution, through resampling, spatial interpolation and vector-raster conversion to eliminate data scale difference;

[0015] S14, ecological data spatial matching and attribute association: in GIS platform, vegetation coverage, soil erosion intensity, surface water distribution, climate data and human activity distribution data are superimposed, based on spatial location, layer registration is performed, attribute association table is established, one-to-one mapping of ecological parameters and geographic units is realized (such as each grid unit is associated with vegetation type, erosion level, water source distance, climate factor and human activity intensity);

[0016] S15, data quality verification and integrated storage: through cross verification (such as comparison of remote sensing data and ground measured data) and spatial consistency test (such as smooth transition of adjacent area data), the accuracy of the data is ensured, and finally the standardized multi-source ecological data is integrated into the time-space database, and is stored according to time stamp and spatial block classification, supporting the dynamic call of subsequent ecological function evaluation model.

[0017] Optionally, the S2 comprises:

[0018] S21, ecological service function index quantification: based on the ecological basic data collected in S1, the water conservation amount is calculated through the water source conservation module in the InVEST model, the carbon sink intensity is evaluated through the net primary productivity carbon sink module of the CASA model, and the soil conservation intensity is evaluated through the soil erosion module calculation module of the RUSLE equation;

[0019] S22, function intensity normalization and weight distribution: the calculated water conservation amount, carbon sink intensity and soil conservation intensity are normalized. Specifically, the linear normalization formula is used to map the minimum value of each service function index to 0 and the maximum value to 1, then the weight of each function is determined by using the analytic hierarchy process combined with expert scoring, wherein the weight of water conservation is set to 0.4, the weight of carbon sink is 0.3, and the weight of soil conservation is 0.3, finally, the weighted sum of the normalized function intensity values is obtained, and the comprehensive ecological service function intensity value of each ecological unit is obtained;

[0020] S23, service function grade division: according to the comprehensive ecological service function intensity value, the natural breakpoint method is used to divide the target area into high, medium and low grades.

[0021] S24, ecological sensitivity factor screening and quantification: based on the ecological basic data collected in S1, the terrain slope, vegetation coverage, soil erosion intensity, surface water proximity and human activity disturbance intensity are selected as the ecological sensitivity factors, and the quantization value of the ecological sensitivity factors is calculated by the GIS spatial analysis method.

[0022] S25, sensitivity index integration and grade division: the weight of each sensitivity factor is defined, wherein the slope weight is 0.25, the vegetation coverage weight is 0.30, the soil erosion intensity weight is 0.20, the surface water proximity weight is 0.15, and the human activity disturbance intensity weight is 0.10, the quantization values of each factor are superimposed by weighting to generate an ecological sensitivity index layer, and the equal interval method is used to divide the sensitivity index into high, medium and low grades.

[0023] S26, ecological system stability evaluation: based on the ecological service function intensity grade obtained in S23 and the ecological sensitivity grade obtained in S25, an ecological system stability matrix is constructed, and finally the stability evaluation result of the ecological system is output.

[0024] Optionally, the S3 comprises:

[0025] S31, ecological priority protection zone identification: based on the divided ecological service function level (high, medium, low) and ecological sensitivity level (high, medium, low), through the GIS spatial overlay analysis method, the "high function-low sensitivity" and "high function-medium sensitivity" regions are selected as the priority protection zone, and combined with the boundary of the existing nature reserve, the preliminary ecological protection red line candidate area is demarcated;

[0026] S32, land use conflict analysis and boundary optimization: the land use status data collected in S1 is overlaid and analyzed with the red line candidate area, the region with human activity conflict is identified, the conflict region is adjusted, and the boundary of the affected region is optimized and adjusted according to the principle of ecological function priority.

[0027] S33, protection zone boundary fusion and expansion: the boundary of the existing nature reserve is fused with the optimized red line candidate area, and whether there is a high ecological service function area not included outside the nature reserve is analyzed;

[0028] S34, protection target and development restriction grading: according to the combination of ecological service function level and ecological sensitivity level in the red line area, three levels of management and control rules are defined.

[0029] S35, red line area mapping and attribute association: through GIS mapping technology, the finally demarcated ecological protection red line area and its corresponding management and control rules are coded into a vector layer, and the detailed attribute table field is associated.

[0030] Optionally, the S4 comprises:

[0031] S41, risk factor screening and quantification: based on the divided ecological service function level and the generated ecological sensitivity level, combined with the climate data, human activity distribution data and historical disaster records collected in S1, the natural disaster factors (including flood frequency, landslide susceptibility index), climate change factors (including annual mean temperature change rate, extreme precipitation event probability) and human disturbance factors (including industrial pollution emission intensity, construction land expansion rate) are screened, and the risk values of each factor are quantified through GIS spatial analysis method;

[0032] S42, ecological risk model construction and weight distribution: through spatial overlay analysis method, the screened natural disaster, climate change and human disturbance factor layers are weighted and overlaid with the ecological service function level and ecological sensitivity level layers, and the weight of each factor (natural disaster weight 0.35, climate change weight 0.30, human disturbance weight 0.35) is determined, the ecological risk index model is constructed, and the comprehensive ecological risk index of each region is calculated.

