A method for evaluating ecological restoration effects based on big data

Abstract

The present invention relates to the field of ecological restoration technology, specifically a big data-based ecological restoration effectiveness assessment method. The method comprises inputting ecological feature vectors into a pre-trained ecological restoration effectiveness assessment model to obtain an ecological restoration assessment result; constructing a three-dimensional virtual scene of the ecological restoration area based on digital twin technology to obtain an ecological restoration heat map of the three-dimensional virtual scene; obtaining restoration nodes based on the ecological restoration heat map to obtain optimized ecological element data for the restoration nodes; and obtaining an optimized ecological restoration assessment result for the restoration nodes based on the optimized ecological element data; and comparing the optimized ecological restoration assessment result with a preset ecological restoration assessment result threshold to obtain an optimized ecological restoration solution. By evaluating ecological feature vectors using the ecological restoration effectiveness assessment model, the present invention can provide a more scientific and systematic assessment result, making the assessment result more credible.

Description

Technical Field

[0001] The present invention relates to the field of ecological restoration technology, and in particular to an ecological restoration effect evaluation method based on big data. Background Art

[0002] Traditional methods often rely on manual observation and expert judgment, and are easily affected by the experience, judgment and subjective views of the assessors, resulting in inconsistency and deviation in the results, and the credibility of the evaluation results is not high; traditional methods often rely on manually collected ecological data, lack a real-time update mechanism, and cannot reflect changes in the ecological restoration process in real time; the restoration assessment results of traditional methods are generally obtained after periodic assessments, and subsequent adjustments are often not flexible enough, and the restoration plan cannot be adjusted in time; traditional methods may feedback the assessment results through text reports or static charts, which lack intuitive visual expression; the adjustment of restoration nodes in traditional methods is often performed manually, which is inefficient and difficult to track. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to overcome the shortcomings of the above-mentioned prior art and provide an ecological restoration effect evaluation method based on big data.

[0004] The technical solution adopted to solve the above technical problems is: a method for evaluating ecological restoration effects based on big data, including:

[0005] Collecting ecological factor data of the ecological restoration area, and performing feature extraction on the ecological factor data to obtain ecological feature vectors corresponding to the ecological factor data;

[0006] Inputting the ecological feature vector into a pre-trained ecological restoration effect evaluation model to obtain an ecological restoration evaluation result;

[0007] Constructing a three-dimensional virtual scene of the ecological restoration area based on digital twin technology, and mapping the ecological restoration assessment results to corresponding geographic coordinates of the three-dimensional virtual scene to obtain an ecological restoration heat map of the three-dimensional virtual scene;

[0008] Obtaining a restoration node based on the ecological restoration heat map, optimizing and adjusting the ecological restoration project of the restoration node to obtain optimized ecological factor data of the restoration node, and obtaining an optimized ecological restoration assessment result of the restoration node based on the optimized ecological factor data;

[0009] The optimized ecological restoration assessment result is compared with a preset ecological restoration assessment result threshold to obtain a degree of deviation between the two, and the ecological restoration project is iteratively optimized based on the degree of deviation to obtain an ecological restoration effect assessment report and an ecological restoration optimization plan.

[0010] Preferably, feature extraction is performed on the ecological element data to obtain an ecological feature vector corresponding to the ecological element data, including:

[0011] Performing standardization processing on the ecological factor data to obtain ecological factor standardized data corresponding to the ecological factor data;

[0012] Time series feature extraction is performed on the ecological element standardized data to obtain an ecological feature vector corresponding to the ecological element data.

[0013] Preferably, the ecological restoration effect evaluation model adopts a fusion architecture of long short-term memory network and graph convolutional network, takes the ecological feature vector as input, and outputs the ecological restoration evaluation result of the ecological restoration area.

