Ecological protection and restoration planning method and system

Abstract

The application discloses an ecological protection and restoration planning method and system, and the method comprises the following steps: acquiring ecological multi-source data of a target region, performing spatial registration and format standardization processing through a geographic information system; constructing a three-dimensional ecological background model, and generating a gridded geographic unit by fusing the ecological multi-source data; performing dynamic coupling analysis on the ecological multi-source data by using a convolutional neural network, identifying an ecological degradation hotspot region, and outputting a spatial probability distribution map; based on the spatial probability distribution of the ecological degradation hotspot region and the ecological background model, generating a multi-level ecological restoration scheme through a self-organizing feature mapping neural network, and outputting a visual planning atlas. The scheme disclosed by the application improves the accuracy and efficiency of ecological assessment, reduces the economic cost of regional ecological protection and restoration, improves the efficiency, and can achieve good expected effects through tests, and has a good popularization prospect.

Description

Technical Field

[0001] This application relates to the field of intelligent environmental data processing technology, and in particular to a method and system for ecological protection and restoration planning. Background Technology

[0002] With the increasing degradation of the global ecological environment, existing ecological protection and restoration plans have the following limitations. First, traditional methods rely on single remote sensing or field survey data (such as NDVI or soil sampling), failing to integrate multi-source heterogeneous data such as high-resolution remote sensing, DEM, meteorological dynamics, and human activities, resulting in one-sided and biased ecological assessment results. For example, in soil erosion analysis, the urban expansion and its resulting land use pressure reflected by nighttime light data are often overlooked, leading to insufficient understanding of the driving mechanisms of soil erosion, which in turn affects the pertinence and effectiveness of restoration plans. The urban expansion pressure revealed by nighttime light data is often ignored, causing restoration plans to deviate from the actual driving mechanisms. Second, although GIS platforms (such as ArcGIS) can achieve spatial overlay analysis, they rely on manually set weight thresholds, making it difficult to dynamically couple the nonlinear relationships between ecological factors. For example, bio-corridor planning often employs minimum-cost path models, failing to integrate technologies like neural networks to optimize topology. This results in low connectivity efficiency for the planned corridors, and the actual economic cost of the final solution far exceeds expectations. Third, existing schemes mostly output static restoration zoning maps, lacking quantitative predictions of the long-term evolution of key ecosystem processes (such as carbon sequestration potential, water conservation, and biodiversity maintenance) under dynamic environments after implementation. For instance, if forest vegetation restoration projects are based solely on current soil conditions, neglecting to incorporate future climate scenario simulations to assess key dynamic indicators such as long-term carbon sequestration potential, it becomes difficult to ensure the sustainability of the selected vegetation and configuration schemes under future climate conditions. This could lead to instability and insufficient adaptability of the core ecological functions of the restoration project.

[0003] Current research attempts to incorporate machine learning, such as CNNs, for land cover classification, but a closed-loop, end-to-end technical system encompassing "multi-source data fusion → intelligent diagnosis → adaptive scheme generation → dynamic effect prediction" has not yet been established. Therefore, there is an urgent need to develop an ecological protection planning method that integrates geographic information and intelligent environmental data processing technologies to achieve scientific decision-making and dynamic optimization for ecological protection and restoration. Summary of the Invention

[0004] This application provides an ecological protection and restoration planning method and system to solve the above-mentioned problems.

[0005] On the one hand, this application provides a method for ecological protection and restoration planning, the method comprising the following steps:

[0006] Step S1: Obtain multi-source ecological data of the target area and perform spatial registration and format standardization processing through a geographic information system;

[0007] Step S2: Construct a three-dimensional ecological baseline model and integrate the multi-source ecological data to generate gridded geographic units;

[0008] Step S3: Use a convolutional neural network to perform dynamic coupling analysis on the ecological multi-source data, identify ecological degradation hotspots, and output a spatial probability distribution map;

[0009] Step S4: Based on the spatial probability distribution of the ecological degradation hotspots and the ecological baseline model, a multi-level ecological restoration scheme is generated through a self-organizing feature mapping neural network, and a visual planning map is output.

