River ecological restoration effect evaluation method based on comprehensive data analysis

Abstract

The invention discloses a comprehensive data analysis-based river ecological restoration effect evaluation method, and particularly relates to the technical field of ecological restoration evaluation.The method comprises the steps of obtaining ecological function data and ecological structure data of a river restoration area, analyzing the ecological function data in combination with a deep learning model, and constructing a vertical distribution model of photosynthesis efficiency; evaluating photosynthesis contribution differences of different water depth levels; on the basis of ecological structure data, monitoring migration characteristics of key nutrients of a vegetation and bottom mud interface, and quantifying a dynamic relationship between nutrition supply and demand balance and vegetation growth recovery by using an interface coupling model; comprehensively analyzing a photosynthesis contribution difference and a nutrition supply and demand dynamic relationship, and generating a comprehensive evaluation index reflecting a vegetation health state and an ecological restoration degree; and based on the evaluation indexes, the restoration effects are graded, a restoration effect distribution diagram and statistical data are generated, and finally an ecological restoration effect report is output.

Description

Technical Field

[0001] The present invention relates to the technical field of ecological restoration evaluation, and more specifically, to a method for evaluating the effect of river ecological restoration based on comprehensive data analysis. Background Art

[0002] With the increasing awareness of ecological protection, river ecological restoration projects have become an important means to improve water quality and restore biodiversity. During the restoration process, aquatic vegetation, as a key component of the ecosystem, directly affects the ecological function and structure of the restoration area through its photosynthesis efficiency.

[0003] In the existing technology, the photosynthesis efficiency of aquatic vegetation after river ecological restoration shows significant inconsistency due to differences in water depth, light, flow rate and vegetation distribution, which makes it difficult to uniformly analyze multi-scale data during the restoration effect evaluation process. The existing evaluation methods lack comprehensive modeling capabilities for different regions and different data scales, and it is difficult to fully reflect the actual effects of ecological restoration, resulting in limitations on the scientificity and accuracy of the evaluation results. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a river ecological restoration effect evaluation method based on comprehensive data analysis to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The river ecological restoration effect evaluation method based on comprehensive data analysis includes the following steps:

[0007] S1: Obtain ecological function data and ecological structure data of the river restoration area; ecological function data include photosynthesis efficiency data and water depth data, and ecological structure data include vegetation distribution data, sediment interface data, and key nutrient data;

[0008] S2: Analyze ecological function data based on deep learning models, and build a vertical distribution model of photosynthesis efficiency in combination with hierarchical analysis methods to evaluate the differences in photosynthesis contributions at different water depths;

[0009] S3: Based on ecological structure data, the migration characteristics of key nutrients at the interface between vegetation and sediment in the river restoration area are monitored, and the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery is quantified using the interface coupling model;

[0010] S4: Comprehensively analyze the differences in photosynthesis contribution and nutrient supply and demand balance at different water depths and the dynamic relationship between vegetation growth and recovery, and generate comprehensive evaluation indicators that reflect the health status of vegetation and the degree of ecological recovery;

[0011] S5: Evaluate the ecological restoration effect of the river restoration area based on comprehensive evaluation index analysis and output a restoration effect report.

[0012] In a preferred embodiment, obtaining ecological function data and ecological structure data of the river restoration area specifically includes:

[0013] Ecological function data include photosynthesis efficiency data of aquatic vegetation and water depth data collected by sensors;

[0014] Ecological structure data include vegetation distribution data obtained through remote sensing technology, sediment interface data obtained through field testing, and key nutrient data obtained through chemical analysis methods;

[0015] The collected ecological function data and ecological structure data are preprocessed and normalized through multimodal data fusion technology.

[0016] In a preferred embodiment, the ecological function data is analyzed based on a deep learning model, and a vertical distribution model of photosynthesis efficiency is constructed in combination with a hierarchical analysis method to evaluate the difference in photosynthesis contribution at different water depths, specifically including:

[0017] Use deep learning models to extract features from photosynthesis efficiency data and water depth data, and build a spatial distribution model of vegetation photosynthesis efficiency;

[0018] The water depth data is divided into multiple depth levels, and the photosynthesis efficiency data in each depth level are statistically calculated according to the hierarchical analysis method to generate the photosynthesis efficiency characteristic value of each depth level;

[0019] Based on the results of hierarchical analysis, the spatial distribution model of photosynthesis efficiency was corrected through the model parameter optimization algorithm, and the vertical distribution model of photosynthesis efficiency was constructed;

[0020] The differences in photosynthesis contributions at different water depths were quantitatively evaluated through a vertical distribution model.

[0021] In a preferred embodiment, the migration characteristics of key nutrients at the interface between vegetation and sediment in the river restoration area are monitored based on ecological structure data, and the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery is quantified using an interface coupling model, specifically including:

[0022] Determine the vegetation coverage in the restoration area based on vegetation distribution data, calibrate the vegetation root distribution area based on sediment interface data, and obtain the concentration data of key nutrients at the sediment interface;

[0023] Using key nutrient data, an interfacial nutrient migration model was established to calculate the migration rate of key nutrients from sediment to the vegetation root zone;

[0024] Based on the output of the interfacial nutrient transport model and combined with vegetation distribution data, the total nutrient uptake in the vegetation root zone is calculated;

[0025] The interface coupling model is used to match the nutrient supply rate of the sediment interface with the nutrient absorption rate of the vegetation root zone to calculate the nutrient supply and demand balance value.