[0033] S43, risk level division and dynamic threshold setting: according to the ecological risk index value, the target area is divided into high risk area, medium risk area and low risk area by using natural breakpoint method;

[0034] S44, dynamic early warning mechanism design: based on real-time remote sensing image data, climate data and human activity data, a time series risk prediction model is established, the model dynamically calculates the ecological risk index change trend in the next 30 days, and sets four levels of early warning signals and response strategies according to the risk index.

[0035] S45, early warning output and feedback linkage: the generated risk level, early warning signal and response strategy are pushed in real time through the GIS management platform to generate an early warning report, and at the same time, the dynamic monitoring and adjustment mechanism described in S5 is triggered to optimize and adjust the ecological protection red line boundary of high-risk areas, further reducing potential ecological risks.

[0036] Optionally, the S44 comprises:

[0037] S441, data preprocessing and feature extraction: the collected real-time remote sensing image data is subjected to radiation correction and cloud mask processing, vegetation index, land surface temperature and water body index are extracted, climate data (such as precipitation, wind speed, temperature) are subjected to time interpolation, missing values are filled, spatial continuous grid data is generated, and human activity data is converted into spatial resolution data matching the ecological risk index model, to ensure that all kinds of data have consistent spatial resolution and time span;

[0038] S442, time series risk prediction model construction: based on historical ecological risk index data and real-time monitoring data (real-time remote sensing image data, climate data and human activity data), a long short-term memory network is used to construct a time series risk prediction model, the input features of the model include current risk index, vegetation index change rate, precipitation deviation and human activity intensity increment, and the output is the risk index prediction value in the next 30 days.

[0039] S443, dynamic early warning threshold adaptive adjustment: according to the division of ecological service function level, a differentiated early warning threshold is set.

[0040] S444, multi-level early warning signal generation and strategy binding: based on the predicted risk index and the adaptively adjusted threshold, four levels of early warning signals are generated.

[0041] S445, early warning visualization: the generated early warning signal is superimposed with the vector layer generated in S35, a heat map is used for rendering to show the risk level distribution, and is pushed to the supervision terminal (including PC and mobile devices) in real time.

[0042] Optionally, the S5 comprises:

[0043] S51, multi-source real-time data integration and feature coding: based on the collected real-time remote sensing images, climate data, human activity distribution data, the vegetation coverage change rate, the ground temperature anomaly, the construction land expansion rate and the pollution source distribution feature are extracted, meanwhile, the generated four-level risk early warning signal, the ecological service function level and the ecological sensitivity level are accessed, and are coded as a multi-dimensional feature vector aligned in space and time, and are input to a red line adjustment decision model;

[0044] S52, dynamic adjustment model construction and training: a deep reinforcement learning framework is used to construct the red line adjustment decision model.

[0045] S53, priority-driven adjustment strategy generation: according to the combination of the risk warning level and the ecological service function level, the adjustment priority is set.

[0046] And combined with the management and control rules of S34 (such as prohibition of contraction in the first control area), a candidate adjustment scheme set is generated, and the schemes conflicting with the management and control rules are excluded;

[0047] S54, red line boundary space optimization and conflict resolution: the candidate adjustment scheme set is subjected to GIS spatial analysis, and a multi-objective genetic algorithm is used to optimize the red line boundary, and the optimization targets include: maximizing the ecological corridor connectivity (calculated by the landscape index MSPA), minimizing the conflict area with human activities (referring to S32 conflict area), maximizing the protection proportion of high-function areas (≥80%), and finally outputting a Pareto optimal solution set, which is selected as the optimal red line adjustment scheme after artificial auditing;

[0048] S55, adjustment effect feedback and model iteration: the optimal red line adjustment scheme is synchronized to the management platform in real time, and through the early warning feedback mechanism, the ecological risk index change and the function level stability within 30 days after adjustment are monitored.

[0049] The beneficial effects of the present application are:

[0050] The present application can scientifically and systematically evaluate the ecological service function, sensitivity and stability of the target region through comprehensive collection of ecological basic data (such as vegetation coverage, soil erosion intensity, climate data, etc.) and combination of various ecological models (such as InVEST model, CASA model, RUSLE model) for ecological function evaluation and classification. This multi-level and multi-dimensional evaluation method makes the delineation of ecological protection red line more accurate, ensures the maximum ecological function of the ecological protection area, effectively avoids the risk of overdevelopment, and further improves the scientificity and accuracy of ecological protection.

[0051] Based on the dynamic monitoring and early warning mechanism of real-time data (such as remote sensing images, meteorological monitoring, climate change, etc.), the present application constructs an accurate ecological risk assessment model, and combines deep learning technology to predict the risk index and adjust the dynamic threshold. Through four levels of early warning signals and emergency response strategies matched with risk levels, regional ecological risk changes can be captured in time and dynamically adjusted, effectively improving the response speed and flexibility of ecological protection. In addition, combined with the dynamic red line adjustment decision model, the red line boundary can be automatically optimized according to the risk changes and ecological function evaluation results, ensuring that the ecological protection red line is always in a reasonable and effective state under the new ecological risk environment, and maximizing the protection of ecological safety.