[0010] In one implementation of this application, the ecological multi-source data includes, but is not limited to: high-resolution remote sensing images, digital elevation models, soil type distribution maps, vegetation cover index time series, meteorological monitoring data, and spatial data on human activity intensity.

[0011] In one implementation of this application, in step S3, the dynamic coupling analysis uses the entropy weight-TOPSIS comprehensive assessment model to calculate the ecological vulnerability index. The process is as follows:

[0012]

[0013] in, i For geographical unit numbering; w j The entropy weight of the j-th evaluation indicator is calculated using the indicator variability. This represents the distance between element j and the positive ideal solution; The distance between element j and the negative ideal solution is represented by the evaluation index set, which includes: vegetation cover attenuation rate, soil organic matter loss, topographic resistance factor γ, and rainstorm erosion force R.

[0014] In one implementation of this application, the formula for calculating the terrain resistance factor γ is as follows:

[0015] γ=ΔH / ΔL

[0016] Where ΔH is the elevation range within the grid, ΔL is the length of the grid diagonal, and the surface roughness is extracted from the texture features of remote sensing images.

[0017] In one implementation of this application, the input layer of the self-organizing feature mapping neural network includes an ecological vulnerability index, the cost of species migration path resistance, the economic cost of restoration measures, and a climate suitability score, and the topological structure of the output layer neurons corresponds to the spatiotemporal configuration matrix of the restoration scheme.

[0018] In one implementation of this application, in step S4, the multi-level ecological restoration scheme includes vegetation restoration priority zoning, engineering measure layout, and ecological corridor topology. The ecological corridor topology is generated through an improved ant colony algorithm, and a simulated annealing mechanism is added during algorithm iteration to avoid local optima. The path fitness function is:

[0019]

[0020] Among them, C k The ecological resistance value C of the k-th segment of the corridor is determined by the land use type and slope. k The calculation incorporates the vegetation cover buffering effect: when the corridor traverses a forested area, C k Multiply by a preset attenuation coefficient; when traversing urban built-up areas, C k Multiply by a preset magnification factor; Connectivity is the number of biological habitats connected by the corridor; Construction_cost is the construction cost of the ecological corridor; α , β , δ These are the weighting coefficients, and α + β + δ =1.

[0021] In one implementation of this application, the spatial data of human activity intensity is obtained by spatiotemporal overlay analysis of nighttime light remote sensing data, traffic network density, and land use change trajectory, and its spatial resolution matches that of the high-resolution remote sensing image.

[0022] In one implementation of this application, in step S2, the size of the gridded geographic units is dynamically graded according to the geomorphic features, and different grid scales are used for areas with different terrain complexities. The grid attribute data is spatially filled using the Kriging interpolation method.

[0023] In one implementation of this application, the method further includes: generating a dynamic prediction model for the implementation effect of the remediation plan, specifically:

[0024] The planning scheme is input into the Long Short-Term Memory Network and combined with climate scenario simulation data to output the ecosystem stability change curve and carbon sink increment spatial distribution map for the next 10 years.

[0025] On the other hand, this application also provides an ecological protection and restoration planning system, the system comprising:

[0026] The data preprocessing module is used to acquire multi-source ecological data of the target area and perform spatial registration and format standardization processing through a geographic information system.

[0027] The multi-source data fusion module is used to construct a three-dimensional ecological baseline model and to generate gridded geographic units by fusing the multi-source ecological data.

[0028] The coupling analysis module is used to perform dynamic coupling analysis on the ecological multi-source data using a convolutional neural network, identify ecological degradation hotspots, and output a spatial probability distribution map.

[0029] The scheme output module is used to generate multi-level ecological restoration schemes based on the spatial probability distribution of the ecological degradation hotspots and the ecological baseline model, and output a visualized planning map.