[0014] Preferably, the three-dimensional virtual scene of the ecological restoration area is constructed based on digital twin technology, including:

[0015] Obtaining geographic data of the ecological restoration area;

[0016] Performing three-dimensional modeling of the ecological restoration area based on the geographic data and the ecological element data to obtain a three-dimensional digital model of the ecological restoration area;

[0017] The three-dimensional digital model is visualized in a three-dimensional virtual scene based on digital twin technology to obtain the three-dimensional virtual scene.

[0018] Preferably, mapping the ecological restoration assessment results to the corresponding geographic coordinates of the three-dimensional virtual scene to obtain an ecological restoration heat map of the three-dimensional virtual scene includes:

[0019] Matching the ecological restoration assessment result with the corresponding geographic coordinates of the three-dimensional virtual scene to obtain a virtual ecological restoration assessment result of the three-dimensional virtual scene corresponding to the ecological restoration area;

[0020] Color mapping is performed on the virtual ecological restoration assessment results to obtain a color gradient heat map, thereby obtaining an ecological restoration heat map of the three-dimensional virtual scene.

[0021] Preferably, color mapping is performed on the virtual ecological restoration assessment results to obtain a color gradient heat map, including:

[0022] Mapping the ecological restoration assessment result threshold to green;

[0023] The virtual ecological restoration assessment result is compared with the ecological restoration assessment result threshold. If the virtual ecological restoration assessment result is close to the ecological restoration assessment result threshold, the color is close to green to obtain the thermal map with a color gradient.

[0024] Preferably, obtaining restoration nodes based on the ecological restoration heat map includes:

[0025] Obtaining nodes of the ecological restoration heat map whose colors are non-green;

[0026] The node is used as the repair node.

[0027] Preferably, the ecological restoration project is used to improve the ecological elements of the ecological restoration area to achieve the purpose of ecological restoration.

[0028] Preferably, the optimized ecological restoration assessment result is compared with a preset ecological restoration assessment result threshold to obtain a degree of deviation between the two, including:

[0029] The indicators of different areas corresponding to the optimized ecological restoration assessment results are weighted.

[0030] To obtain evaluation results with different weights;

[0031] The assessment results are compared with the threshold values ​​of the ecological restoration assessment results in a temporal and spatial manner to obtain the degree of deviation between the two in different regions.

[0032] Preferably, the ecological restoration project is iteratively optimized based on the deviation to obtain an ecological restoration effect evaluation report and an ecological restoration optimization plan, including:

[0033] Obtaining the ecological restoration effect evaluation report of the entire ecological restoration area based on the deviation;

[0034] Based on the deviation degree, the restoration measures of some areas of the ecological restoration project are optimized so that the overall ecological restoration result of the ecological restoration area can reach the ecological restoration assessment result threshold to obtain the ecological restoration optimization plan.

[0035] The beneficial effects of the present invention are as follows: (1) The present invention can accurately obtain detailed information of the ecological restoration area by collecting ecological element data and performing feature extraction, thereby obtaining more accurate evaluation results; (2) The present invention evaluates the ecological feature vector through the ecological restoration effect evaluation model, which can provide a more scientific and systematic evaluation result, making the evaluation result more credible; (3) The present invention constructs a three-dimensional virtual scene through digital twins and maps the restoration evaluation results to a heat map, making the evaluation results more intuitive, and being able to clearly see the restoration effect of each area, and accurately optimize the restoration measures based on the data in the heat map; (4) The present invention can not only optimize after the evaluation by dynamically adjusting the restoration nodes, but also continuously improve during the restoration process, thereby improving the ecological restoration effect; (5) The present invention can make real-time and fine-tuned adjustments to the restoration plan through the restoration nodes and the optimized ecological element data, making the ecological restoration optimization plan more accurate and timely. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic flow chart of the steps of the overall method in one embodiment of the present invention; DETAILED DESCRIPTION

[0037] Example 1, as Figure 1 As shown, the present invention proposes an ecological restoration effect evaluation method based on big data, including:

[0038] S1. Collect ecological factor data of the ecological restoration area and perform feature extraction on the ecological factor data to obtain ecological feature vectors corresponding to the ecological factor data;

[0039] S2. Input the ecological feature vector into the pre-trained ecological restoration effect evaluation model to obtain the ecological restoration evaluation result;

[0040] S3. Construct a three-dimensional virtual scene of the ecological restoration area based on digital twin technology, and map the ecological restoration assessment results to the corresponding geographic coordinates of the three-dimensional virtual scene to obtain an ecological restoration heat map of the three-dimensional virtual scene;

[0041] S4. Obtain restoration nodes based on the ecological restoration heat map, optimize and adjust the ecological restoration projects at the restoration nodes to obtain optimized ecological factor data for the restoration nodes, and obtain optimized ecological restoration assessment results for the restoration nodes based on the optimized ecological factor data;

[0042] S5. Compare the optimized ecological restoration assessment result with a preset ecological restoration assessment result threshold to obtain a deviation between the two, and iteratively optimize the ecological restoration project based on the deviation to obtain an ecological restoration effect evaluation report and an ecological restoration optimization plan.

[0043] In the present invention, ecological element data refers to the data of various components of the ecological environment, including air quality, water quality, soil quality, plant cover, species diversity, etc., which can reflect the state of the ecosystem; feature extraction refers to the extraction of key information or features that can represent the essence of the data from the original data through a certain algorithm or technology in data processing. In ecological restoration, feature extraction is the extraction of effective features from ecological element data for subsequent analysis; ecological feature vector refers to a vector representation obtained after feature extraction, which contains the characteristic information of ecological elements and is used to describe the state or change of the ecological environment; ecological restoration effect evaluation model refers to the prediction or judgment of whether the restoration measures are effective by evaluating the ecological restoration process and results. The model is trained with historical ecological element data and can output the evaluation results of the ecological restoration effect; digital twin technology refers to the construction of a virtual model that is highly consistent with the real-world physical system through digital means to reflect and simulate the state of the real world in real time. In ecological restoration, digital twin technology can construct a virtual three-dimensional scene of the ecological restoration area for visual analysis of the restoration effect; three-dimensional virtual scene refers to a three-dimensional environment simulated from the real world created based on digital twin technology. This scene can display the ecological restoration effect. The ecological restoration heat map is a visualization tool that maps the ecological restoration assessment results to the geographic coordinates of a three-dimensional virtual scene. The resulting heat map can clearly show the strength of the ecological restoration effect in each area, with the depth of color representing the quality of the restoration effect. Restoration nodes refer to areas where the ideal restoration effect has not been achieved during the ecological restoration process and require optimized restoration measures to achieve the ideal restoration effect. Ecological restoration projects refer to various projects carried out to improve and restore the ecological environment, including restoration measures such as vegetation restoration, soil and water conservation, and pollution control. Optimizing ecological factor data refers to adjusting and optimizing ecological factor data based on the actual conditions of the restoration nodes during the ecological restoration process to achieve better restoration results. This optimized data helps improve the overall effectiveness of ecological restoration. The ecological restoration assessment result threshold is a preset standard value used to evaluate ecological restoration effects, used to measure whether the restoration has achieved the expected goals. When the assessment result is below this threshold, an optimized restoration plan is implemented to achieve the expected goals. The ecological restoration optimization plan refers to the improvement measures or plans derived from the comparison of the optimized restoration assessment results with the preset threshold. Its purpose is to further adjust the ecological restoration project to ensure better restoration and improvement of the ecological environment.

[0044] Example 2, a method for evaluating ecological restoration effects based on big data proposed by the present invention, compared to Example 1, further includes:

[0045] A1. Extract features from ecological factor data to obtain ecological feature vectors corresponding to the ecological factor data, including:

[0046] A2. Standardize the ecological factor data to obtain standardized ecological factor data corresponding to the ecological factor data. The mathematical expression of the standardization process is as follows:

[0047] ;

[0048] in, Represents the standardized data of ecological elements, The amount of ecological factor data is s, Represents the data value in the ecological factor data with a data volume of s, It represents the average value of the ecological factor data with a data volume of s. Represents the standard deviation of ecological factor data.

