Ecological risk assessment method and system based on biodiversity

Abstract

The invention relates to the technical field of ecological risk assessment, and discloses an ecological risk assessment method and system based on biodiversity, and the method comprises the steps: introducing a space-time convolutional neural network and an ecological network analysis model, and combining with dynamic correlation analysis to dynamically recognize the correlation between key species and ecological system function degradation. Not only can the space-time degradation trend of biodiversity and ecological system functions be predicted, but also key driving factors, high-risk nodes, high-risk time periods and time dynamic influence paths of key species on ecological system function degradation of ecological risks can be identified based on the trend, so that the accuracy of an ecological risk assessment result is improved; and a more scientific and accurate basis is provided for ecological risk management.

Description

Technical Field

[0001] The present invention relates to the technical field of ecological risk assessment, and in particular to an ecological risk assessment method and system based on biodiversity. Background Art

[0002] With global climate change, drastic changes in land use, increased pollution emissions, and frequent interference from human activities, the global ecosystem is facing serious risks of degradation. At present, ecological risk assessment methods mainly rely on monitoring results of static data or simple linear models, which have obvious limitations in capturing the dynamic evolution characteristics of ecosystems and cannot reflect the dynamic changes of ecological processes in time and space. At the same time, there is a lack of in-depth analysis of the relationship between biodiversity and ecosystem functions, making it difficult to identify the key drivers of ecological risks. These deficiencies lead to low accuracy and applicability of ecological risk assessment results, making it difficult to provide effective decision-making support for ecological protection and management. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide an ecological risk assessment method and system based on biodiversity to solve the problem that the accuracy and applicability of current ecological risk assessment results are low, making it difficult to provide effective decision support for ecological protection and management.

[0004] The first aspect of the present invention discloses an ecological risk assessment method based on biodiversity, the method comprising the following steps:

[0005] S1. Collect biodiversity data, ecosystem function data and environmental impact data;

[0006] S2, performing data cleaning, normalization and feature extraction operations on the collected data to construct a spatiotemporal data set as a first data set;

[0007] S3. Predicting the spatiotemporal trends of biodiversity and ecosystem function degradation based on the first data set by using a spatiotemporal convolutional neural network to obtain a prediction result;

[0008] S4. Correlate the prediction results with the actual monitoring data to generate a temporally and spatially matched biodiversity and ecosystem function dataset as the second dataset;

[0009] S5. Using the second data set as input to an ecological network analysis model, and identifying the dynamic relationship between biodiversity and ecosystem function degradation based on the ecological network analysis model;

[0010] S6. Evaluate ecological risks according to the results of the dynamic association and generate ecological risk assessment results.

[0011] Furthermore, the biodiversity data include species richness, number of functional species, species distribution and population dynamics; the ecosystem function data include carbon storage, water purification capacity, soil conservation and habitat quality; the environmental impact data include climate change data, land use change data, pollution data and human interference data.

[0012] Furthermore, after generating the ecological risk assessment result, the method further includes:

[0013] The ecological risk assessment results are fed back to the spatiotemporal convolutional neural network, and the parameters of the spatiotemporal convolutional neural network are dynamically adjusted based on the ecological risk assessment results.

[0014] Furthermore, the step S3 includes the following sub-steps:

[0015] S301, dividing the first data set into multiple time steps and space grids to form a spatiotemporal feature tensor; the spatiotemporal feature tensor includes a time dimension, a space dimension and a feature dimension;

[0016] S302, performing a spatial convolution operation on the spatiotemporal feature tensor through a spatiotemporal convolutional neural network to extract local feature patterns of biodiversity and ecosystem functions in different spatial grids;

[0017] S303, performing a temporal convolution operation on the spatiotemporal feature tensor that has undergone the spatial convolution processing, to obtain the temporal dynamic trend of biodiversity and ecosystem function degradation;

[0018] S304. Input the first spatiotemporal feature tensor into the fully connected layer of the spatiotemporal convolutional neural network, and output the spatiotemporal trend prediction results of biodiversity and ecosystem function degradation through the fully connected layer; the first spatiotemporal feature tensor includes the spatiotemporal feature tensor after the spatiotemporal convolution processing operation.