[0026] The nutrient supply and demand balance value and vegetation distribution data are used to further generate a supply and demand balance index to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery.

[0027] In a preferred embodiment, the total amount of nutrient absorption in the root area of ​​the vegetation is calculated based on the output of the interface nutrient migration model and combined with the vegetation distribution data. Specifically, the nutrient absorption rate in the root area of ​​the vegetation is calculated by the absorption kinetics model: Among them, U represents the nutrient absorption rate per unit time, V max Indicates the maximum absorption rate of nutrients by vegetation roots, C r represents the nutrient concentration in the root zone of vegetation, K m It represents the half-saturation constant of nutrient absorption by vegetation roots;

[0028] The total amount of nutrients absorbed by the vegetation root area is calculated by spatial integration: Q total =∫ A U·dA; among them, Q total It represents the total absorption of the vegetation root area, and A represents the spatial range of the root distribution area.

[0029] In a preferred embodiment, the nutrient supply rate at the sediment interface is matched with the nutrient absorption rate in the vegetation root zone through an interface coupling model to calculate the nutrient supply and demand balance value:

[0030] The interface coupling model is used to match the nutrient supply rate at the sediment interface and the absorption rate of the vegetation roots to calculate the nutrient supply and demand balance value: Among them, B represents the balance value of nutrient supply and demand, R supply Represents the total amount of nutrients provided by the sediment interface, R demand Indicates the total nutrient requirement for vegetation roots.

[0031] In a preferred embodiment, the nutrient supply and demand balance value and vegetation distribution data are used to further generate a supply and demand balance index to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery:

[0032] Based on the nutrient supply and demand balance value and vegetation distribution data, a supply and demand balance index is generated to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery: Among them, I balance represents the supply and demand balance index, Aveg Indicates the area of ​​vegetation coverage, A total Represents the total area of ​​the repair region.

[0033] In a preferred embodiment, the difference in photosynthesis contribution at different water depths and the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery are comprehensively analyzed to generate a comprehensive evaluation index reflecting the health status of vegetation and the degree of ecological recovery, specifically including:

[0034] Based on the differences in photosynthesis contribution at different water depths, a photosynthesis contribution matrix was constructed, in which each matrix element corresponds to the photosynthesis efficiency of the water depth and its proportion in the overall contribution.

[0035] Based on the supply-demand balance index and vegetation coverage, a supply-demand balance matrix is ​​constructed, in which each matrix element corresponds to the ratio of the supply-demand balance index to the vegetation coverage rate;

[0036] The photosynthesis contribution matrix and the supply-demand balance matrix are weighted and superimposed, and a comprehensive analysis matrix is ​​generated using a multidimensional data fusion algorithm. The matrix elements represent the comprehensive ecological contribution values ​​of different water depth levels.

[0037] The comprehensive analysis matrix was normalized and combined with vegetation distribution data to generate a comprehensive evaluation index that reflects the health status of vegetation and the degree of ecological restoration.

[0038] In a preferred embodiment, the ecological restoration effect of the river restoration area is evaluated based on the comprehensive evaluation index, and a restoration effect report is output, which specifically includes:

[0039] Based on the comprehensive evaluation indicators, the evaluation results are divided into multiple ecological restoration effect levels according to the preset classification rules, where the classification rules include the distribution range of the comprehensive evaluation indicators and the corresponding level thresholds;

[0040] According to the spatial distribution results of the comprehensive evaluation index, a restoration effect distribution map of each sub-region in the region is generated, in which the restoration effect level of each sub-region corresponds to the level of its comprehensive evaluation index value;

[0041] Extract the restoration effect statistics of the whole area based on the restoration effect distribution map, including the distribution ratio of restoration effect levels and the area proportion of areas with different levels;

[0042] The restoration effect distribution map and restoration effect statistical information are summarized to generate an ecological restoration effect report for the river restoration area. The restoration effect report includes a restoration effect grade distribution map, statistical data tables, and a summary of the classification results.

[0043] Technical effects and advantages of the river ecological restoration effect evaluation method based on comprehensive data analysis of the present invention:

[0044] 1. By comprehensively acquiring ecological function data and ecological structure data, and combining deep learning models and hierarchical analysis methods to construct a vertical distribution model of photosynthesis efficiency, the differences in photosynthesis contribution at different water depths can be accurately evaluated. In addition, by monitoring the migration characteristics of key nutrients at the interface between vegetation and sediment based on ecological structure data, and using an interface coupling model to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery, the present invention achieves a dual analysis of ecological functions and structures to ensure that the evaluation results are more comprehensive. By comprehensively analyzing the differences in photosynthesis contribution and the dynamic relationship between nutrient supply and demand, and generating comprehensive evaluation indicators, the problem of difficulty in uniformly analyzing multi-scale data in the prior art is effectively solved, and the overall ecological status of the river restoration area can be reflected more scientifically and accurately.