[0052] The present application can balance the conflict between ecological protection demand and human activities (such as construction, industry, agriculture, etc.) by using multi-objective genetic algorithm for conflict resolution in red line boundary optimization, maximize ecological corridor connectivity, minimize human activity conflict area, and ensure the protection proportion of high function area. Through this optimization process, the adverse effects of human activities on the ecological environment can be effectively avoided, and the coordination between ecological protection and regional sustainable development can be promoted. Especially for the priority protection of high sensitive areas, the scientificity and effectiveness of the ecological protection red line area are ensured, providing reliable guarantee for the long-term stability and healthy development of the ecological system. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only illustrate the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0054] Fig. 1 The method flowchart of the embodiment of the present application is shown in the following.

[0055] Fig. 2 The S3 flowchart of the embodiment of the present application is shown in the following. DETAILED DESCRIPTION

[0056] The present application will be described in detail below in combination with the drawings and specific embodiments. It should be noted that in order to make the embodiments more detailed, the following embodiments are the best, preferred embodiments, and other alternative ways can also be used by those skilled in the art to implement some known technologies; and the drawings are only used to more specifically describe the embodiments, and are not intended to specifically limit the present application.

[0057] As shown in the following, Figs. 1-2 A method for dividing ecological protection red line applied to ecological basic survey, comprising the following steps:

[0058] S1, Ecological Foundation Data Collection: Collect ecological foundation data within the target area, including vegetation coverage, soil erosion intensity, surface water distribution, land use status data, climate data, human activity distribution data, historical disaster records, and remote sensing image data, and perform spatial matching and standardized processing through a geographic information system;

[0059] S2, Ecological Function Assessment and Classification: Based on the collected ecological foundation data, use ecological models to assess the stability, ecological service function intensity (water conservation, carbon sink, soil conservation), and ecological sensitivity of ecological units, and classify the ecological service function levels (high, medium, and low);

[0060] S3, Regional Ecological Function Division and Red Line Framework Design: Based on the ecological service function levels, combined with land use status and nature reserve boundaries, delineate ecological protection red line areas, and clearly define protection targets and development restriction types;

[0061] S4, Ecological Risk Assessment and Early Warning: Based on the assessment results of S2, construct an ecological risk model to assess the risks of natural disasters, climate change, and human disturbance factors within the red line area, and design a dynamic early warning mechanism;

[0062] S5, Dynamic Monitoring and Adjustment Mechanism: Use real-time ecological foundation data from S1, and through machine learning algorithms combined with ecological service function levels and risk warning levels, dynamically adjust the red line range, and respond to the risk warning results of S4.

[0063] S1 includes:

[0064] S11, Multi-source Data Acquisition and Classification: Obtain multi-temporal, multi-spectral remote sensing image data of the target area through satellite remote sensing platforms, collect vegetation coverage, soil erosion intensity, surface water distribution, and climate data (including precipitation, temperature, wind speed) through ground monitoring stations, obtain land use status data (including the spatial distribution and area proportion of cultivated land, forest land, grassland, construction land, and unused land) through satellite remote sensing interpretation and national land survey database, obtain human activity distribution data (including the spatial distribution of residential areas, industrial land, and transportation networks) through social and economic statistical databases and field surveys, and obtain historical disaster records (including the time, spatial distribution, and impact range of events such as floods, landslides, and debris flows) through local disaster management department databases and historical remote sensing image inversion;

[0065] S12, data preprocessing and format standardization: perform radiation correction, atmospheric correction and geometric precise correction on remote sensing image data to generate standard false color composite image, perform missing value filling, outlier removal and time series smoothing processing on ground monitoring data and human activity data, and convert them into geographic information system (GIS) compatible vector or raster format (such as Shapefile, GeoTIFF);

[0066] S13, spatial reference system unification: project all data to the same geographic coordinate system (such as WGS84 coordinate system) and set a unified spatial resolution (such as 30m x 30m grid), eliminate data scale differences by resampling, spatial interpolation and vector-raster conversion;

[0067] S14, ecological data spatial matching and attribute association: overlay vegetation coverage, soil erosion intensity, surface water distribution, climate data and human activity distribution data in GIS platform, perform layer registration based on spatial location, establish attribute association table, realize one-to-one mapping of ecological parameters and geographic units (such as each grid cell associated with vegetation type, erosion level, water source distance, climate factor and human activity intensity);

[0068] S15, data quality verification and integrated storage: ensure data accuracy through cross verification (such as comparison of remote sensing data and ground measured data) and spatial consistency test (such as smooth transition of adjacent area data), finally integrate standardized multi-source ecological data into time and space database, store according to time stamp and spatial block, support dynamic call of subsequent ecological function evaluation model.