[0019] Further, the first spatiotemporal feature tensor also includes a weighted feature tensor, and before executing step S304, it is determined whether the first spatiotemporal feature tensor includes the weighted feature tensor. If the determination is yes, only the weighted feature tensor is input as the first spatiotemporal feature tensor into the fully connected layer of the spatiotemporal convolutional neural network;

[0020] The weighted feature tensor generation process includes:

[0021] The attention weight of the feature is calculated at each time step and spatial grid position of the spatiotemporal feature tensor obtained after the spatiotemporal convolution operation, and the importance of each time step and spatial grid position is represented by the attention weight matrix;

[0022] The spatiotemporal feature tensor is weighted by using the attention weights to obtain a weighted feature tensor.

[0023] Furthermore, the step S4 includes the following sub-steps:

[0024] S401, performing time dimension matching and space dimension matching operations on the prediction result and the actual monitoring data;

[0025] S402, based on the matching results of the time dimension and the space dimension, the prediction results are integrated with the actual monitoring data to generate an initial space-time matching data set;

[0026] S403, performing a consistency check operation on the initial spatiotemporal matching data set, and integrating the checked spatiotemporal matching data set into a second data set; the consistency check operation includes removing outliers and inconsistent data points.

[0027] Furthermore, the step S5 includes the following sub-steps:

[0028] S501, constructing an ecological network of an ecological network analysis model based on the second data set, the ecological network comprising a plurality of nodes and edges; wherein the nodes comprise biodiversity characteristics and ecosystem function characteristics; the edges comprise mutual relationships between the nodes, and the weights of the edges are calculated based on the correlation between the biodiversity characteristics and the ecosystem function characteristics in the second data set;

[0029] S502, calculating the functional contribution between nodes;

[0030] S503. Determine the key nodes in the ecological network by combining the functional contributions between the nodes, and identify the dynamic association between biodiversity characteristics and ecosystem functional characteristics through a dynamic association analysis algorithm.

[0031] Furthermore, the step S503 includes the following sub-steps:

[0032] S5031. Constructing a dynamic evolution sequence of the ecological network at different time steps based on the second data set; the dynamic evolution sequence includes a network snapshot of nodes and node association relationships at each time step;

[0033] S5032, calculating the centrality index of the node in each time step, and determining the key nodes in the ecological network based on the centrality index and functional contribution;

[0034] S5033. Selecting subnetworks of continuous time steps in the dynamic evolution sequence by using a time window sliding method, and extracting dynamic change characteristics of key nodes and their edges in the subnetwork;

[0035] S5034, calculating the dynamic correlation strength between key nodes through Granger causality analysis based on the dynamic change characteristics, and constructing a dynamic correlation strength matrix; wherein, in the process of calculating the dynamic correlation strength, weighting is performed according to the functional contribution;

[0036] S5035. Based on the dynamic correlation intensity and the dynamic correlation intensity matrix, the dynamic evolution of key nodes, the dynamic correlation trend between key nodes, and the temporal dynamic impact path of key species on the degradation of ecosystem functions are obtained.

[0037] Furthermore, the step S6 includes the following sub-steps:

[0038] S601. Determine high-risk nodes and high-risk periods of ecosystem function degradation at different time steps based on the dynamic evolution of key nodes;

[0039] S602. Analyze the changes in the correlation intensity between biodiversity characteristics and ecosystem function characteristics based on the dynamic correlation trends between key nodes, and identify the key driving factors that lead to the degradation of ecosystem functions;

[0040] S603. Based on the identified high-risk nodes, high-risk periods, key driving factors and the temporal dynamic impact paths of key species on ecosystem function degradation, ecological risk levels are divided and ecological risk assessment results are generated.

