Ecological environment dynamic evaluation and management method based on spatio-temporal data analysis

Abstract

The invention provides an ecological environment dynamic evaluation and management method based on spatio-temporal data analysis, and relates to the technical field of ecological environment monitoring, and the method comprises the steps: collecting multi-source ecological environment data, and cleaning the data to obtain cleaning data; and data fusion is carried out by adopting spatial interpolation and time sequence analysis, an ecological environment quality index is calculated, and a dynamic change trend is identified. And in combination with a future change result and a management target, an optimization strategy is formulated, and a multi-target optimization algorithm is applied to generate an optimal management scheme. According to the method, the accuracy of ecological environment monitoring and evaluation is improved, scientific decision support is provided for managers, and sustainable development is assisted.

Description

Technical Field

[0001] The present invention relates to the technical field of ecological environment monitoring, and in particular to a method for dynamic evaluation and management of ecological environment based on spatiotemporal data analysis. Background Art

[0002] With the intensification of global climate change and human activities, the dynamic changes of the ecological environment have had a profound impact on social and economic development and the stability of the ecosystem. Traditional ecological environmental assessment methods usually rely on static data or monitoring data at a single time point, which is difficult to fully reflect the dynamic changes of the ecological environment. In addition, existing methods have deficiencies in data integration, spatiotemporal analysis, and dynamic prediction, and cannot effectively support the scientific management and decision-making of the ecological environment.

[0003] In recent years, with the rapid development of remote sensing technology, geographic information system (GIS) and big data analysis technology, dynamic ecological environment assessment based on spatiotemporal data has become possible. However, how to efficiently integrate, analyze and model multi-source spatiotemporal data and apply the analysis results to ecological environment management is still a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a dynamic ecological environment assessment and management method based on spatiotemporal data analysis, which provides a comprehensive, dynamic, scientific and operational ecological environment assessment and management method by integrating multi-source data, dynamic assessment models and optimization algorithms. Its beneficial effects are not only reflected in the precise monitoring and assessment of the ecological environment, but also provide managers with scientific decision-making support tools, which can significantly improve the efficiency and effectiveness of ecological environment protection and help achieve the sustainable development of the ecological environment.

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

[0006] A method for dynamic assessment and management of ecological environment based on spatiotemporal data analysis, including:

[0007] Collect multi-source ecological and environmental data;

[0008] Cleaning the multi-source ecological environment data to obtain cleaned data;

[0009] Using a spatial interpolation method and a time series analysis method to perform spatiotemporal data fusion on the cleaned data to obtain a fused spatiotemporal data set;

[0010] Inputting the fused spatiotemporal data set into the trained dynamic assessment model to obtain the future ecological environment change results;

[0011] Calculating an ecological environment quality index based on the fused spatiotemporal data set, and using a spatiotemporal statistical analysis method to identify a dynamic change trend of the ecological environment on the fused spatiotemporal data set;

[0012] According to the future ecological environment change results, the ecological environment quality index and the dynamic change trend, combined with the ecological environment management goals, an optimization strategy is formulated, and a multi-objective optimization algorithm is used to optimize the optimization strategy to generate the optimal management plan.

[0013] Preferably, the multi-source ecological environment data includes remote sensing image data, meteorological data, ground monitoring data and socio-economic data.

[0014] Preferably, the multi-source ecological environment data is cleaned to obtain cleaned data, including:

[0015] The multi-source ecological environment data are grouped according to a preset collection period to obtain a plurality of data groups;

[0016] Calculate the difference coefficient between the current data group and the previous data group in sequence;

[0017] Determine whether the value of the coefficient of difference is within a preset range;

[0018] If the value of the difference coefficient is not within the preset range, the corresponding data group is removed;

[0019] If the value of the difference coefficient is within a preset range, the corresponding data group is retained until all data groups are traversed to obtain the cleaned data.

[0020] Preferably, the difference coefficient calculation formula is:

[0021]

[0022] Among them, p X,Y is the coefficient of difference, cov(X,Y) represents the covariance between the current data set X and the previous data set Y, α X represents the mean of the current data set X, β Y Represents the mean of the previous data set Y.