[0030] The ecological protection and restoration planning method and system provided in this application have the following beneficial effects:

[0031] (1) Improved the accuracy and efficiency of ecological assessment. Through the fusion of multi-source data and the construction of gridded geographic units, the three-dimensional coupling analysis of factors such as vegetation, topography and human activities was realized, which solved the one-sidedness of traditional single-source data assessment. Combined with CNN dynamic coupling to identify degraded areas, the data processing efficiency was improved and more accurate predictions were achieved.

[0032] (2) A multi-level scheme is generated by SOFM neural network, and the ecological corridor topology is optimized based on the improved ant colony algorithm. The ecological connectivity and construction cost are dynamically balanced by the path fitness function, so as to reduce the economic cost of ecological corridor planning and construction.

[0033] (3) An LSTM prediction model is introduced to simulate the long-term effects of ecological restoration schemes under climate scenarios, outputting stability curves and carbon sink increments, supporting dynamic adjustment strategies. Compared with traditional static planning, this improves the ecosystem restoration achievement rate over the next 10 years and enhances the ability to respond to extreme climate events. Attached Figure Description

[0034] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0035] Figure 1 A flowchart illustrating an ecological protection and restoration planning method provided in this application embodiment;

[0036] Figure 2 This is a diagram illustrating the composition of an ecological protection and restoration planning system provided in an embodiment of this application. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0038] This application provides an ecological protection and restoration planning method and system. The technical solutions proposed in this application will be described in detail below with reference to the accompanying drawings.

[0039] Figure 1 This is a flowchart illustrating an ecological protection and restoration planning method provided in an embodiment of this application. Figure 1 As shown, the method mainly includes the following steps:

[0040] Step S1: Obtain multi-source ecological data of the target area and perform spatial registration and format standardization processing through a geographic information system;

[0041] Step S2: Construct a three-dimensional ecological baseline model and integrate the multi-source ecological data to generate gridded geographic units;

[0042] Step S3: Use a convolutional neural network to perform dynamic coupling analysis on the ecological multi-source data, identify ecological degradation hotspots, and output a spatial probability distribution map;

[0043] Step S4: Based on the spatial probability distribution of the ecological degradation hotspots and the ecological baseline model, a multi-level ecological restoration scheme is generated through a self-organizing feature mapping neural network, and a visual planning map is output.

[0044] In this application embodiment, the ecological multi-source data includes, but is not limited to: high-resolution remote sensing images, digital elevation models, soil type distribution maps, vegetation cover index time series, meteorological monitoring data, and spatial data on human activity intensity.

[0045] In this embodiment of the application, in step S3, the dynamic coupling analysis uses the entropy weight-TOPSIS comprehensive assessment model to calculate the ecological vulnerability index. The process is as follows:

[0046]

[0047] in, i For geographical unit numbering; w j The entropy weight of the j-th evaluation indicator is calculated using the indicator variability. This represents the distance between element j and the positive ideal solution; The distance between element j and the negative ideal solution is represented by the evaluation index set, which includes: vegetation cover attenuation rate, soil organic matter loss, topographic resistance factor γ, and rainstorm erosion force R.

[0048] In this embodiment of the application, the formula for calculating the terrain resistance factor γ is as follows:

[0049] γ=ΔH / ΔL

[0050] Where ΔH is the elevation range within the grid, ΔL is the length of the grid diagonal, and the surface roughness is extracted from the texture features of remote sensing images.

[0051] In this embodiment, the input layer of the self-organizing feature mapping neural network includes an ecological vulnerability index, the cost of species migration path resistance, the economic cost of restoration measures, and a climate suitability score, while the topological structure of the output layer neurons corresponds to the spatiotemporal configuration matrix of the restoration scheme.