[0041] The second aspect of the present invention discloses an ecological risk assessment system based on biodiversity, which is implemented based on the method disclosed in the first aspect. The system includes a data acquisition module, a data processing module, a construction module and an assessment module; wherein:

[0042] The data collection module is used to collect biodiversity data, ecosystem function data and environmental impact data;

[0043] The data processing module is used to perform data cleaning, normalization and feature extraction operations on the collected data to construct a spatiotemporal data set as a first data set;

[0044] The construction module is used to construct a spatiotemporal convolutional neural network and an ecological network analysis model; the spatiotemporal convolutional neural network is used to predict the spatiotemporal trend of biodiversity and ecosystem function degradation based on the first data set, obtain prediction results, and associate the prediction results with actual monitoring data to generate a spatiotemporal matching biodiversity and ecosystem function data set as the second data set;

[0045] The ecological network analysis model is used to identify the dynamic relationship between biodiversity and ecosystem function degradation based on the second data set;

[0046] The assessment module is used to assess ecological risks according to the results of the dynamic association and generate ecological risk assessment results.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] The present invention introduces a spatiotemporal convolutional neural network and an ecological network analysis model, and combines it with dynamic association analysis to dynamically identify the correlation between key species and ecosystem function degradation. It can not only predict the spatiotemporal degradation trend of biodiversity and ecosystem functions, but also identify the key driving factors of ecological risks, high-risk nodes, high-risk time periods, and the temporal dynamic impact path of key species on ecosystem function degradation based on this trend, thereby improving the accuracy of ecological risk assessment results and providing a more scientific and accurate basis for ecological risk management. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the economic application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0050] Figure 1 A schematic diagram of a process flow of an ecological risk assessment method based on biodiversity disclosed in an embodiment of the present invention;

[0051] Figure 2 This is a schematic structural diagram of an ecological risk assessment system based on biodiversity disclosed in yet another embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments.

[0053] Embodiment 1

[0054] The first aspect of the present invention discloses an ecological risk assessment method based on biodiversity, see Figure 1 , Figure 1 : is a flow chart of an ecological risk assessment method based on biodiversity disclosed in an embodiment of the present invention, the method comprising the following steps:

[0055] S1. Collect biodiversity data, ecosystem function data and environmental impact data;

[0056] S2. Perform data cleaning, normalization and feature extraction operations on the collected data to construct a spatiotemporal dataset as the first dataset.

[0057] In an embodiment of the present invention, the spatiotemporal dataset includes both a time dimension and a space dimension. Among them, the time dimension reflects the dynamic changes of data at different time steps (such as days, months, and years), and the spatial dimension represents the distribution of data at different spatial locations (such as grids, regions, and sampling points). Specifically, biodiversity data include but are not limited to data such as species richness, number of functional species, species distribution, and population dynamics; ecosystem function data include but are not limited to data such as carbon storage, water purification capacity, soil conservation, and habitat quality; environmental impact data include but are not limited to climate change data, land use change data, pollution data, and human interference data. After cleaning to remove outliers and normalizing to convert data of different dimensions into a unified scale, effective information is extracted through feature extraction operations to form a spatiotemporal dataset that can be used for spatiotemporal trend prediction and ecological risk assessment.

[0058] S3. Predicting the spatiotemporal trends of biodiversity and ecosystem function degradation based on the first data set by using a spatiotemporal convolutional neural network to obtain a prediction result;

[0059] S4. Correlate the prediction results with the actual monitoring data to generate a temporally and spatially matched biodiversity and ecosystem function dataset as the second dataset;

[0060] S5. Using the second data set as input to an ecological network analysis model, and identifying the dynamic relationship between biodiversity and ecosystem function degradation based on the ecological network analysis model;

[0061] S6. Evaluate ecological risks according to the results of the dynamic association and generate ecological risk assessment results.