[0069] S2 includes:

[0070] S21, ecological service function index quantification: based on the ecological basic data collected in S1, calculate water conservation capacity through water conservation module in InVEST model, evaluate carbon sink intensity through net primary productivity carbon sink module of CASA model, and evaluate soil conservation intensity through soil erosion module calculation module of RUSLE equation;

[0071] The water conservation module of InVEST model uses the following calculation method to estimate the water conservation capacity, which is calculated as:

[0072] ;

[0073] Wherein, is the water conservation capacity, P is the precipitation, is the evapotranspiration coefficient, E is the evapotranspiration, and R is the runoff;

[0074] CASA model is used to evaluate the net primary productivity (NPP) of plants in the region, and then calculate the carbon sink intensity according to NPP, which is represented as:

[0075] NPP calculation formula:

[0076] ;

[0077] wherein NPP is the net primary productivity, f(T, P, I) is a plant growth model function, usually related to temperature T, precipitation P and light I, etc., and A is the area of the region;

[0078] The carbon sink amount is estimated according to the NPP, and is expressed as: ; wherein, is the carbon sink intensity;

[0079] The RUSLE equation estimates the soil erosion amount, and the soil conservation intensity is calculated by the difference between the potential erosion amount and the actual erosion amount, and the RUSLE equation is expressed as: ;

[0080] wherein, is the soil erosion amount, R is the precipitation erosion force factor, K is the soil erodibility factor, LS is the topographic factor (including slope and slope length), C is the cover factor (related to vegetation type and land coverage), is the soil conservation measure factor (reflecting human measures such as soil and water conservation engineering);

[0081] S22, function intensity normalization and weight distribution: the water source conservation amount, the carbon sink intensity and the soil conservation intensity calculated are normalized. Specifically, the minimum value of each service function index is mapped to 0 and the maximum value is mapped to 1 using a linear normalization formula, then the weight of each function is determined using the analytic hierarchy process combined with expert scoring, wherein the weight of water source conservation is set to 0.4, the weight of carbon sink is 0.3, and the weight of soil conservation is 0.3, finally, the normalized function intensity values are weighted and summed to obtain the comprehensive ecological service function intensity value of each ecological unit. The specific calculation formula is:

[0082] ;

[0083] wherein, , , are the normalized intensity values of water source conservation, carbon sink and soil conservation respectively, , , are the corresponding weight values;

[0084] S23, service function grade division: according to the comprehensive ecological service function intensity value, the target region is divided into high, medium and low grades using the natural breakpoint method;

[0085] Specifically, if the comprehensive service function intensity value of a certain region is , the region is classified as a high-function region; if , it is classified as a medium-function region, and if , it is classified as a low-function region. The classification results are stored in the form of a grid layer, and the attribute value of each grid cell is associated with the spatial boundary of the corresponding ecological unit to form a complete spatial distribution map. This classification result not only facilitates subsequent red line framework design, but also provides clear decision support for ecological protection and regional planning.

[0086] S24, ecological sensitivity factor screening and quantification: based on the ecological basic data collected in S1, the terrain slope, vegetation coverage, soil erosion intensity, surface water proximity, and human activity disturbance intensity are selected as the ecological sensitivity factors, and the quantification values of the ecological sensitivity factors are calculated through GIS spatial analysis methods, wherein:

[0087] Slope: according to different terrain slopes, it is classified as follows: 0-5° for level 1, 5-15° for level 2, and >15° for level 3.

[0088] Vegetation coverage: segmented using normalized difference vegetation index (NDVI) values: NDVI <0.2 for high sensitivity, 0.2≤NDVI<0.5 for medium sensitivity, and NDVI≥0.5 for low sensitivity.

[0089] Soil erosion intensity: classified according to the soil erosion intensity values calculated by the RUSLE model.

[0090] Surface water proximity: classified according to the distance of each ecological unit from the surface water body: <1km for high sensitivity, 1-5km for medium sensitivity, and >5km for low sensitivity.

[0091] Human activity disturbance intensity: classified according to the distance from residential areas or industrial land: <1km for high sensitivity, 1-5km for medium sensitivity, and >5km for low sensitivity.

[0092] S25, sensitivity index integration and grade division: define the weights of each sensitivity factor, wherein the slope weight is 0.25, the vegetation coverage weight is 0.30, the soil erosion intensity weight is 0.20, the surface water proximity weight is 0.15, and the human activity disturbance intensity weight is 0.10. The quantification values of each factor are weighted and superimposed to generate an ecological sensitivity index layer, and the sensitivity index is divided into high, medium, and low three grades using the equal interval method:

[0093] High sensitivity area: index≥0.75;

[0094] Medium sensitivity area: 0.5≤index<0.75;

[0095] Low sensitivity zone: index < 0.5.

[0096] S26, ecosystem stability assessment: based on the ecological service function intensity level obtained in S23 and the ecological sensitivity level obtained in S25, an ecosystem stability matrix is constructed, and the definition is:

[0097] The "high function-low sensitivity" area is the first level of stability (priority protection);

[0098] The "medium function-medium sensitivity" area and the "high function-medium sensitivity" area are the second level of stability (moderate protection);

[0099] The "low function-high sensitivity" area and the "medium function-high sensitivity" area are the third level of stability (repair priority);

[0100] A spatial distribution map of stability level is generated, and the distribution map is associated with the attribute table of the ecological unit, and finally the stability assessment results of the ecosystem are output.

[0101] S3 includes:

[0102] S31, identification of ecological priority protection area: based on the divided ecological service function level (high, medium, low) and ecological sensitivity level (high, medium, low), through GIS spatial overlay analysis method, the "high function-low sensitivity" and "high function-medium sensitivity" area are selected as priority protection area, and combined with the boundary of existing nature reserve, the preliminary ecological protection red line candidate area is demarcated, the specific method is: using spatial reclassification technology, the ecological function and sensitivity level layer is overlaid, and the area meeting the protection condition is marked;

[0103] S32, land use conflict analysis and boundary optimization: the land use status data collected in S1 is overlaid and analyzed with the red line candidate area, the area with human activity conflict is identified, the boundary of the affected area is optimized and adjusted, such as shrinking the range of industrial land, preserving the integrity of ecological corridor, etc., to ensure that the ecological function and ecological connectivity of the ecological protection red line area are not destroyed.