[0052] In this embodiment of the application, step S4 includes a multi-level ecological restoration scheme comprising vegetation restoration priority zoning, engineering measure layout, and ecological corridor topology. The ecological corridor topology is generated through an improved ant colony algorithm, with simulated annealing incorporated into the algorithm iteration to avoid local optima. The path fitness function is:

[0053]

[0054] Among them, C k The ecological resistance value C of the k-th segment of the corridor is determined by the land use type and slope. k The calculation incorporates the vegetation cover buffering effect: when the corridor traverses a forested area, C k Multiply by a preset attenuation coefficient; when traversing urban built-up areas, C k Multiply by a preset magnification factor; Connectivity is the number of biological habitats connected by the corridor; Construction_cost is the construction cost of the ecological corridor; α , β , δ These are the weighting coefficients, and α + β + δ =1.

[0055] In this embodiment of the application, the spatial data of human activity intensity is obtained by spatiotemporal overlay analysis of nighttime light remote sensing data, traffic network density and land use change trajectory, and its spatial resolution matches that of the high-resolution remote sensing image.

[0056] In this embodiment of the application, in step S2, the size of the gridded geographic unit is dynamically graded according to the geomorphic features, and different grid scales are used for areas with different terrain complexities. The grid attribute data is spatially filled by Kriging interpolation.

[0057] In this embodiment of the application, the method further includes: generating a dynamic prediction model for the implementation effect of the remediation plan, specifically:

[0058] The planning scheme is input into the Long Short-Term Memory Network and combined with climate scenario simulation data to output the ecosystem stability change curve and carbon sink increment spatial distribution map for the next 10 years.

[0059] The above describes an ecological protection and restoration planning method provided by an embodiment of this application. Based on the same inventive concept, this application also provides an ecological protection and restoration planning system. Figure 2 A diagram illustrating the composition of an ecological protection and restoration planning system provided in this application embodiment is shown below. Figure 2 As shown, the system mainly includes: a data preprocessing module 201, used to acquire ecological multi-source data of the target area and perform spatial registration and format standardization processing through a geographic information system;

[0060] Multi-source data fusion module 202 is used to construct a three-dimensional ecological baseline model and fuse the ecological multi-source data to generate gridded geographic units;

[0061] The coupling analysis module 203 is used to perform dynamic coupling analysis on the ecological multi-source data using a convolutional neural network, identify ecological degradation hotspots, and output a spatial probability distribution map.

[0062] The scheme output module 204 is used to generate a multi-level ecological restoration scheme based on the spatial probability distribution of the ecological degradation hotspot area and the ecological baseline model, and output a visualized planning map.

[0063] The following examples demonstrate the application scenarios of the methods provided in this application.

[0064] The following problems existed in the ecological restoration and protection of a certain region in the past: (1) Severe soil erosion: 68% of the beach area was sandy soil, with an average annual sediment loss of 12,000 tons / square kilometer; (2) Disruption of biological connectivity: Human activities (farmland / urban expansion) led to habitat fragmentation, and wetland bird habitats were reduced by 40%; (3) Static restoration plan: Traditional GIS planning did not couple climate and economic factors, and the carbon sequestration increment prediction error was >35% after the implementation of projects such as Japanese knotweed planting. The specific plan provided in this application has achieved good ecological protection and restoration results. The specific planning process is as follows:

[0065] 1. Multi-source data fusion and ecological baseline modeling

[0066] Data Acquisition: Collect 0.5-meter resolution remote sensing images, 30-meter DEM, soil salinity distribution map, NDVI time series from 2015 to 2024, rainfall intensity data for the past 10 years (maximum daily rainfall of 120 mm), and human activity data such as nighttime light index (annual average increase of 8.3%) and road network density (estimated to reach 4.2 km / km² in 2025).

[0067] Spatial registration: The GIS platform uniformly projects the coordinate system to CGCS2000. Grid cell sizes are based on terrain levels: 50m × 50m for sandy beach areas (high erosion risk zone); and 100m × 100m for dike areas (low-lying areas). Some grid attributes are shown in Table 1 below.