[0062] Furthermore, after generating the ecological risk assessment result, the method further includes:

[0063] The ecological risk assessment results are fed back to the spatiotemporal convolutional neural network, and the parameters of the spatiotemporal convolutional neural network are dynamically adjusted based on the ecological risk assessment results.

[0064] Specifically, the construction process of the spatiotemporal convolutional neural network in the embodiment of the present invention includes: constructing a high-quality spatiotemporal data set based on historically collected biodiversity data, ecosystem function data and environmental impact data, performing data cleaning, normalization and feature extraction operations on the data set, and converting the data into a spatiotemporal feature tensor suitable for network input. Preferably, in the embodiment of the present invention, the network architecture of ST-CNN is selected, including a spatial convolution layer, a temporal convolution layer, and a fully connected layer, the network is trained by a supervised learning method, the prediction error is measured using a loss function, and the network parameters are adjusted by back propagation and optimization algorithms. After the training is completed, the performance of the model is evaluated by a validation set and a test set, so that ST-CNN can accurately predict the spatiotemporal trends of biodiversity and ecosystem function degradation.

[0065] Furthermore, step S3 includes the following sub-steps:

[0066] S301, dividing the first data set into multiple time steps and space grids to form a spatiotemporal feature tensor; the spatiotemporal feature tensor includes a time dimension, a space dimension and a feature dimension;

[0067] S302, performing a spatial convolution operation on the spatiotemporal feature tensor through a spatiotemporal convolutional neural network to extract local feature patterns of biodiversity and ecosystem functions in different spatial grids;

[0068] S303, performing a temporal convolution operation on the spatiotemporal feature tensor that has undergone spatial convolution processing, to obtain a temporal dynamic trend of biodiversity and ecosystem function degradation;

[0069] S304. Input the first spatiotemporal feature tensor into the fully connected layer of the spatiotemporal convolutional neural network, and output the spatiotemporal trend prediction results of biodiversity and ecosystem function degradation through the fully connected layer; the first spatiotemporal feature tensor includes the spatiotemporal feature tensor after the spatiotemporal convolution processing operation.

[0070] Specifically, the prediction results output by the spatiotemporal convolutional neural network ST-CNN are the spatiotemporal trends of biodiversity and ecosystem function degradation, which contain a multidimensional data matrix of time dimension, space dimension and prediction indicator dimension. For example, when expressing the changing trends of ecosystem function indicators such as species richness, number of functional species, carbon storage, water purification capacity, and soil conservation at different time steps and different spatial grids, the prediction results may show that the species richness in a certain area will gradually decrease in the next 6 months, or the carbon storage of a wetland will significantly decrease in a specific time period.

[0071] In this embodiment, the specific operation process of step S3 enables ST-CNN to effectively combine information in the time and space dimensions, thereby improving the accuracy and reliability of the prediction and ensuring the feasibility and technical integrity of ST-CNN in predicting biodiversity and ecosystem function degradation.

[0072] Further, the first spatiotemporal feature tensor also includes a weighted feature tensor, and before executing step S304, it is determined whether the first spatiotemporal feature tensor includes the weighted feature tensor. If the determination is yes, only the weighted feature tensor is input as the first spatiotemporal feature tensor into the fully connected layer of the spatiotemporal convolutional neural network;

[0073] Among them, the weighted feature tensor generation process includes:

[0074] The attention weight of the feature is calculated at each time step and spatial grid position of the spatiotemporal feature tensor obtained after the spatiotemporal convolution operation, and the importance of each time step and spatial grid position is represented by the attention weight matrix;

[0075] The spatiotemporal feature tensor is weighted by using the attention weights to obtain a weighted feature tensor.

[0076] In this embodiment, by introducing a weighted feature tensor and setting the weighted feature tensor to dynamically assign different weights to features at different time steps and spatial grid positions through an attention mechanism, the spatiotemporal convolutional neural network can focus on features that contribute greatly to the prediction results or have important ecological significance, effectively reducing the interference of redundant information and noise, and improving the ability to identify key features in complex ecosystems, thereby making the prediction results more ecologically interpretable.