[0045] 2. Based on the classification and evaluation of river restoration effects based on comprehensive evaluation indicators, a restoration effect distribution map and statistical data are generated, and an ecological restoration effect report is output, providing a reliable basis for the visual analysis and quantitative evaluation of restoration effects. The restoration effect grade distribution and statistical information contained in the report provide specific data support for the optimal design of river restoration plans, enhancing the controllability and pertinence of restoration effects. The overall method integrates multiple types of data and adopts deep learning and coupling model technology to achieve full process optimization from data acquisition, feature extraction to evaluation result output, with significant advantages of comprehensive evaluation, accurate results, and strong practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the river ecological restoration effect evaluation method based on comprehensive data analysis of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Example: Figure 1 The present invention provides a river ecological restoration effect evaluation method based on comprehensive data analysis, which includes the following steps:

[0049] Obtain ecological function data and ecological structure data of river restoration areas.

[0050] The ecological function data were analyzed based on the deep learning model, and the vertical distribution model of photosynthesis efficiency was constructed by combining the hierarchical analysis method to evaluate the differences in photosynthesis contributions at different water depths.

[0051] Based on ecological structure data, the migration characteristics of key nutrients at the interface between vegetation and sediment in the river restoration area are monitored, and the interface coupling model is used to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery.

[0052] A comprehensive analysis is conducted on the differences in photosynthesis contribution at different water depths, the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery, and a comprehensive evaluation index reflecting the health status of vegetation and the degree of ecological recovery is generated.

[0053] The ecological restoration effect of the river restoration area is evaluated based on comprehensive evaluation indicators, and a restoration effect report is output.

[0054] Obtain ecological function data and ecological structure data of the river restoration area, including:

[0055] Ecological function data include photosynthesis efficiency data of aquatic vegetation and water depth data collected by sensors:

[0056] Multi-point optical sensors are arranged in the river restoration area. The sensors are installed on fixed brackets at different water depths and can monitor the photosynthesis efficiency of aquatic vegetation under natural light conditions in real time. The data collected by the sensors include photosynthetic rate, chlorophyll concentration and dynamic changes of dissolved oxygen, all recorded in the form of time series. During collection, the sensor calibration needs to be based on the local water quality transparency to avoid the deviation of photosynthesis efficiency data due to interference from suspended particles in the water.

[0057] Water depth data is collected by deploying ultrasonic water depth measurement equipment, which is installed at different representative locations in the river restoration area, such as the mainstream area and the densely vegetated area, covering the main water depth gradients in the restoration area. The equipment records water level changes in real time and stores the data as daily measurements, ensuring high-precision water depth information at every point in time.

[0058] Ecological structure data include vegetation distribution data obtained through remote sensing technology, sediment interface data obtained through on-site testing, and key nutrient data obtained through chemical analysis methods:

[0059] High-resolution remote sensing image technology is used to obtain vegetation distribution data, and drones equipped with multispectral sensors are selected to conduct full coverage scanning of the restoration area to generate a refined vegetation spatial distribution map. Remote sensing images extract the distribution range and coverage of aquatic vegetation in the river restoration area through vegetation indices (such as NDVI), and identify changes in vegetation distribution density. After data collection is completed, the remote sensing images are orthorectified to eliminate geometric distortion caused by the tilt of the aircraft.

[0060] The sediment interface data was obtained through on-site testing methods. Representative water sample points in the restoration area were selected. The sediment surface samples were collected using sediment sampling equipment, and the sampling depth and geographic coordinate information were recorded. The physical properties (such as particle size distribution) and chemical properties (such as organic matter content and pH value) of the sediment samples were tested using laboratory analysis methods to quantify the sediment interface characteristics. In addition, an underwater laser scanner was used to scan the sediment interface morphology to generate a high-resolution sediment topography map.

[0061] The key nutrient data in river water and sediment are obtained through chemical analysis methods. Water samples from sampling points are selected, and the concentration of nutrients such as nitrogen and phosphorus in the water is detected by ion chromatography; for sediment samples, the total amount and effective content of nitrogen and phosphorus are determined by high-temperature digestion combined with spectral analysis. Each sampling data is associated with the sampling location, water depth and sediment characteristics to ensure the spatial consistency of the data.

[0062] The collected ecological function data and ecological structure data are preprocessed and normalized through multimodal data fusion technology:

[0063] The collected ecological function data and ecological structure data are subjected to multimodal data fusion processing to eliminate redundancy and inconsistency between data. A multimodal fusion algorithm based on a probabilistic graphical model is used to unify photosynthesis efficiency data, water depth data, vegetation distribution data, sediment interface data and key nutrient data. The data fusion process matches the grid range of vegetation distribution data with sediment interface data and water depth data according to the spatial distribution characteristics to form a multi-level spatial correlation matrix. At the same time, wavelet denoising technology is used to eliminate environmental noise that may exist in the sampling process, such as sensor interference in photosynthesis efficiency data or sudden fluctuations in water depth data.

[0064] The collected data were converted into different formats, including photosynthesis efficiency data and water depth data into time-space format, vegetation distribution data into raster layers, and sediment interface data into high-resolution vector models. For missing data, such as missing photosynthesis efficiency data at certain time points due to equipment failure, an interpolation method based on local weighted regression was used to complete the data input to ensure complete data input.