[0104] S33, protection area boundary fusion and expansion: the boundary of the existing nature reserve is fused with the optimized red line candidate area, and whether there are high ecological service function areas (such as water conservation area, important carbon sink area, etc.) outside the nature reserve is analyzed. If so, buffer analysis (radius ≥ 1km) is adopted to expand the area not included, and these areas are included in the red line protection range, forming a more coherent ecological protection network;

[0105] S34, Protection target and development restriction classification: According to the combination of ecological service function level and ecological sensitivity level within the red line area, three levels of management rules are defined, and the specific rules are as follows:

[0106] First-level control area (high function-low sensitivity area): All development activities are prohibited in this area, and only ecological research and monitoring are allowed;

[0107] Second-level control area (high function-medium sensitivity / medium function-low sensitivity area): Infrastructure construction is restricted in this area, and the construction of pollution-type industries is prohibited;

[0108] Third-level control area (medium function-medium sensitivity area): Moderate ecological tourism and low-intensity agricultural activities are allowed in this area, but large-scale development projects are prohibited.

[0109] S35, Red line area mapping and attribute association: Through GIS mapping technology, the finally delimited ecological protection red line area and its corresponding management rules are coded into vector layer, and detailed attribute table fields are associated, including: function level, sensitivity level, control type, area proportion, etc. Information. Finally, standard geographic information format files (such as GeoJSON, Shapefile, etc.) are generated, and red line area distribution map, management rule table and spatial conflict optimization report are output for decision-making and subsequent management.

[0110] S4 includes:

[0111] S41, Risk factor screening and quantification: Based on the divided ecological service function level and generated ecological sensitivity level, combined with the climate data, human activity distribution data and historical disaster records collected in S1, natural disaster factors (including flood frequency, landslide susceptibility index), climate change factors (including annual mean temperature change rate, extreme precipitation event probability) and human disturbance factors (including industrial pollution emission intensity, construction land expansion rate) are screened, and the risk values of each factor are quantified through GIS spatial analysis method;

[0112] Specifically, flood frequency is classified by the number of historical occurrences, pollution emission intensity is quantified by unit area pollutant emission, landslide susceptibility is calculated by factors such as slope and precipitation, and extreme precipitation event probability is calculated according to historical meteorological data;

[0113] S42, ecological risk model construction and weight distribution: through spatial overlay analysis method, the selected natural disaster, climate change and human disturbance factor layer and ecological service function level, ecological sensitivity level layer are weighted and overlaid, and the weight of each factor (natural disaster weight 0.35, climate change weight 0.30, human disturbance weight 0.35) is determined, the ecological risk index model is constructed, the comprehensive ecological risk index of each region is calculated, and the formula is as follows:

[0114] Ecological risk index = ∑ (factor value x weight);

[0115] The ecological risk index spatial distribution map of the target area is generated, and it is associated with the ecological unit spatial boundary.

[0116] S43, risk level division and dynamic threshold setting: according to the ecological risk index value, the natural breakpoint method is adopted to divide the target area into high risk area, medium risk area and low risk area, as follows:

[0117] High risk area (index ≥ 0.8);

[0118] Medium risk area (0.5 ≤ index < 0.8);

[0119] Low risk area (index < 0.5);

[0120] On this basis, the threshold is dynamically adjusted according to the ecological service function level, for example: for the area with high ecological function (such as water conservation area), the risk threshold is reduced by 20%, so as to improve the early warning sensitivity of the area and ensure timely discovery of risks;

[0121] S44, dynamic early warning mechanism design: based on real-time remote sensing image data, climate data and human activity data, a time series risk prediction model is established, the model dynamically calculates the ecological risk index change trend in the next 30 days, and according to the risk index, four levels of early warning signals and response strategies are set,

[0122] Red alert (index ≥ 0.8): extremely high risk, immediately start emergency response.

[0123] Orange alert (0.6 ≤ index < 0.8): higher risk, start some protection measures.

[0124] Yellow alert (0.4 ≤ index < 0.6): medium risk, enhance supervision and protection measures.

[0125] Blue alert (index < 0.4): low risk, maintain regular management.

[0126] And the early warning signal is associated with the emergency response strategy (such as suspending all development activities when the red alert is given), so as to ensure timely response.

[0127] S45, early warning output and feedback linkage: The generated risk level, early warning signal and response strategy are pushed in real time through the GIS management platform to generate an early warning report, which includes detailed information such as risk type, spatial location, and response measures. At the same time, the dynamic monitoring and adjustment mechanism of S5 is triggered to optimize and adjust the ecological protection red line boundary of high-risk areas, further reducing potential ecological risks.

[0128] S44 includes:

[0129] S441, data preprocessing and feature extraction: The collected real-time remote sensing image data is subjected to radiation correction and cloud mask processing, and vegetation index, land surface temperature and water body index are extracted. Climate data such as precipitation, wind speed and temperature are time-interpolated to fill in missing values, and spatially continuous raster data is generated. Human activity data such as construction land expansion range and pollution source points are converted into spatial resolution data matching the ecological risk index model to ensure consistent spatial resolution and time span for subsequent analysis and prediction.