[0077] Further, step S4 includes the following sub-steps:

[0078] S401, performing time dimension matching and space dimension matching operations on the prediction result and the actual monitoring data;

[0079] S402, based on the matching results of the time dimension and the space dimension, the prediction results are integrated with the actual monitoring data to generate an initial space-time matching data set;

[0080] S403, performing a consistency check operation on the initial spatiotemporal matching data set, and integrating the checked spatiotemporal matching data set into a second data set; the consistency check operation includes removing outliers and inconsistent data points.

[0081] Furthermore, the step S5 includes the following sub-steps:

[0082] S501, constructing an ecological network of an ecological network analysis model based on the second data set, the ecological network comprising a plurality of nodes and edges; wherein the nodes comprise biodiversity characteristics and ecosystem function characteristics; the edges comprise mutual relationships between the nodes, and the weights of the edges are calculated based on the correlation between the biodiversity characteristics and the ecosystem function characteristics in the second data set;

[0083] S502: Calculate the functional contribution between nodes.

[0084] Specifically, functional contribution is used to measure the contribution of biodiversity characteristic nodes to ecosystem functions, that is, the importance of a species or biological community in maintaining ecosystem functions.

[0085] S503. Determine the key nodes in the ecological network by combining the functional contributions between the nodes, and identify the dynamic association between biodiversity characteristics and ecosystem functional characteristics through a dynamic association analysis algorithm.

[0086] Specifically, in the embodiment of the present invention, a key node refers to a node in an ecological network that has a significant impact on the ecosystem function and / or the ecological network structure, and may be a biodiversity characteristic node or an ecosystem function characteristic node.

[0087] Further, step S503 includes the following sub-steps:

[0088] S5031. Constructing a dynamic evolution sequence of the ecological network at different time steps based on the second data set; the dynamic evolution sequence includes a network snapshot of nodes and node association relationships at each time step;

[0089] S5032. Calculate the centrality index of the nodes in each time step, and determine the key nodes in the ecological network based on the centrality index and the functional contribution.

[0090] Specifically, centrality indicators include degree centrality, betweenness centrality, and eigenvector centrality. Among them, nodes with high degree centrality represent species or ecosystem functional elements that have more direct connections with other nodes; nodes with high betweenness centrality represent key species that connect different ecosystem functional elements; and nodes with high eigenvector centrality represent nodes with greater overall influence.

[0091] S5033. Selecting subnetworks of continuous time steps in the dynamic evolution sequence by using a time window sliding method, and extracting dynamic change characteristics of key nodes and their edges in the subnetwork;

[0092] S5034, calculating the dynamic correlation strength between key nodes through Granger causality analysis based on the dynamic change characteristics, and constructing a dynamic correlation strength matrix; wherein, in the process of calculating the dynamic correlation strength, weighting is performed according to the functional contribution;

[0093] S5035. Based on the dynamic correlation intensity and the dynamic correlation intensity matrix, the dynamic evolution of key nodes, the dynamic correlation trend between key nodes, and the temporal dynamic impact path of key species on the degradation of ecosystem functions are obtained.

[0094] For the ecological network analysis model, its construction process includes constructing an ecological network through a dataset after time-space matching, configuring a network topology analysis algorithm to identify key nodes, and configuring a dynamic association analysis algorithm (such as Granger causality analysis) to capture the temporal dynamic association relationship between nodes. Through multiple iterations and verifications, the analysis parameters are adjusted so that the ecological network analysis model can effectively reveal the dynamic association between biodiversity and ecosystem function degradation, providing a scientific basis for ecological risk assessment.