[0049] A3. Extract time series features from the standardized data of ecological elements to obtain the ecological feature vectors corresponding to the ecological element data.

[0050] In an optional embodiment, the ecological restoration effect evaluation model adopts a fusion architecture of long short-term memory network and graph convolution network, takes ecological feature vector as input, and outputs the ecological restoration evaluation result of the ecological restoration area;

[0051] The specific implementation of the ecological restoration effect evaluation model is as follows:

[0052] The temporal feature extraction module uses a long short-term memory network to take the ecological feature vector as input, captures the temporal variation of ecological elements through memory units, and outputs a temporal feature matrix;

[0053] Among them, the mathematical expression of the time series feature matrix is ​​as follows:

[0054]

[0055] in, represents the time series feature matrix, represents the set of real numbers, represents the time step, represents the hidden layer dimension;

[0056] The spatial feature extraction module uses the ecological restoration area as a graph node set and converts the spatial distance into graph edge weights based on an exponential decay mechanism to obtain an ecological relationship graph;

[0057] The mathematical expression of graph edge weight is as follows:

[0058]

[0059] in, Representing graph nodes and The edge weights of represents the base of natural logarithms, represents the attenuation coefficient, Representation node and spatial distance;

[0060] Based on the graph convolution network and the ecological relationship graph, the temporal feature matrix is ​​spatially convolved to obtain the spatial feature matrix;

[0061] Among them, the mathematical expression of the spatial feature matrix is ​​as follows:

[0062]

[0063] in, represents the spatial feature matrix, represents the activation function (such as ReLU), represents the degree matrix, i.e. the number of edges connected to each node. The adjacency matrix representing the ecological relationship graph, represents the time series feature matrix, represents the weight matrix of the first layer of the graph convolutional network, Represents the weight matrix of the second layer of the graph convolutional network;

[0064] Fusion of temporal and spatial features based on the attention mechanism to obtain a temporal-spatial fusion matrix;

[0065] The temporal-spatial feature fusion matrix is ​​expressed as follows:

[0066]

[0067] in, represents the temporal-spatial feature fusion matrix, Indicates that the correlation matrix is ​​normalized by row to obtain the attention weight matrix, represents the time series feature matrix, represents the weight matrix, represents the spatial feature matrix, represents the key weight matrix, represents the value weight matrix;

[0068] The output layer maps the temporal-spatial feature fusion matrix into the evaluation value of the ecological restoration effect to obtain the ecological restoration effect evaluation model.

[0069] It should be noted that a long short-term memory network (LSTM) is a special type of recurrent neural network used to process and predict time series data. It uses "memory units" to store and control the flow of information, enabling the model to learn long-term trends and patterns in the data. A graph convolutional network (GCN) is a deep learning model primarily used to process graph-structured data. It aggregates information around nodes (elements in the graph) through convolution operations, effectively capturing the relationships and structural information between nodes in the graph. A fusion architecture combines two or more different types of network models to leverage their respective strengths. The fusion architecture of a long short-term memory network and a graph convolutional network enhances the model's overall performance by combining the time series learning capabilities of the LSTM network with the graph-structured data processing capabilities of the GCN. In the evaluation of ecological restoration effects, this fusion architecture can simultaneously process time series and graph data, providing a more comprehensive assessment of the effectiveness of ecological restoration. The ecological restoration assessment results of an ecological restoration area refer to the results of a quantitative or qualitative analysis of the restoration effects of a particular ecological restoration area. They reflect whether the ecological restoration measures have effectively improved the ecological environment, including changes in biodiversity restoration, soil moisture recovery, and air quality improvement. The evaluation results can be used to understand the effectiveness of restoration and guide subsequent restoration work.