[0023] Preferably, the cleaned data is subjected to spatiotemporal data fusion using a spatial interpolation method and a time series analysis method to obtain a fused spatiotemporal data set, including:

[0024] Unifying the cleaned data into a standard space-time grid format, and adding a timestamp and spatial coordinates to each data point in the space-time grid;

[0025] Based on the Kriging interpolation method, spatial interpolation is performed on the data at each time point in the space-time grid to generate complete spatial distribution data;

[0026] Performing time series analysis on the data of each spatial position in the spatial distribution data to fill in missing values ​​in time and smooth the time series to obtain time analysis data;

[0027] The spatial distribution data and the time analysis data are subjected to spatiotemporal data fusion to obtain the fused spatiotemporal data set.

[0028] Preferably, time series analysis is performed on the data of each spatial position in the spatial distribution data to fill in missing values ​​in time and smooth the time series to obtain time analysis data, including:

[0029] Extracting time series from data at each spatial location;

[0030] The time series is predicted and interpolated according to the LSTM long short-term memory network, missing values ​​in the time interval are filled, and time series fluctuations are smoothed to obtain the time analysis data.

[0031] Preferably, the dynamic evaluation model is a CNN-LSTM combined model.

[0032] Preferably, the calculation formula of the ecological environment quality index is:

[0033] EQI=w1·NDVI+w2·AQI+w3·WQI+w4·LUI+w5·SEI

[0034] Among them: EQI is the ecological environment quality index, ranging from 0 to 1, and the higher the value, the better the ecological environment quality; NDVI is the normalized vegetation index, which reflects the vegetation coverage; AQI is the air quality index, which reflects the degree of air pollution; WQI is the water quality index, which reflects the degree of water pollution; LUI is the land use intensity index, which reflects the intensity of human activities on land resources; SEI is the socio-economic index, which reflects the impact of socio-economic development on the ecological environment; w1, w2, w3, w4 and w5 are weight coefficients, which indicate the relative importance of each indicator to the ecological environment quality, satisfying w1+w2+w3+w4+w5=1.

[0035] Preferably, the spatiotemporal statistical analysis method is based on the Mann-Kendall trend test method.

[0036] Preferably, the multi-objective optimization algorithm is a particle swarm optimization algorithm.

[0037] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0038] The present invention provides an ecological environment dynamic assessment and management method based on spatiotemporal data analysis, including: collecting multi-source ecological environment data; cleaning the multi-source ecological environment data to obtain cleaned data; using spatial interpolation method and time series analysis method to perform spatiotemporal data fusion on the cleaned data to obtain a fused spatiotemporal data set; inputting the fused spatiotemporal data set into a trained dynamic assessment model to obtain future ecological environment change results; calculating the ecological environment quality index based on the fused spatiotemporal data set, and using a spatiotemporal statistical analysis method to identify the dynamic change trend of the ecological environment for the fused spatiotemporal data set; according to the future ecological environment change results, the ecological environment quality index and the dynamic change trend, combined with the ecological environment management goals, formulating an optimization strategy, and using a multi-objective optimization algorithm to optimize the optimization strategy to generate an optimal management plan. The present invention provides a comprehensive, dynamic, scientific and operable ecological environment assessment and management method by integrating multi-source data, dynamic assessment models and optimization algorithms. Its beneficial effects are not only reflected in the precise monitoring and assessment of the ecological environment, but also provide managers with scientific decision-making support tools, which can significantly improve the efficiency and effect of ecological environment protection and help achieve sustainable development of the ecological environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0040] Figure 1 A flow chart of a method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] 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.

[0042] The purpose of this invention is to provide a dynamic ecological environment assessment and management method based on spatiotemporal data analysis, which provides a comprehensive, dynamic, scientific and operational ecological environment assessment and management method by integrating multi-source data, dynamic assessment models and optimization algorithms. Its beneficial effects are not only reflected in the precise monitoring and assessment of the ecological environment, but also provide managers with scientific decision-making support tools, which can significantly improve the efficiency and effectiveness of ecological environment protection and help achieve sustainable development of the ecological environment.

[0043] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0044] Figure 1 A flow chart of a method provided by an embodiment of the present invention, such as Figure 1 As shown, the present invention provides a method for dynamic evaluation and management of ecological environment based on spatiotemporal data analysis, comprising:

[0045] Step 100: Collect multi-source ecological environment data;

[0046] Step 200: Cleaning multi-source ecological environment data to obtain cleaned data;

[0047] Step 300: Using a spatial interpolation method and a time series analysis method to perform spatiotemporal data fusion on the cleaned data to obtain a fused spatiotemporal data set;

[0048] Step 400: Input the fused spatiotemporal data set into the trained dynamic assessment model to obtain the future ecological environment change results;

[0049] Step 500: Calculate the ecological environment quality index based on the fused spatiotemporal data set, and use spatiotemporal statistical analysis methods to identify the dynamic change trend of the ecological environment on the fused spatiotemporal data set;

[0050] Step 600: According to the future ecological environment change results, ecological environment quality index and dynamic change trend, combined with the ecological environment management goals, an optimization strategy is formulated, and a multi-objective optimization algorithm is used to optimize the optimization strategy to generate an optimal management plan.