[0095] Preferably, the correlation between biodiversity characteristics and ecosystem function characteristics is calculated as follows:

[0096] A i，j =f(x i , x j )

[0097]

[0098] Among them, A i，j is the association degree between node i and node j; x i 、x j are the eigenvalues ​​of node i and node j, respectively. The eigenvalues ​​represent the numerical values ​​of biodiversity or ecosystem functions; is the mean of the eigenvalues ​​of nodes i and j.

[0099] The dynamic correlation strength is calculated as follows:

[0100]

[0101] G i，j (t) = Granger (X i (t), X j (t))

[0102] Among them, X j (t) is the time series data of node j at time step t, which is used as the explained variable; X i (t) is the time series data of node i at time step t, which serves as the explanatory variable; a k 、b k is the regression coefficient; k is the time lag order; p is the maximum lag order; ∈ j (t) is the regression error term of node j; G i，j (t) is the dynamic association strength between node i and node j at time step t.

[0103] Furthermore, step S6 includes the following sub-steps:

[0104] S601. Determine high-risk nodes and high-risk periods for ecosystem function degradation at different time steps based on the dynamic evolution of key nodes.

[0105] Specifically, based on the dynamic evolution sequence, the changes of key nodes in the time dimension are tracked to observe the dynamic change trend of the centrality, functional contribution and correlation strength of these nodes in the ecological network structure. If the functional contribution of some nodes decreases significantly, or shows an obvious degradation trend at a certain time step, these nodes and corresponding time steps are marked as high-risk nodes and high-risk periods.

[0106] S602. Analyze the changes in the correlation intensity between biodiversity characteristics and ecosystem function characteristics based on the dynamic correlation trends between key nodes, and determine the key driving factors that lead to the degradation of ecosystem functions.

[0107] Specifically, through the dynamic correlation intensity matrix, we can identify whether the correlation between key nodes is strengthening, weakening, or whether new correlations have emerged or disappeared. Combined with the functional contribution and the importance of the nodes, we can screen out species or environmental factors that have a significant impact on the degradation of ecosystem functions and identify them as key driving factors leading to the degradation of ecosystem functions. Key driving factors include but are not limited to biological factors (such as the reduction of key species and the decline of pollinator communities), environmental factors (such as pollution and climate change) or human activities (such as land use changes and overfishing).

[0108] S603. Based on the identified high-risk nodes, high-risk periods, key driving factors and the temporal dynamic impact paths of key species on ecosystem function degradation, ecological risk levels are divided and ecological risk assessment results are generated.

[0109] Specifically, by identifying high-risk nodes, high-risk periods and key driving factors, ecological risks are divided into multiple levels (such as high risk, medium risk and low risk), and the time dynamic impact path is considered at the same time to clarify the impact process of key species on ecological function degradation. As a preferred method, the risk assessment results are organized into an ecological risk assessment matrix, and the spatiotemporal distribution and dynamic evolution of ecological risks are intuitively presented in a visual form, providing a scientific basis for ecological protection, risk intervention and management decisions.

[0110] Embodiment 2

[0111] The second aspect of the present invention discloses an ecological risk assessment system based on biodiversity, see Figure 2 , Figure 2 is a structural diagram of an ecological risk assessment system based on biodiversity disclosed in another embodiment of the present invention, the system includes a data acquisition module, a data processing module, a construction module and an assessment module; wherein,

[0112] The data collection module is used to collect biodiversity data, ecosystem function data and environmental impact data;

[0113] The data processing module is used to perform data cleaning, normalization and feature extraction operations on the collected data to construct a spatiotemporal data set as a first data set;

[0114] The construction module is used to construct a spatiotemporal convolutional neural network and an ecological network analysis model; the spatiotemporal convolutional neural network is used to predict the spatiotemporal trend of biodiversity and ecosystem function degradation based on the first data set, obtain prediction results, and associate the prediction results with actual monitoring data to generate a spatiotemporal matching biodiversity and ecosystem function data set as the second data set;

[0115] The ecological network analysis model is used to identify the dynamic relationship between biodiversity and ecosystem function degradation based on the second data set;

[0116] The assessment module is used to assess ecological risks according to the results of the dynamic association and generate ecological risk assessment results.