[0130] S442, time series risk prediction model construction: Based on historical ecological risk index data and real-time monitoring data (real-time remote sensing image data, climate data and human activity data), a long short-term memory network is used to construct a time series risk prediction model. The input features of the model include the current risk index, vegetation index change rate, precipitation deviation and human activity intensity increment, and the output is the risk index prediction value for the next 30 days. The training data set is divided into training set, validation set and test set in the ratio of 7:2:1. Early stopping method is applied in the training process to prevent overfitting. The Adam optimizer is selected as the optimizer, and the mean square error is used as the loss function to ensure the stability and prediction accuracy of the model.

[0131] S443, dynamic early warning threshold adaptive adjustment: According to the division of ecological service function levels, different early warning thresholds are set. Specifically, the red early warning threshold for high-function areas is set to the value of the top 90% of historical risk index data, that is, if the current risk index reaches or exceeds the maximum value of the top 90% of past data, a red early warning is triggered. The red early warning threshold for medium-function areas is set to the value of the top 85% of historical risk index data, and the red early warning threshold for low-function areas is set to the value of the top 80% of historical risk index data. When real-time weather data triggers an extreme climate event (such as 24-hour precipitation exceeding 100 mm), the early warning threshold will temporarily decrease by 10% to improve the sensitivity of early warning, thereby ensuring timely response to sudden ecological risks.

[0132] S444, multi-level early warning signal generation and strategy binding: Based on the predicted risk index and the adaptively adjusted threshold, four levels of early warning signals are generated:

[0133] Red alert (≥ threshold value);

[0134] Orange alert (threshold value x 0.8 ≤ index < threshold value);

[0135] Yellow alert (threshold value x 0.6 ≤ index < threshold value x 0.8);

[0136] Blue alert (< threshold value x 0.6);

[0137] Each warning signal is bound to a corresponding emergency response strategy. For example, when the red alert is triggered, the "suspension of construction permit approval in the red line area" is triggered, and when the orange alert is triggered, the "pollution enterprises are limited to 50% production", and the specific strategy is managed through the GIS management platform, and can be manually revised and optimized according to real-time needs.

[0138] S445, warning visualization: superimpose the generated warning signal on the vector layer generated in S35, use heat map rendering to display the risk level distribution, and push it to the supervision terminal (including PC and mobile devices) in real time.

[0139] S5 includes:

[0140] S51, multi-source real-time data integration and feature coding: based on the collected real-time remote sensing images, climate data, and human activity distribution data, extract vegetation coverage change rate, surface temperature anomaly, construction land expansion rate, and pollution source distribution characteristics, at the same time, access the generated four-level risk warning signal, ecological service function level and ecological sensitivity level, and code them into a multi-dimensional feature vector that is spatiotemporally aligned, and input into the red line adjustment decision model;

[0141] S52, dynamic adjustment model construction and training: use a deep reinforcement learning framework to build a red line adjustment decision model, where the state space includes the current ecological service function level of the red line area, the risk warning level, and the human activity intensity, and the action space is the expansion, contraction or maintenance of the boundary (such as expanding 500 meters or contracting 200 meters). The reward function is calculated based on the weighted calculation of the ecological function improvement value and the risk reduction value (weight ratio 6:4). The model training uses historical adjustment records (≥3 years of data), and iteratively optimizes the strategy through the Q-learning algorithm until convergence, ensuring the ecological protection effect of the red line area.

[0142] S53, priority-driven adjustment strategy generation: according to the combination of risk warning level and ecological service function level, set the adjustment priority;

[0143] Red alert + high function area is the first priority (mandatory boundary expansion),

[0144] Orange alert + high function area is the second priority (recommended expansion),

[0145] Yellow warning + medium function area is three priority (local optimization).

[0146] And combined with the control rules of S34 (such as prohibition of contraction in the first control area), a candidate adjustment scheme set is generated, and the schemes conflicting with the control rules are eliminated;

[0147] S54, red line boundary space optimization and conflict resolution: GIS spatial analysis is performed on the candidate adjustment scheme set, and multi-objective genetic algorithm is used to optimize the red line boundary. The optimization objectives include: maximizing the connectivity of ecological corridors (calculated by landscape index MSPA), minimizing the conflict area with human activities (referring to S32 conflict area), maximizing the protection proportion of high function area (≥80%), and finally outputting a Pareto optimal solution set. After manual review, the optimal red line adjustment scheme is selected;

[0148] S55, adjustment effect feedback and model iteration: the optimal red line adjustment scheme is synchronized to the management platform in real time, and through the early warning feedback mechanism, the ecological risk index change and function level stability within 30 days after adjustment are monitored. If the risk does not decrease or the function level decreases, the model is retrained (update the reward function weight or expand the state feature), and the model parameters are iterated once a month and recorded to the spatio-temporal database, so as to form a closed loop mechanism of "monitoring → adjustment → verification → optimization".

[0149] The present application encompasses any substitution, modification, equivalent method and scheme made on the essence and scope of the present application. In order to make the public have a thorough understanding of the present application, specific details are described in the following preferred embodiments of the present application, and the present application can also be fully understood without the description of these details. In addition, in order to avoid unnecessary confusion to the essence of the present application, well-known methods, processes, procedures, elements and circuits are not described in detail.