[0065] The data were normalized to unify the dimensions and ranges of different data. The photosynthesis efficiency data were converted into a ratio of 0 to 1 through the maximum and minimum normalization method; the water depth data were scaled based on the maximum water depth of the restoration area; the vegetation distribution data were converted into percentage coverage through pixel value normalization; the sediment interface data and key nutrient data were z-score normalized based on the sample mean and standard deviation, respectively. The normalized data was stored as a standardized feature set to facilitate the input and analysis of subsequent deep learning models.

[0066] Based on the deep learning model, the ecological function data was analyzed, and the vertical distribution model of photosynthesis efficiency was constructed by combining the hierarchical analysis method to evaluate the differences in photosynthesis contribution at different water depths, including:

[0067] The deep learning model is used to extract features from photosynthesis efficiency data and water depth data, and a spatial distribution model of vegetation photosynthesis efficiency is constructed:

[0068] The preprocessed photosynthesis efficiency data and water depth data were used as the input of the deep learning model, and the convolutional neural network (CNN) was used for feature extraction. The input data included multidimensional time series data (such as the changing trend of photosynthesis efficiency) and spatial attribute data (such as the geographic coordinates and water depth values ​​of each monitoring point). The initial parameters of the model were initialized by an optimization algorithm based on the gradient descent method.

[0069] The convolutional layer of CNN is used to extract the spatial distribution characteristics of photosynthesis efficiency data. The size of the convolution kernel is set to a 3×3 grid according to the water depth gradient to capture the photosynthesis variation pattern in the spatial neighborhood. At the same time, the data is reduced in dimension through the pooling layer to reduce the amount of calculation and retain the main features. Finally, a preliminary spatial distribution model of vegetation photosynthesis efficiency is generated, which contains the predicted values ​​of photosynthesis efficiency in each region and its correlation with water depth.

[0070] The extracted features are mapped into a relationship diagram between water depth and photosynthesis efficiency through the fully connected layer. The preliminary results may be biased. The parameters of the convolution layer and the pooling layer are adjusted through the back propagation algorithm to further correct the model output and ensure the accuracy of the photosynthesis efficiency spatial distribution model.

[0071] The water depth data is divided into multiple depth levels, and the photosynthesis efficiency data in each depth level are statistically calculated according to the hierarchical analysis method to generate the characteristic value of photosynthesis efficiency in each depth level:

[0072] According to the water depth data range of the river restoration area, the water depth is divided into several depth levels, such as 0-1m, 1-2m, 2-3m, etc., with an interval of 1m. Each depth level contains its corresponding photosynthesis efficiency data point to ensure that the data distribution is representative.

[0073] Statistical analysis is performed on the photosynthesis efficiency data of each depth level, including but not limited to calculating the mean value, variance and range of variation, to generate characteristic values ​​of photosynthesis efficiency at each depth level.

[0074] Based on the results of hierarchical analysis, the spatial distribution model of photosynthesis efficiency was corrected through the model parameter optimization algorithm, and the vertical distribution model of photosynthesis efficiency was constructed:

[0075] Based on the spatial distribution characteristics extracted by the deep learning model and the hierarchical analysis results, a preliminary vertical distribution model of photosynthesis efficiency was constructed. The model formula is as follows: M(z) = α·f(z) + β; where M(z) represents the trend of photosynthesis efficiency with water depth, z represents water depth, α and β are model parameters, and f(z) is the interpolation function of the characteristic value of photosynthesis efficiency obtained by hierarchical analysis.

[0076] Using the parameter optimization algorithm based on the gradient descent method, the values ​​of α and β are iteratively adjusted to minimize the error between the model output and the actual stratified data; the optimization objective function is defined as: Among them, L represents the objective function value, that is, the loss value of the model, which reflects the error between the model prediction result and the actual observation data; N represents the number of water depth levels, that is, the total number of independent depth ranges into which the water depth is divided, such as 0-1m, 1-2m, etc.; i represents the water depth of the i-th layer, corresponding to the depth of each layer; M(z i ) represents the predicted photosynthesis efficiency value of the model at the i-th water depth; It represents the characteristic value of photosynthesis efficiency actually observed in the i-th layer, that is, the average photosynthesis efficiency calculated by stratified analysis.

[0077] The vertical distribution model was used to quantitatively evaluate the differences in photosynthesis contributions at different water depths:

[0078] According to the vertical distribution model, the contribution of photosynthesis efficiency at different water depths to overall photosynthesis is calculated; the formula is as follows: Among them, C i Indicates the contribution of the i-th layer water depth to the overall photosynthesis; μ i represents the average photosynthesis efficiency of the i-th layer of water depth; V i represents the water volume of the i-th water depth, which is calculated based on the layered water depth range and the area of ​​the repair region, and is used to measure the actual impact range of the water depth layer; j is the index of the water depth layer, ranging from 1 to N; μ j is the average photosynthesis efficiency of the jth layer; V j is the volume of water in the jth layer; i is the index of the current layer, which is used to calculate the specific contribution ratio C of this layer i ; j is a loop variable used to iterate through all levels to calculate the total contribution to overall photosynthesis.

[0079] The contribution ratio of each level is output as a table or graphical result to support subsequent comprehensive analysis and decision-making. The evaluation results can reflect the distribution law of photosynthesis in different water depth areas of the river channel and provide data support for the comprehensive evaluation of ecological restoration effects.