[0070] In an optional embodiment, a three-dimensional virtual scene of an ecological restoration area is constructed based on digital twin technology, including:

[0071] B1. Obtain geographic data of ecological restoration areas;

[0072] B2. Conduct three-dimensional modeling of the ecological restoration area based on geographic data and ecological element data to obtain a three-dimensional digital model of the ecological restoration area;

[0073] B3. Based on digital twin technology, the three-dimensional digital model is visualized in a three-dimensional virtual scene to obtain a three-dimensional virtual scene.

[0074] It should be noted that geographic data refers to various information related to the position, form, environment and phenomena on the earth's surface. In ecological restoration, geographic data usually includes information such as the terrain, soil type, hydrological conditions, vegetation distribution, etc. of the restoration area. These data can provide basic support for subsequent three-dimensional modeling; three-dimensional modeling refers to a process of creating three-dimensional objects, scenes or environments, usually using computer software. In ecological restoration, based on geographic data and ecological element data, three-dimensional modeling can be used to reconstruct the three-dimensional spatial form of the restoration area and simulate the actual scene of the ecosystem; a three-dimensional digital model refers to a virtual model generated by a computer that represents the three-dimensional structure of an object or scene. It is created based on three-dimensional modeling technology and can accurately describe the spatial form, structure and ecological element characteristics of the ecological restoration area; three-dimensional virtual scene visualization refers to the use of computer graphics technology to convert a three-dimensional digital model into a virtual scene for human observation and interaction. Through the visualization of the virtual scene, users can intuitively view and understand the restoration effect of the ecological restoration area.

[0075] In an optional embodiment, the ecological restoration assessment results are mapped to corresponding geographic coordinates of the three-dimensional virtual scene to obtain an ecological restoration heat map of the three-dimensional virtual scene, including:

[0076] C1. Matching the ecological restoration assessment results with the corresponding geographic coordinates of the three-dimensional virtual scene to obtain a virtual ecological restoration assessment result of the ecological restoration area corresponding to the three-dimensional virtual scene;

[0077] C2. Perform color mapping on the virtual ecological restoration assessment results to obtain a color gradient heat map, thereby obtaining an ecological restoration heat map of the three-dimensional virtual scene.

[0078] It should be noted that geographic coordinates refer to the geographic coordinates of the virtual scene, which correspond to the real geographic location of the restoration area, ensuring the consistency between the virtual scene and the actual scene; virtual ecological restoration assessment results refer to the virtual presentation of restoration effect assessment generated by combining the ecological restoration assessment results with geographic coordinates in a three-dimensional virtual scene, making the assessment results more intuitive; color mapping is a visualization technology that corresponds data values ​​to colors. In the heat map of ecological restoration, different colors represent different assessment results. Through color mapping, the differences in restoration effects can be presented in visual form, which can make it easier to understand the spatial distribution of restoration effects.

[0079] In an optional embodiment, color mapping is performed on the virtual ecological restoration assessment results to obtain a color gradient heat map, including:

[0080] D1. Map the ecological restoration assessment result threshold to green;

[0081] D2. Compare the virtual ecological restoration assessment result with the ecological restoration assessment result threshold. If the virtual ecological restoration assessment result is close to the ecological restoration assessment result threshold, the color is close to green to obtain a color gradient heat map.

[0082] It should be noted that mapping the threshold of the ecological restoration assessment result to green means that the threshold of the ecological restoration assessment result is designated as green. Usually, green represents a good restoration effect. Through this mapping method, the system corresponds the assessment result to a color (such as green), so that a good restoration effect is presented on the heat map in a green way. When the restoration effect meets the expected standard, the color will be green; the color close to green means that in the presentation of the heat map, when the virtual assessment result approaches the threshold, its corresponding color will be closer and closer to green. In this way, the color can intuitively show the quality of the restoration effect. Colors close to green indicate better restoration effects, while colors far from green indicate poor restoration effects.