[0150] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be regarded as the protection scope of the present application.

Claims

1. A method for demarcating ecological protection red lines for ecological basic surveys, characterized in that: The following steps are involved: S1. Collection of ecological basic data: Collect ecological basic data in the target area, including vegetation coverage, soil erosion intensity, surface water distribution, land use status data, climate data, human activity distribution data, historical disaster records and remote sensing image data, and perform spatial matching and standardization through geographic information system; S2, Ecological Function Assessment and Classification: Based on the collected ecological basic data, ecological models are used to assess the stability, ecological service function intensity and ecological sensitivity of ecological units, and to classify ecological service function levels and ecological sensitivity levels; S3, Regional Ecological Function Division and Redline Framework Design: Based on the ecological service function level and ecological sensitivity level, combined with the current land use situation and the boundaries of nature reserves, ecological protection redline areas are delineated, and protection objectives and development restriction types are clearly defined; S4, Ecological Risk Assessment and Early Warning: Based on the assessment results of S2, an ecological risk model will be constructed to assess the risks of natural disasters, climate change, and human interference within the redline area, and a dynamic early warning mechanism will be designed, including: S41, risk factor screening and quantification: Based on the divided ecological service function level and the generated ecological sensitivity level, combined with the climate data, human activity distribution data and historical disaster records collected in S1, natural disaster factors, climate change factors and human interference factors are screened, and the risk value of each factor is quantified through GIS spatial analysis methods; S42, Ecological Risk Model Construction and Weight Assignment: Using spatial overlay analysis, weighted overlays were performed on the selected natural disaster, climate change, and human disturbance factor layers with the ecological service function level and ecological sensitivity level layers. The weights of each factor were determined, and an ecological risk index model was constructed to calculate the comprehensive ecological risk index for each region. S43, Risk level classification and dynamic threshold setting: Based on the ecological risk index value, the target area is divided into high-risk area, medium-risk area and low-risk area using the natural breakpoint method; S44, Dynamic Early Warning Mechanism Design: Based on real-time remote sensing imagery data, climate data, and human activity data, a time series risk prediction model is established. The model dynamically calculates the trend of ecological risk index changes in the next 30 days and sets four levels of early warning signals and response strategies based on the risk index, including: S441, Data Preprocessing and Feature Extraction: Perform radiometric correction and cloud mask processing on collected real-time remote sensing image data, extract vegetation index, surface temperature, and water index, perform temporal interpolation on climate data, fill missing values, generate spatially continuous raster data, and convert human activity data into spatial resolution data that matches the ecological risk index model; S442, Time Series Risk Prediction Model Construction: Based on historical ecological risk index data and real-time monitoring data, a time series risk prediction model is constructed using a long-short-term memory network. The model input features include the current risk index, vegetation index change rate, precipitation deviation, and human activity intensity increment. The output is the risk index forecast value for the next 30 days. S443, adaptive adjustment of dynamic warning thresholds: setting differentiated warning thresholds based on the ecological service function levels; S444, Multi-level warning signal generation and policy binding: Generates four-level warning signals based on the predicted risk index and adaptively adjusted thresholds; S445, early warning visualization: The generated early warning signal is superimposed on the vector layer generated in S35, and the risk level distribution is displayed using heat map rendering, and pushed to the supervision terminal in real time; S45, early warning output and feedback linkage: The generated risk level, early warning signal and response strategy are pushed in real time through the GIS management platform to generate an early warning report. At the same time, the dynamic monitoring and adjustment mechanism described in S5 is triggered to prioritize the optimization and adjustment of the ecological protection red line boundaries in high-risk areas. S5, dynamic monitoring and adjustment mechanism: using the real-time ecological basic data of S1, through machine learning algorithms, combined with the ecological service function level and risk warning level, dynamically adjust the red line range in response to the risk warning results of S4.

2. The method for demarcating ecological protection red lines for ecological basic survey according to claim 1, characterized in that: Said S1 comprises: S11, Multi-source data acquisition and classification: Obtain multi-temporal and multi-spectral remote sensing image data of the target area through satellite remote sensing platforms; collect vegetation coverage, soil erosion intensity, surface water distribution, and climate data through ground monitoring stations; obtain current land use data through satellite remote sensing interpretation and land survey databases; obtain human activity distribution data through socioeconomic statistics databases and field surveys; and obtain historical disaster records through local disaster management department databases and historical remote sensing image inversion; S12, Data Preprocessing and Format Standardization: Perform radiometric correction, atmospheric correction, and geometric precision correction on remote sensing image data to generate standard false-color composite images; perform missing value filling, outlier removal, and time series smoothing on vegetation coverage, soil erosion intensity, surface water distribution, climate data, and human activity data, and convert them into a unified vector or raster format compatible with geographic information systems; S13, spatial reference system unification: All data are projected into the same geographic coordinate system and set to a unified spatial resolution, eliminating data scale differences through resampling, spatial interpolation, and vector-to-raster conversion; S14, Spatial matching and attribute association of ecological data: Overlay vegetation coverage, soil erosion intensity, surface water distribution, climate data, and human activity distribution data on the GIS platform, perform layer registration based on spatial location, establish an attribute association table, and achieve a one-to-one mapping between ecological parameters and geographic units; S15, data quality verification and integrated storage: ensure data accuracy through cross-validation and spatial consistency testing, and finally integrate the standardized ecological basic data into the database.