[0068] Table 1. Mesh Attribute Table (Partial)

[0069]

[0070] 2. CNN Degradation Recognition and Entropy Weight-TOPSIS Evaluation

[0071] Dynamic coupling analysis: Input grid attributes into the ResNet-50 model to identify soil erosion hotspots (concentrated in the central part of the beach area, accounting for 32% of the area) and biodiversity loss areas (wetland edges, connectivity index < 0.4).

[0072] Ecological Vulnerability Index (EVI) calculation:

[0073] EVI i =0.32× (Vegetation attenuation) + 0.28 × (soil loss) + 0.25 × γ (topographic resistance) + 0.15 × R (rainstorm erosion), where the topographic resistance factor γ is corrected by the root coverage of Polygonum cuspidatum in the beach area (γ is 0.6 when the measured root density is >15,000 plants / acre), and the output shows that the highly vulnerable area (EVI>0.7) accounts for 41% of the entire area.

[0074] 3. Generation of Self-Organizing Feature Map (SOFM) Scheme via Neural Network

[0075] Input layer parameters: Ecological resistance: resistance value of sandy beach area = 8.0, forest land = 2.5; Economic cost: 1200 yuan / mu for planting Japanese knotweed, 3500 yuan / mu for arbor forest belt; Climate suitability: based on RCP4.5 scenario score (0~1).

[0076] Output layer optimization scheme: (1) Vegetation restoration zone: Priority I zone (EVI>0.7): plant Japanese knotweed (sand fixation) + salt-tolerant shrubs (Tamarix); Priority II zone (0.5<EVI≤0.7): mixed forest (Fraxinus chinensis + Juniperus chinensis).

[0077] Ecological corridor topology: Based on an improved ant colony algorithm, connecting 6 wetland patches: path fitness function weights: α=0.5 (ecological connectivity), β=0.3 (number of habitats), δ=0.2 (construction cost); Urban crossing section: C K =2.5 (preset magnification factor), bypassing the newly added wetland buffer zone, crossing the woodland section: C K =0.6 (preset attenuation coefficient), shortening the path by 12km.

[0078] 4. Dynamic prediction using Long Short-Term Memory (LSTM) networks

[0079] Input the remediation plan into the LSTM model to simulate the effects over the next ten years from 2026 to 2035. Climate data: IPCCRCP4.5 scenario (annual mean temperature +1.2℃, rainfall variability coefficient +15%). Output: Carbon sink increment in 2035: 86,000 tons. Ecosystem stability index increased from 0.62 to 0.81.

[0080] In this example, the multimodal data fusion module uses the M300 RTK UAV + Sentinel-2 satellite data interface, the GPU computing engine uses NVIDIA A100×4 (which can process 500,000 grid cells in parallel), and the visualization terminal uses a 3D electronic sand table (1:1000 scale).

[0081] In summary, this example demonstrates the significant application value of the technical solution provided in this application within complex ecological scenarios. Firstly, the multi-source data gridding coupled with CNN analysis addresses the issue of biased ecological assessments (e.g., improving the accuracy of site selection for Polygonum cuspidatum planting areas to 92%). Secondly, the improved ant colony algorithm balances economic costs and ecological benefits (reducing corridor construction costs by 28.6%). Thirdly, LSTM integration of climate scenarios supports long-term restoration decisions (carbon sink prediction error <10%). The solution system provided in this application can be extended to counties (cities, districts) along the Yellow River, providing a standardized technical paradigm for the construction of ecological corridors along the Yellow River.