[0083] In an optional embodiment, obtaining restoration nodes based on the ecological restoration heat map includes:

[0084] E1. Obtain the non-green nodes in the ecological restoration heat map;

[0085] E2. Use this node as the repair node.

[0086] It should be noted that the nodes with non-green color refer to the heat map. Green usually indicates a better restoration effect. If the heat map node of a certain area is not green, it means that the restoration effect of the area is poor and the ecological restoration measures of the area need to be optimized.

[0087] In an optional embodiment, the ecological restoration project is used to improve the ecological elements of the ecological restoration area to achieve the purpose of ecological restoration.

[0088] In an optional embodiment, the optimized ecological restoration assessment result is compared with a preset ecological restoration assessment result threshold to obtain a deviation between the two, including:

[0089] F1. Weighting indicators for different regions corresponding to the optimized ecological restoration assessment results to obtain assessment results with different weights;

[0090] F2. Compare the assessment results with the threshold of the ecological restoration assessment results in a temporal and spatial manner to obtain the degree of deviation between the two in different regions.

[0091] In an optional embodiment, the ecological restoration project is iteratively optimized based on the deviation to obtain an ecological restoration effect evaluation report and an ecological restoration optimization plan, including:

[0092] G1. Obtaining the ecological restoration effect evaluation report of the entire ecological restoration area based on the deviation degree;

[0093] G2. Optimize the restoration measures for a portion of the ecological restoration project based on the deviation so that the overall ecological restoration result of the ecological restoration area can reach the ecological restoration assessment result threshold;

[0094] G3. Obtain the restoration parameters after optimization and adjustment of the ecological restoration project, and formulate an optimization adjustment plan based on the restoration parameters to obtain the ecological restoration optimization plan

[0095] It should be noted that restoration parameters refer to various specific parameters used in ecological restoration projects, such as vegetation type, soil quality, water quality indicators, irrigation frequency, etc. These parameters determine the implementation plan of the restoration project and affect the final restoration effect. By adjusting the restoration parameters, the restoration effect can be optimized; the ecological restoration optimization plan refers to a new restoration plan formulated based on the adjustment of restoration parameters in response to the shortcomings or optimization needs of the current restoration project. The goal is to improve the restoration effect and make it reach the threshold of the ecological restoration assessment results.

[0096] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. A method for evaluating ecological restoration effects based on big data, characterized in that: include: Collecting ecological factor data of the ecological restoration area, and performing feature extraction on the ecological factor data to obtain ecological feature vectors corresponding to the ecological factor data; Inputting the ecological feature vector into a pre-trained ecological restoration effect evaluation model, inputting the ecological feature vector into a temporal feature extraction module of the ecological restoration effect evaluation model for time series feature learning to obtain dynamic features of the ecological feature vector that change over time, inputting the dynamic features into a spatial feature extraction module of the ecological restoration effect evaluation model for time-space fusion to obtain temporal-spatial features of the ecological feature vector, and mapping the temporal-spatial features into an evaluation value of the ecological restoration effect based on the output layer of the ecological restoration effect evaluation model to obtain an ecological restoration evaluation result; Constructing a three-dimensional virtual scene of the ecological restoration area based on digital twin technology, and mapping the ecological restoration assessment results to corresponding geographic coordinates of the three-dimensional virtual scene to obtain an ecological restoration heat map of the three-dimensional virtual scene; Obtaining a restoration node based on the ecological restoration heat map, optimizing and adjusting the ecological restoration project of the restoration node to obtain optimized ecological factor data of the restoration node, and obtaining an optimized ecological restoration assessment result of the restoration node based on the optimized ecological factor data; The optimized ecological restoration assessment result is compared with a preset ecological restoration assessment result threshold to obtain a degree of deviation between the two, and the ecological restoration project is iteratively optimized based on the degree of deviation to obtain an ecological restoration effect assessment report and an ecological restoration optimization plan.