[0051] Preferably, the multi-source ecological environment data includes remote sensing image data, meteorological data, ground monitoring data and socio-economic data.

[0052] Specifically, step 100 of this embodiment includes:

[0053] Step 101: Remote sensing image data collection

[0054] Remote sensing image data is obtained through satellite remote sensing platforms (such as Landsat, Sentinel, MODIS, etc.) or drones, mainly including multispectral image data reflecting surface characteristics (such as red light and near-infrared bands) as well as information such as surface temperature and vegetation coverage. In addition, high-resolution or medium-resolution image data can be selected according to the specific needs of the study area to ensure that the data covers the entire target area, and image data within the corresponding time range can be downloaded to capture dynamic changes in time and space.

[0055] Step 102: Meteorological data collection

[0056] Meteorological data are obtained through meteorological monitoring stations or public meteorological databases (such as NOAA, ECMWF, National Meteorological Administration, etc.), mainly including meteorological parameters such as temperature, precipitation, humidity, wind speed, air pressure, etc. In order to ensure the temporal and spatial consistency of the data, meteorological data consistent with the time range of the remote sensing image data should be selected, and the corresponding meteorological data subset should be extracted according to the geographical range of the target area.

[0057] Step 103: Ground monitoring data collection

[0058] Ground monitoring data is obtained through environmental monitoring data provided by monitoring stations set up in the target area or relevant institutions, mainly including air quality (such as PM2.5, PM10, SO2 concentration), water quality parameters (such as dissolved oxygen, chemical oxygen demand, total phosphorus concentration) and soil quality information. During the collection process, attention should be paid to the spatial distribution of data to ensure that the coverage of the monitoring station can reflect the environmental conditions of the entire target area.

[0059] Step 104: Socioeconomic Data Collection

[0060] Socioeconomic data are obtained through government statistical yearbooks, public databases (such as World Bank, UNDP, etc.) or regional economic surveys, mainly including information such as population density, GDP, land use type, industrial and agricultural activity intensity, etc. When collecting data, it should be ensured that the data has a high spatial resolution (such as county or township level), and key indicators that can reflect the impact of socioeconomic activities on the ecological environment should be selected to provide support for subsequent dynamic assessment of the ecological environment.

[0061] Through the collection of the above four types of data, a basic data set of multi-source ecological and environmental data was constructed, providing comprehensive and accurate input for subsequent data cleaning, spatiotemporal fusion and dynamic evaluation.

[0062] Preferably, the multi-source ecological environment data is cleaned to obtain cleaned data, including:

[0063] The multi-source ecological environment data are grouped according to a preset collection period to obtain a plurality of data groups;

[0064] Calculate the difference coefficient between the current data group and the previous data group in sequence;

[0065] Determine whether the value of the coefficient of difference is within a preset range;

[0066] If the value of the difference coefficient is not within the preset range, the corresponding data group is removed;

[0067] If the value of the difference coefficient is within a preset range, the corresponding data group is retained until all data groups are traversed to obtain the cleaned data.

[0068] Preferably, the difference coefficient calculation formula is:

[0069]

[0070] Among them, p X,Y is the coefficient of difference, cov(X,Y) represents the covariance between the current data set X and the previous data set Y, α X represents the mean of the current data set X, β Y Represents the mean of the previous data set Y.

[0071] Specifically, step 200 of this embodiment includes:

[0072] Step 201: Data Grouping

[0073] First, the multi-source ecological and environmental data are grouped according to the preset collection period (such as daily, weekly or monthly), and the data are divided into multiple data groups in chronological order. Each data group contains all the data points collected within the period, such as remote sensing image data, meteorological data, ground monitoring data and socio-economic data of a certain day. The purpose of grouping is to facilitate the consistency analysis of the data in time series and provide a basis for the subsequent calculation of the coefficient of difference.

[0074] Step 202: Calculate the coefficient of variation

[0075] For each data group, the coefficient of difference between the current data group and the previous data group is calculated in turn. The coefficient of difference measures the similarity between two data groups by analyzing the degree of co-variation between them. Specifically, the calculation of the coefficient of difference needs to consider the means of the two data groups and the covariance between them. The covariance reflects the correlation between the two data groups, while the mean is used to standardize the overall level of the data groups. In this way, the degree of difference between the current data group and the previous data group can be quantified.