[0117] It should be noted that the specific implementation process of the second embodiment is similar to that of the first embodiment and will not be repeated in the second embodiment.

[0118] Finally, it should be noted that the method and system for ecological risk assessment based on biodiversity disclosed in the embodiments of the present invention disclose only the preferred embodiments of the present invention and are only used to illustrate the technical scheme of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical schemes described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical schemes from the spirit and scope of the technical schemes of the embodiments of the present invention.

Claims

1. A biodiversity-based ecological risk assessment method, characterized in that: The method comprises: S1. Collect biodiversity data, ecosystem function data and environmental impact data; S2, performing data cleaning, normalization and feature extraction operations on the collected data to construct a spatiotemporal data set as a first data set; S3. Predicting the spatiotemporal trends of biodiversity and ecosystem function degradation based on the first data set by using a spatiotemporal convolutional neural network to obtain a prediction result; S4. Correlate the prediction results with the actual monitoring data to generate a temporally and spatially matched biodiversity and ecosystem function dataset as the second dataset; S5. Using the second data set as input to an ecological network analysis model, and identifying the dynamic relationship between biodiversity and ecosystem function degradation based on the ecological network analysis model; S6. Evaluate ecological risks according to the results of the dynamic association and generate ecological risk assessment results.

2. The biodiversity-based ecological risk assessment method according to claim 1, characterized in that: The biodiversity data include species richness, number of functional species, species distribution and population dynamics; the ecosystem function data include carbon storage, water purification capacity, soil conservation and habitat quality; the environmental impact data include climate change data, land use change data, pollution data and human interference data.

3. The method for ecological risk assessment based on biodiversity according to claim 1, characterized in that: After generating the ecological risk assessment results, the method further comprises: The ecological risk assessment results are fed back to the spatiotemporal convolutional neural network, and the parameters of the spatiotemporal convolutional neural network are dynamically adjusted based on the ecological risk assessment results.

4. The method for ecological risk assessment based on biodiversity according to claim 1, characterized in that: The step S3 comprises the following sub-steps: S301, dividing the first data set into multiple time steps and space grids to form a spatiotemporal feature tensor; the spatiotemporal feature tensor includes a time dimension, a space dimension and a feature dimension; S302, performing a spatial convolution operation on the spatiotemporal feature tensor through a spatiotemporal convolutional neural network to extract local feature patterns of biodiversity and ecosystem functions in different spatial grids; S303, performing a temporal convolution operation on the spatiotemporal feature tensor that has undergone spatial convolution processing, to obtain a temporal dynamic trend of biodiversity and ecosystem function degradation; S304, inputting the first spatiotemporal feature tensor into a fully connected layer of a spatiotemporal convolutional neural network, and outputting the spatiotemporal trend prediction results of biodiversity and ecosystem function degradation through the fully connected layer; The first spatiotemporal feature tensor includes a spatiotemporal feature tensor after a spatiotemporal convolution operation.

5. The method for ecological risk assessment based on biodiversity according to claim 4, characterized in that: The first spatiotemporal feature tensor also includes a weighted feature tensor, and before executing step S304, it is determined whether the first spatiotemporal feature tensor includes the weighted feature tensor. If the determination is yes, only the weighted feature tensor is input as the first spatiotemporal feature tensor into the fully connected layer of the spatiotemporal convolutional neural network; The weighted feature tensor generation process includes: The attention weight of the feature is calculated at each time step and spatial grid position of the spatiotemporal feature tensor obtained after the spatiotemporal convolution operation, and the importance of each time step and spatial grid position is represented by the attention weight matrix; The spatiotemporal feature tensor is weighted by using the attention weights to obtain a weighted feature tensor.