2. The ecological restoration effect evaluation method based on big data according to claim 1 is characterized in that: Performing feature extraction on the ecological element data to obtain an ecological feature vector corresponding to the ecological element data includes: Performing standardization processing on the ecological factor data to obtain ecological factor standardized data corresponding to the ecological factor data; Time series feature extraction is performed on the ecological element standardized data to obtain an ecological feature vector corresponding to the ecological element data.

3. The ecological restoration effect evaluation method based on big data according to claim 2 is characterized in that: The ecological restoration effect evaluation model adopts a fusion architecture of long short-term memory network and graph convolution network. The input of the ecological restoration effect evaluation model is the ecological feature vector, and the ecological restoration effect evaluation model is used to output the ecological restoration evaluation results of the ecological restoration area.

4. The ecological restoration effect evaluation method based on big data according to claim 3 is characterized in that: A three-dimensional virtual scene of the ecological restoration area is constructed based on digital twin technology, including: Obtaining geographic data of the ecological restoration area; Performing three-dimensional modeling of the ecological restoration area based on the geographic data and the ecological element data to obtain a three-dimensional digital model of the ecological restoration area; The three-dimensional digital model is visualized in a three-dimensional virtual scene based on digital twin technology to obtain the three-dimensional virtual scene.

5. The ecological restoration effect evaluation method based on big data according to claim 4 is characterized in that: Mapping the ecological restoration assessment results to corresponding geographic coordinates of the three-dimensional virtual scene to obtain an ecological restoration heat map of the three-dimensional virtual scene, including: Matching the ecological restoration assessment result with the corresponding geographic coordinates of the three-dimensional virtual scene to obtain a virtual ecological restoration assessment result of the three-dimensional virtual scene corresponding to the ecological restoration area; Color mapping is performed on the virtual ecological restoration assessment results to obtain a color gradient heat map, thereby obtaining an ecological restoration heat map of the three-dimensional virtual scene.

6. The ecological restoration effect evaluation method based on big data according to claim 5 is characterized in that: Color mapping is performed on the virtual ecological restoration assessment results to obtain a color gradient heat map, including: Mapping the ecological restoration assessment result threshold to green; The virtual ecological restoration assessment result is compared with the ecological restoration assessment result threshold. If the virtual ecological restoration assessment result is close to the ecological restoration assessment result threshold, the color is close to green to obtain the thermal map with a color gradient.

7. The ecological restoration effect evaluation method based on big data according to claim 6 is characterized in that: Obtaining restoration nodes based on the ecological restoration heat map includes: Obtaining nodes of the ecological restoration heat map whose colors are non-green; The node is used as the repair node.

8. The ecological restoration effect evaluation method based on big data according to claim 7 is characterized in that: The ecological restoration project is used to improve the ecological elements of the ecological restoration area to achieve the purpose of ecological restoration.

9. The ecological restoration effect evaluation method based on big data according to claim 8 is characterized in that: Comparing the optimized ecological restoration assessment result with a preset ecological restoration assessment result threshold to obtain a degree of deviation between the two, including: The indicators of different areas corresponding to the optimized ecological restoration assessment results are weighted. To obtain evaluation results with different weights; The assessment results are compared with the threshold values ​​of the ecological restoration assessment results in a temporal and spatial manner to obtain the degree of deviation between the two in different regions.

10. The ecological restoration effect evaluation method based on big data according to claim 9 is characterized in that: The ecological restoration project is iteratively optimized based on the deviation to obtain an ecological restoration effect evaluation report and an ecological restoration optimization plan, including: Obtaining the ecological restoration effect evaluation report of the entire ecological restoration area based on the deviation; Based on the deviation degree, the restoration measures of some areas of the ecological restoration project are optimized so that the overall ecological restoration result of the ecological restoration area can reach the ecological restoration assessment result threshold to obtain the ecological restoration optimization plan.

Images