[0080] Based on ecological structure data, the migration characteristics of key nutrients at the interface between vegetation and sediment in the river restoration area are monitored, and the interface coupling model is used to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery, including:

[0081] Based on the vegetation distribution data, the vegetation coverage in the restoration area is determined, and the vegetation root distribution area is calibrated in combination with the sediment interface data, and the concentration data of key nutrients at the sediment interface are obtained:

[0082] The vegetation distribution data obtained by high-resolution remote sensing images are used to extract the vegetation coverage in the restoration area, and the vegetation coverage rate is calculated through multispectral images. The normalized difference vegetation index (NDVI) algorithm is used to identify the vegetation coverage area, and the calculation formula is as follows: Among them, Rnir represents the reflectance of the near-infrared band, Rred represents the reflectance of the red light band, and NDVI represents the normalized difference vegetation index.

[0083] The effective vegetation distribution area is identified by setting a threshold, and a spatial raster map of the vegetation coverage is generated.

[0084] Combined with the sediment interface data, the depth range of vegetation root growth is calibrated. The possible distribution depth of vegetation roots is determined by the particle size distribution, water content and organic matter content of the sediment samples, and a three-dimensional spatial model of vegetation root distribution is established for subsequent analysis.

[0085] Using key nutrient data, an interfacial nutrient migration model was established to calculate the migration rate of key nutrients from the bottom mud to the vegetation root zone:

[0086] Ion chromatography was used to detect the concentration of key nutrients (such as nitrogen and phosphorus) in sediment samples, and the concentration of key nutrients was spatially interpolated in combination with the raster map of the vegetation distribution area. The spatial distribution of key nutrients in the entire restoration area was calculated using the Kriging interpolation algorithm to generate the initial input data for the migration model.

[0087] The migration rate of key nutrients is calculated by the diffusion-convection equation, and the model formula is as follows: Among them, R m It represents the migration rate of key nutrients, that is, the speed at which key nutrients migrate from the sediment interface to the vegetation root area per unit time. eff represents the effective diffusion coefficient of key nutrients, which is used to describe the diffusion capacity of nutrients in the sediment interface area. C represents the concentration of key nutrients, which is used to reflect the nutrient content at a certain position in the sediment interface. h represents the depth coordinate of the sediment interface. v h It represents the convection velocity of nutrients in the depth direction and is used to describe the migration rate of nutrients in the sediment interface due to convection. It represents the second-order partial derivative of the key nutrient concentration in the depth direction, which is used to describe the rate of change of the concentration gradient and reflect the changing trend in the diffusion process. It represents the first-order partial derivative of the concentration of key nutrients in the depth direction, which is used to describe the magnitude of the concentration gradient and reflect the direction and rate of concentration change during convective migration.

[0088] By numerically solving the above formula, the migration rate of nutrients from each depth zone to the vegetation root zone is calculated.

[0089] Based on the output of the interfacial nutrient transport model and combined with the vegetation distribution data, the total nutrient absorption in the vegetation root area is calculated:

[0090] The nutrient absorption rate of the vegetation root zone is calculated by the absorption kinetic model, and the model formula is as follows: Among them, U represents the nutrient absorption rate per unit time, V max Indicates the maximum absorption rate of nutrients by vegetation roots, C r represents the nutrient concentration in the root zone of vegetation, K m It represents the half-saturation constant of nutrient absorption by vegetation roots.

[0091] The total amount of nutrient absorption in the vegetation root area is calculated by spatial integration, and the calculation formula is as follows: Q total =∫ A U·dA; among them, Q total It represents the total absorption of the vegetation root area, and A represents the spatial range of the root distribution area.

[0092] The interface coupling model is used to match the nutrient supply rate of the sediment interface with the nutrient absorption rate of the vegetation root area, and the nutrient supply and demand balance value is calculated:

[0093] The interface coupling model is used to match the nutrient supply rate of the sediment interface and the absorption rate of the vegetation roots to calculate the nutrient supply and demand balance value. The formula is as follows: Among them, B represents the balance value of nutrient supply and demand, R supply Represents the total amount of nutrients provided by the sediment interface, R demand Indicates the total nutrient requirement for vegetation roots.

[0094] The nutrient supply and demand balance value and vegetation distribution data are used to further generate the supply and demand balance index to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery:

[0095] Based on the nutrient supply and demand balance value and vegetation distribution data, the supply and demand balance index is generated to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery. The calculation formula is as follows: Among them, I balance represents the supply and demand balance index, A vegIndicates the area of ​​vegetation coverage, A total Represents the total area of ​​the repair region.

[0096] GIS tools were used to visualize the spatial distribution of the supply-demand balance index and generate a dynamic supply-demand balance map to evaluate the overall status of vegetation growth recovery.

[0097] The larger the supply-demand balance index is, the more sufficient the nutrient supply is relative to the vegetation growth demand, and the more stable and sufficient the dynamic relationship between nutrient supply-demand balance and vegetation growth recovery is. This means that vegetation can obtain enough key nutrients from the sediment interface to support its growth recovery, and the balance and restoration effect of the ecosystem are better.

[0098] The differences in photosynthesis contribution at different water depths and the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery are comprehensively analyzed to generate comprehensive evaluation indicators reflecting the health status of vegetation and the degree of ecological recovery, including:

[0099] Based on the differences in photosynthesis contribution at different water depths, a photosynthesis contribution matrix was constructed, in which each matrix element corresponds to the photosynthesis efficiency at the water depth and its proportion in the overall contribution:

[0100] The difference in photosynthesis contribution comes from the analysis results of photosynthesis efficiency and water depth. For each water depth level, the ratio of its photosynthesis efficiency to the overall photosynthesis efficiency is calculated to form a photosynthesis contribution matrix.