6. The method for ecological risk assessment based on biodiversity according to claim 1, characterized in that: The step S4 comprises the following sub-steps: S401, performing time dimension matching and space dimension matching operations on the prediction result and the actual monitoring data; S402, based on the matching results of the time dimension and the space dimension, the prediction results are integrated with the actual monitoring data to generate an initial space-time matching data set; S403, performing a consistency check operation on the initial spatiotemporal matching data set, and integrating the checked spatiotemporal matching data set into a second data set; the consistency check operation includes removing outliers and inconsistent data points.

7. The method for ecological risk assessment based on biodiversity according to claim 1, characterized in that: The step S5 comprises the following sub-steps: S501, constructing an ecological network of an ecological network analysis model based on the second data set, the ecological network comprising a plurality of nodes and edges; wherein the nodes comprise biodiversity characteristics and ecosystem function characteristics; the edges comprise mutual relationships between the nodes, and the weights of the edges are calculated based on the correlation between the biodiversity characteristics and the ecosystem function characteristics in the second data set; S502, calculating the functional contribution between nodes; S503. Determine the key nodes in the ecological network by combining the functional contributions between the nodes, and identify the dynamic association between biodiversity characteristics and ecosystem functional characteristics through a dynamic association analysis algorithm.

8. The method for ecological risk assessment based on biodiversity according to claim 7, characterized in that: The step S503 includes the following sub-steps: S5031. Constructing a dynamic evolution sequence of the ecological network at different time steps based on the second data set; the dynamic evolution sequence includes a network snapshot of nodes and node association relationships at each time step; S5032, calculating the centrality index of the node in each time step, and determining the key nodes in the ecological network based on the centrality index and functional contribution; S5033. Selecting subnetworks of continuous time steps in the dynamic evolution sequence by using a time window sliding method, and extracting dynamic change characteristics of key nodes and their edges in the subnetwork; S5034, calculating the dynamic correlation strength between key nodes through Granger causality analysis based on the dynamic change characteristics, and constructing a dynamic correlation strength matrix; wherein, in the process of calculating the dynamic correlation strength, weighting is performed according to the functional contribution; S5035. Based on the dynamic correlation intensity and the dynamic correlation intensity matrix, the dynamic evolution of key nodes, the dynamic correlation trend between key nodes, and the temporal dynamic impact path of key species on the degradation of ecosystem functions are obtained.

9. The biodiversity-based ecological risk assessment method according to claim 8, characterized in that: The step S6 comprises the following sub-steps: S601. Determine high-risk nodes and high-risk periods of ecosystem function degradation at different time steps based on the dynamic evolution of key nodes; S602. Analyze the changes in the correlation intensity between biodiversity characteristics and ecosystem function characteristics based on the dynamic correlation trends between key nodes, and identify the key driving factors that lead to the degradation of ecosystem functions; S603. Based on the identified high-risk nodes, high-risk periods, key driving factors and the temporal dynamic impact paths of key species on ecosystem function degradation, ecological risk levels are divided and ecological risk assessment results are generated.

10. An ecological risk assessment system based on biodiversity, characterized in that: The system is implemented based on the method described in any one of claims 1 to 9, and the system includes a data acquisition module, a data processing module, a construction module and an evaluation module; wherein, The data collection module is used to collect biodiversity data, ecosystem function data and environmental impact data; The data processing module is used to perform data cleaning, normalization and feature extraction operations on the collected data to construct a spatiotemporal data set as a first data set; The construction module is used to construct a spatiotemporal convolutional neural network and an ecological network analysis model; the spatiotemporal convolutional neural network is used to predict the spatiotemporal trend of biodiversity and ecosystem function degradation based on the first data set, obtain prediction results, and associate the prediction results with actual monitoring data to generate a spatiotemporal matching biodiversity and ecosystem function data set as the second data set; The ecological network analysis model is used to identify the dynamic relationship between biodiversity and ecosystem function degradation based on the second data set; The assessment module is used to assess ecological risks according to the results of the dynamic association and generate ecological risk assessment results.

Images