3. The method for demarcating ecological protection red lines for ecological basic survey according to claim 2 is characterized in that: The S2 ecological service function strength assessment includes: S21, quantification of ecological service function indicators: Based on the ecological basic data collected in S1, the water conservation module in the InVEST model is used to calculate the water conservation capacity, the net primary productivity carbon sink module in the CASA model is used to evaluate the carbon sink intensity, and the soil erosion modulus calculation module in the RUSLE equation is used to evaluate the soil conservation intensity; S22, functional intensity normalization and weight allocation: The calculated water conservation capacity, carbon sequestration intensity, and soil conservation intensity are normalized. The weight of each function is determined using the analytic hierarchy process combined with expert scoring. The normalized functional intensity values ​​are weighted and summed to obtain the comprehensive ecological service functional intensity value of each ecological unit. S23, service function level division: Based on the comprehensive ecological service function intensity value, the target area is divided into three levels: high, medium and low using the natural breakpoint method.

4. The method for demarcating ecological protection red lines for ecological basic survey according to claim 3 is characterized in that: The ecological sensitivity and stability assessment specifically includes: S24, screening and quantification of ecological sensitivity factors: Based on the ecological basic data collected in S1, terrain slope, vegetation coverage, soil erosion intensity, surface water proximity and human activity interference intensity were selected as ecological sensitivity factors, and the quantitative values ​​of ecological sensitivity factors were calculated using GIS spatial analysis methods; S25, Sensitivity Index Integration and Grading: Define the weights of each sensitivity factor, where the slope weight is 0.25, the vegetation cover weight is 0.30, the soil erosion intensity weight is 0.20, the surface water proximity weight is 0.15, and the human activity interference intensity weight is 0.

10. By weighted superposition of the quantitative values ​​of each factor, an ecological sensitivity index layer is generated, and the sensitivity index is divided into three levels: high, medium, and low using the equal spacing method; S26, Ecosystem Stability Assessment: Based on the ecological service function intensity level obtained in S23 and the ecological sensitivity level obtained in S25, an ecosystem stability matrix is ​​constructed, and the final ecosystem stability assessment result is output.

5. The method for demarcating ecological protection red lines for ecological basic survey according to claim 4 is characterized in that: The S3 includes: S31, Identification of Priority Ecological Protection Areas: Based on the ecological service function level and ecological sensitivity level, GIS spatial overlay analysis methods are used to screen "high function-low sensitivity" and "high function-medium sensitivity" areas as priority protection areas. In combination with the boundaries of existing nature reserves, preliminary candidate ecological protection red line areas are delineated. S32, Land Use Conflict Analysis and Boundary Optimization: Perform spatial overlay analysis on the current land use data collected in S1 and the candidate redline areas to identify areas with human activity conflicts, adjust the conflicting areas, and optimize the boundaries of the affected areas using the principle of ecological function priority; S33, fusion and expansion of protected area boundaries: spatially integrate the existing nature reserve boundaries with the optimized red line candidate areas, and analyze whether there are areas with high ecological service functions outside the nature reserve that have not been included; S34, Protection Objectives and Development Restriction Classification: Define three levels of control rules based on the combination of ecological service function level and ecological sensitivity level within the redline area; S35, red line area mapping and attribute association: Using GIS mapping technology, the final ecological protection red line area and its corresponding management and control rules are encoded into a vector layer and associated with the attribute table fields.

6. The method for demarcating ecological protection red lines for ecological basic survey according to claim 5 is characterized in that: The S5 includes: S51, Multi-source Real-time Data Integration and Feature Coding: Based on collected real-time remote sensing images, climate data, and human activity distribution data, the vegetation cover change rate, surface temperature anomalies, construction land expansion rate, and pollution source distribution characteristics are extracted. At the same time, the generated four-level risk warning signals, ecological service function levels, and ecological sensitivity levels are integrated and encoded into a spatiotemporally aligned multidimensional feature vector for input into the redline adjustment decision model. S52, Dynamic Adjustment Model Construction and Training: Using a deep reinforcement learning framework to build a redline adjustment decision model; S53, priority-driven adjustment strategy generation: Based on the combination of risk warning level and ecological service function level, adjustment priorities are set, and combined with the control rules of S34, a set of candidate adjustment plans is generated, and plans that conflict with the control rules are eliminated; S54, Spatial Optimization and Conflict Resolution of Redline Boundaries: GIS spatial analysis is performed on a set of candidate adjustment solutions. A multi-objective genetic algorithm is used to optimize the redline boundaries. The optimization objectives include maximizing the connectivity of ecological corridors, minimizing the area of ​​conflict with human activities, and maximizing the proportion of high-function areas protected. The Pareto optimal solution set is ultimately output, and the optimal redline adjustment solution is selected after manual review. S55, adjustment effect feedback and model iteration: synchronize the optimal red line adjustment plan to the management platform in real time, and monitor the changes in the ecological risk index and the stability of the functional level within 30 days after the adjustment through the early warning feedback mechanism.

Images