[0101] Each element of the photosynthesis contribution matrix is ​​defined as the contribution ratio of photosynthesis of a certain water depth level in a certain area. The ratio is calculated as follows:

[0102] First, multiply the photosynthesis efficiency value by the water volume to obtain the total photosynthesis contribution value of the area;

[0103] Then, divide the contribution value by the total contribution value of all areas in the water depth level to obtain the proportion.

[0104] Each matrix element represents the contribution ratio of the water depth level in the area.

[0105] For example, the photosynthesis contribution ratio of a certain area is calculated as follows: first, multiply the photosynthesis efficiency of the area by the water volume to obtain the local contribution value; then divide the local contribution value by the sum of all local contribution values ​​of the water depth level to obtain the ratio of the area.

[0106] Based on the supply-demand balance index and vegetation coverage, a supply-demand balance matrix is ​​constructed, in which each matrix element corresponds to the ratio of the supply-demand balance index to the vegetation coverage rate:

[0107] The supply-demand balance index is derived from the analysis results of the nutrient supply-demand balance state and is used to express the balance relationship between nutrient supply and demand. Combined with the vegetation coverage, a supply-demand balance matrix can be constructed.

[0108] Each element of the supply-demand balance matrix is ​​defined as the result of multiplying the supply-demand balance index of a certain area by the vegetation coverage rate. The specific calculation method is as follows:

[0109] First, determine the supply-demand balance index of the region; then, multiply the index by the vegetation coverage rate of the region to obtain the corresponding value in the matrix; each matrix element represents the comprehensive correlation value between the supply-demand balance and the vegetation coverage rate of the region.

[0110] The photosynthesis contribution matrix and the supply-demand balance matrix are weighted and superimposed, and a comprehensive analysis matrix is ​​generated using a multidimensional data fusion algorithm. The matrix elements represent the comprehensive ecological contribution values ​​of different water depths:

[0111] Set the weights between photosynthesis contribution and supply-demand balance, and the sum of the weights is 1. The weights of photosynthesis contribution and supply-demand balance are used to reflect the importance of the two.

[0112] Each element of the comprehensive analysis matrix is ​​calculated by: multiplying the value in the photosynthesis contribution matrix by the weight of the photosynthesis contribution; multiplying the value in the supply and demand balance matrix by the weight of the supply and demand balance; adding these two weighted values ​​to obtain the element value in the comprehensive analysis matrix.

[0113] For example, the comprehensive analysis matrix value of a certain area is calculated as: the photosynthesis contribution value multiplied by the photosynthesis weight; the supply and demand balance value multiplied by the supply and demand balance weight; the sum of the two is the comprehensive ecological contribution value of the area.

[0114] The comprehensive analysis matrix was normalized and combined with vegetation distribution data to generate comprehensive evaluation indicators that reflect the health status of vegetation and the degree of ecological restoration:

[0115] All values ​​of the comprehensive analysis matrix are normalized to a range between zero and one. The normalization method is as follows: First, find the maximum and minimum values ​​in the comprehensive analysis matrix; then, subtract the minimum value from each value in the matrix and divide it by the difference between the maximum and minimum values; after normalization, each value is expressed as a relative value in the range of zero to one.

[0116] The normalized comprehensive analysis matrix and vegetation distribution data are used to calculate the comprehensive evaluation index of the region. The specific method is as follows: multiply the value of the normalized matrix by the area of ​​the vegetation coverage area to obtain the weighted value; add up all the weighted values ​​and divide them by the total area of ​​the region to obtain the comprehensive evaluation index.

[0117] The comprehensive evaluation index represents the comprehensive ecological status of the entire region; the larger the comprehensive evaluation index, the higher the vegetation health status and ecological recovery degree in the region, which indicates that the comprehensive performance of the region in ecological function and structure is superior, the photosynthesis efficiency at the water depth level contributes more to the overall, the nutrient supply and demand balance index matches the vegetation coverage to a high degree, and the dynamic relationship between vegetation growth and recovery is stable and sufficient. Higher evaluation indicators also reflect that the supply of nutrients in the ecosystem can meet or even exceed the demand for vegetation growth, and the spatial distribution of photosynthesis efficiency is balanced and reasonable. Therefore, the comprehensive evaluation index can be used as a comprehensive measurement tool to quantitatively evaluate the vegetation health status and ecological recovery degree, and guide the optimization of river restoration effects and regional ecological planning.

[0118] Evaluate the ecological restoration effect of the river restoration area based on comprehensive evaluation indicators and output a restoration effect report, including:

[0119] Based on the comprehensive evaluation indicators, the evaluation results are divided into multiple ecological restoration effect levels according to the preset classification rules, where the classification rules include the distribution range of the comprehensive evaluation indicators and the corresponding level thresholds:

[0120] The preset classification rules are based on the distribution range of the comprehensive evaluation indicators and divide the indicator values ​​into several levels. Each level is defined by a corresponding threshold range, for example:

[0121] Areas with a comprehensive evaluation index less than 0.3 are defined as low restoration effect levels; areas with a comprehensive evaluation index between 0.3 and 0.7 are defined as medium restoration effect levels; and areas with a comprehensive evaluation index greater than 0.7 are defined as high restoration effect levels.