[0082] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0083] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0084] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for ecological protection and restoration planning, characterized in that, The method includes the following steps: Step S1: Obtain multi-source ecological data of the target area and perform spatial registration and format standardization processing through a geographic information system; Step S2: Construct a three-dimensional ecological baseline model and integrate the multi-source ecological data to generate gridded geographic units. The size of each gridded geographic unit is dynamically graded based on geomorphic features, with differentiated grid scales used for areas of varying terrain complexity. Grid attribute data is spatially filled using Kriging interpolation. Dynamic coupling analysis employs the entropy-weighted TOPSIS comprehensive assessment model to calculate the ecological vulnerability index. The process is as follows: in, i For geographical unit numbering; w j The entropy weight of the j-th evaluation indicator is calculated using the indicator variability. This represents the distance between element j and the positive ideal solution; This represents the distance between element j and the negative ideal solution; the evaluation index set includes: vegetation cover attenuation rate, soil organic matter loss, topographic resistance factor γ, and rainstorm erosion force R; the calculation formula for the topographic resistance factor γ is as follows: γ = ΔH / ΔL; Where ΔH is the elevation range within the grid, ΔL is the grid diagonal length, and the surface roughness is extracted from the texture features of remote sensing images; Step S3: Use a convolutional neural network to perform dynamic coupling analysis on the ecological multi-source data, identify ecological degradation hotspots, and output a spatial probability distribution map; Step S4: Based on the spatial probability distribution of the ecological degradation hotspots and the ecological baseline model, a multi-level ecological restoration scheme is generated using a self-organizing feature mapping neural network, and a visualized planning map is output. The multi-level ecological restoration scheme includes vegetation restoration priority zoning, engineering measure layout, and ecological corridor topology. The ecological corridor topology is generated through an improved ant colony algorithm, and a simulated annealing mechanism is added during algorithm iteration to avoid local optima. The path fitness function is: Among them, C k The ecological resistance value C of the k-th segment of the corridor is determined by the land use type and slope. k The calculation incorporates the vegetation cover buffering effect: when the corridor traverses a forested area, C k Multiply by a preset attenuation coefficient; when traversing urban built-up areas, C k Multiply by a preset magnification factor; Connectivity is the number of biological habitats connected by the corridor; Construction_cost is the construction cost of the ecological corridor; α , β , δ These are the weighting coefficients, and α + β + δ =1.

2. The ecological protection and restoration planning method according to claim 1, characterized in that, The ecological multi-source data includes, but is not limited to: high-resolution remote sensing images, digital elevation models, soil type distribution maps, vegetation cover index time series, meteorological monitoring data, and spatial data on human activity intensity.

3. The ecological protection and restoration planning method according to claim 1, characterized in that, The input layer of the self-organizing feature mapping neural network includes an ecological vulnerability index, the cost of species migration path resistance, the economic cost of restoration measures, and a climate suitability score. The topological structure of the output layer neurons corresponds to the spatiotemporal configuration matrix of the restoration scheme.

4. The ecological protection and restoration planning method according to claim 2, characterized in that, The spatial data on human activity intensity was obtained through spatiotemporal overlay analysis of nighttime light remote sensing data, traffic network density, and land use change trajectories, and its spatial resolution matched that of the high-resolution remote sensing image.

5. The ecological protection and restoration planning method according to claim 1, characterized in that, The method further includes: generating a dynamic prediction model for the implementation effect of the remediation plan, specifically: The planning scheme is input into the Long Short-Term Memory Network and combined with climate scenario simulation data to output the ecosystem stability change curve and carbon sink increment spatial distribution map for the next 10 years.

6. An ecological protection and restoration planning system, applied to the ecological protection and restoration planning method described in claim 1, characterized in that, The system includes: The data preprocessing module is used to acquire multi-source ecological data of the target area and perform spatial registration and format standardization processing through a geographic information system. The multi-source data fusion module is used to construct a three-dimensional ecological baseline model and to generate gridded geographic units by fusing the multi-source ecological data. The coupling analysis module is used to perform dynamic coupling analysis on the ecological multi-source data using a convolutional neural network, identify ecological degradation hotspots, and output a spatial probability distribution map. The scheme output module is used to generate multi-level ecological restoration schemes based on the spatial probability distribution of the ecological degradation hotspots and the ecological baseline model, and output a visualized planning map.

Images