[0122] Classification rules clarify the range of each level by setting threshold intervals to ensure consistency in classification results.

[0123] According to the set classification rules, the spatial distribution data of the comprehensive evaluation index is traversed one by one, and the index value of each area is mapped to the corresponding restoration effect level. The result is saved in the form of a raster map, in which the value of each pixel represents its restoration effect level.

[0124] According to the spatial distribution results of the comprehensive evaluation index, the restoration effect distribution map of each sub-region in the region is generated, where the restoration effect level of each sub-region corresponds to the level of its comprehensive evaluation index value:

[0125] Based on the classified restoration effect level data, the restoration effect level of each sub-area is visualized in the form of a spatial distribution map. In the distribution map, different colors are used to mark each restoration effect level area, and the color depth corresponds to the level. For example: red indicates a low restoration effect level; yellow indicates a medium restoration effect level; and green indicates a high restoration effect level.

[0126] According to the actual scope of the river restoration area and the required accuracy, the spatial resolution of the restoration effect distribution map is set to ensure that the distribution map can not only clearly reflect the regional restoration effect, but also meet the needs of subsequent analysis.

[0127] Based on the restoration effect distribution map, the restoration effect statistics of the entire area are extracted, including the distribution ratio of the restoration effect level, the area proportion of areas with different levels, etc.:

[0128] By counting the number of pixels at each level in the restoration effect distribution map, the distribution ratio of each restoration effect level is calculated. The distribution ratio of the restoration effect level is the ratio of the number of pixels at a certain restoration effect level to the total number of pixels.

[0129] According to the number of pixels at each restoration effect level in the distribution map and the actual area corresponding to each pixel, the area proportion of each level is calculated.

[0130] The area proportion of a certain grade is the ratio of the total area of ​​the area of ​​a certain grade to the total area of ​​the restoration area.

[0131] The distribution ratio and area proportion of the restoration effect level are saved in a table format to facilitate subsequent summary and report generation.

[0132] The restoration effect distribution map and restoration effect statistical information are summarized to generate an ecological restoration effect report for the river restoration area. The restoration effect report includes a restoration effect grade distribution map, a statistical data table, and a summary of the classification results:

[0133] The restoration effect report includes the following parts: restoration effect level distribution map: showing the spatial distribution of restoration effects in the area, marking the regional scope of each level; statistical data table: showing the distribution ratio and area share of each restoration effect level in tabular form; summary of classification results: briefly describing the classification rules and result summary of restoration effect evaluation.

[0134] The restoration effect report is generated in the form of a PDF file with detailed descriptions of distribution maps and statistical tables. The report can be used for quantitative evaluation of river restoration effects and optimization scheme design.

[0135] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0136] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0137] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0138] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0139] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0140] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0141] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0142] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0143] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0144] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A river ecological restoration effect evaluation method based on comprehensive data analysis, characterized in that: The steps include: S1: Obtain ecological function data and ecological structure data of the river restoration area; ecological function data include photosynthesis efficiency data and water depth data, and ecological structure data include vegetation distribution data, sediment interface data, and key nutrient data; S2: Analyze ecological function data based on deep learning models, and build a vertical distribution model of photosynthesis efficiency in combination with hierarchical analysis methods to evaluate the differences in photosynthesis contributions at different water depths; S3: Based on ecological structure data, the migration characteristics of key nutrients at the interface between vegetation and sediment in the river restoration area are monitored, and the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery is quantified using the interface coupling model; S4: Comprehensively analyze the differences in photosynthesis contribution and nutrient supply and demand balance at different water depths and the dynamic relationship between vegetation growth and recovery, and generate comprehensive evaluation indicators that reflect the health status of vegetation and the degree of ecological recovery; S5: Evaluate the ecological restoration effect of the river restoration area based on comprehensive evaluation index analysis and output a restoration effect report.

2. The river ecological restoration effect evaluation method based on comprehensive data analysis according to claim 1 is characterized in that: Obtain ecological function data and ecological structure data of the river restoration area, including: Ecological function data include photosynthesis efficiency data of aquatic vegetation and water depth data collected by sensors; Ecological structure data include vegetation distribution data obtained through remote sensing technology, sediment interface data obtained through field testing, and key nutrient data obtained through chemical analysis methods; The collected ecological function data and ecological structure data are preprocessed and normalized through multimodal data fusion technology.

3. The river ecological restoration effect evaluation method based on comprehensive data analysis according to claim 2 is characterized in that: Based on the deep learning model, the ecological function data was analyzed, and the vertical distribution model of photosynthesis efficiency was constructed by combining the hierarchical analysis method to evaluate the differences in photosynthesis contribution at different water depths, including: Use deep learning models to extract features from photosynthesis efficiency data and water depth data, and build a spatial distribution model of vegetation photosynthesis efficiency; The water depth data is divided into multiple depth levels, and the photosynthesis efficiency data in each depth level are statistically calculated according to the hierarchical analysis method to generate the photosynthesis efficiency characteristic value of each depth level; Based on the results of hierarchical analysis, the spatial distribution model of photosynthesis efficiency was corrected through the model parameter optimization algorithm, and the vertical distribution model of photosynthesis efficiency was constructed; The differences in photosynthesis contributions at different water depths were quantitatively evaluated using a vertical distribution model.

4. The river ecological restoration effect evaluation method based on comprehensive data analysis according to claim 3 is characterized in that: Based on ecological structure data, the migration characteristics of key nutrients at the interface between vegetation and sediment in the river restoration area are monitored, and the interface coupling model is used to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery, including: Determine the vegetation coverage in the restoration area based on vegetation distribution data, calibrate the vegetation root distribution area based on sediment interface data, and obtain the concentration data of key nutrients at the sediment interface; Using key nutrient data, an interfacial nutrient migration model was established to calculate the migration rate of key nutrients from sediment to the vegetation root zone; Based on the output of the interfacial nutrient transport model and combined with vegetation distribution data, the total nutrient uptake in the vegetation root zone is calculated; The interface coupling model is used to match the nutrient supply rate of the sediment interface with the nutrient absorption rate of the vegetation root zone to calculate the nutrient supply and demand balance value. The nutrient supply and demand balance value and vegetation distribution data are used to further generate a supply and demand balance index to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery.

5. The river ecological restoration effect evaluation method based on comprehensive data analysis according to claim 4 is characterized in that: Based on the output of the interface nutrient migration model and combined with the vegetation distribution data, the total nutrient absorption of the vegetation root area is calculated. Specifically, the nutrient absorption rate of the vegetation root area is calculated by the absorption kinetics model: Among them, U represents the nutrient absorption rate per unit time, V max Indicates the maximum absorption rate of nutrients by vegetation roots, C r represents the nutrient concentration in the root zone of vegetation, K m It represents the half-saturation constant of nutrient absorption by vegetation roots; The total amount of nutrients absorbed by the vegetation root area is calculated by spatial integration: Q total =∫ A U·dA; among them, Q total It represents the total absorption of the vegetation root area, and A represents the spatial range of the root distribution area.

6. The river ecological restoration effect evaluation method based on comprehensive data analysis according to claim 5 is characterized in that: The interface coupling model is used to match the nutrient supply rate of the sediment interface with the nutrient absorption rate of the vegetation root area, and the nutrient supply and demand balance value is calculated: The interface coupling model is used to match the nutrient supply rate at the sediment interface and the absorption rate of the vegetation roots to calculate the nutrient supply and demand balance value: Among them, B represents the balance value of nutrient supply and demand, R supply Represents the total amount of nutrients provided by the sediment interface, R demand Indicates the total nutrient requirement for vegetation roots.

7. The river ecological restoration effect evaluation method based on comprehensive data analysis according to claim 6 is characterized in that: The nutrient supply and demand balance value and vegetation distribution data are used to further generate the supply and demand balance index to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery: Based on the nutrient supply and demand balance value and vegetation distribution data, a supply and demand balance index is generated to quantify the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery: Among them, I balance represents the supply and demand balance index, A veg Indicates the area of ​​vegetation coverage, A total Represents the total area of ​​the repair region.

8. The river ecological restoration effect evaluation method based on comprehensive data analysis according to claim 7 is characterized in that: The differences in photosynthesis contribution at different water depths and the dynamic relationship between nutrient supply and demand balance and vegetation growth recovery are comprehensively analyzed to generate comprehensive evaluation indicators reflecting the health status of vegetation and the degree of ecological recovery, including: Based on the differences in photosynthesis contribution at different water depths, a photosynthesis contribution matrix was constructed, in which each matrix element corresponds to the photosynthesis efficiency of the water depth and its proportion in the overall contribution. Based on the supply-demand balance index and vegetation coverage, a supply-demand balance matrix is ​​constructed, in which each matrix element corresponds to the ratio of the supply-demand balance index to the vegetation coverage rate; The photosynthesis contribution matrix and the supply-demand balance matrix are weighted and superimposed, and a comprehensive analysis matrix is ​​generated using a multidimensional data fusion algorithm. The matrix elements represent the comprehensive ecological contribution values ​​of different water depth levels. The comprehensive analysis matrix was normalized and combined with vegetation distribution data to generate a comprehensive evaluation index that reflects the health status of vegetation and the degree of ecological restoration.

9. The river ecological restoration effect evaluation method based on comprehensive data analysis according to claim 8 is characterized in that: Evaluate the ecological restoration effect of the river restoration area based on comprehensive evaluation indicators and output a restoration effect report, including: Based on the comprehensive evaluation indicators, the evaluation results are divided into multiple ecological restoration effect levels according to the preset classification rules, where the classification rules include the distribution range of the comprehensive evaluation indicators and the corresponding level thresholds; According to the spatial distribution results of the comprehensive evaluation index, a restoration effect distribution map of each sub-region in the region is generated, in which the restoration effect level of each sub-region corresponds to the level of its comprehensive evaluation index value; Extract the restoration effect statistics of the whole area based on the restoration effect distribution map, including the distribution ratio of restoration effect levels and the area proportion of areas with different levels; The restoration effect distribution map and restoration effect statistical information are summarized to generate an ecological restoration effect report for the river restoration area. The restoration effect report includes a restoration effect grade distribution map, statistical data tables, and a summary of the classification results.

Images