[0076] Step 203: Determine the range of the coefficient of difference

[0077] After calculating the coefficient of difference, compare it with the preset range. The preset range is usually determined based on the actual application scenario and data characteristics, such as reasonable upper and lower limits obtained through historical data analysis. If the value of the coefficient of difference exceeds the preset range, it means that there is an abnormal difference between the current data group and the previous data group, which may be caused by data collection errors, noise interference or other abnormal conditions. In this case, the data group needs to be marked as abnormal data.

[0078] Step 204: Data set screening and cleaning

[0079] According to the range judgment result of the difference coefficient, the data group is screened. If the value of the difference coefficient is within the preset range, the current data group is retained and its data quality is considered to meet the requirements; if the value of the difference coefficient is not within the preset range, the current data group is removed to avoid the influence of abnormal data on subsequent analysis. By traversing all data groups, data groups that meet the quality requirements are gradually screened out, and finally the cleaned multi-source ecological environment data are obtained, providing high-quality input data for subsequent spatiotemporal data fusion and dynamic evaluation.

[0080] Specifically, after data cleaning, this embodiment performs denoising on the retained data set to further improve the quality and reliability of the data. For remote sensing image data, median filtering or wavelet transform methods can be used to remove random noise in the image; for meteorological data and ground monitoring data, sliding average method or Kalman filtering can be used to smooth time series data to eliminate abnormal fluctuations; for socioeconomic data, outliers can be identified and eliminated through statistical methods (such as box plot analysis). In the denoising process, the appropriate denoising algorithm should be selected according to different data types to ensure the authenticity and integrity of the data.

[0081] After denoising, this embodiment also uniformly converts multi-source data into a standardized format for subsequent spatiotemporal data fusion and dynamic evaluation. For remote sensing image data, it can be converted into GeoTIFF format, and the image can be corrected for coordinate projection; for meteorological data and ground monitoring data, it can be stored in a time series format (such as CSV or NetCDF) with timestamp and spatial coordinate information attached; for socioeconomic data, it can be converted into a structured table format (such as Excel or database table), and the data fields can be named in a standardized manner. Through format conversion, all data are ensured to have a consistent time and space reference system, providing standardized data input for subsequent analysis.

[0082] Preferably, the cleaned data is subjected to spatiotemporal data fusion using a spatial interpolation method and a time series analysis method to obtain a fused spatiotemporal data set, including:

[0083] Unifying the cleaned data into a standard space-time grid format, and adding a timestamp and spatial coordinates to each data point in the space-time grid;

[0084] Based on the Kriging interpolation method, spatial interpolation is performed on the data at each time point in the space-time grid to generate complete spatial distribution data;

[0085] Performing time series analysis on the data of each spatial position in the spatial distribution data to fill in missing values ​​in time and smooth the time series to obtain time analysis data;

[0086] The spatial distribution data and the time analysis data are subjected to spatiotemporal data fusion to obtain the fused spatiotemporal data set.

[0087] Preferably, time series analysis is performed on the data of each spatial position in the spatial distribution data to fill in missing values ​​in time and smooth the time series to obtain time analysis data, including:

[0088] Extracting time series from data at each spatial location;

[0089] The time series is predicted and interpolated according to the LSTM long short-term memory network, missing values ​​in the time interval are filled, and time series fluctuations are smoothed to obtain the time analysis data.

[0090] Preferably, the dynamic evaluation model is a CNN-LSTM combined model.

[0091] Specifically, step 300 of this embodiment includes:

[0092] Step 301: Standardization and spatiotemporal gridding of cleaned data

[0093] First, the cleaned multi-source ecological and environmental data are uniformly converted into a standard spatiotemporal grid format for spatiotemporal data fusion. Specifically, the spatial grid (such as 1km×1km grid cells) is divided according to the geographical scope of the study area, and spatial coordinates (latitude and longitude or grid number) are added to each grid cell. At the same time, the data is sorted according to the time dimension, and a timestamp (such as YYYY-MM-DD) is added to each data point to ensure that the data has clear spatial and temporal attributes. Through this standardized processing, an initial data grid containing spatiotemporal coordinates is generated, providing a basis for subsequent spatial interpolation and time series analysis.

[0094] Step 302: Spatial interpolation based on Kriging interpolation

[0095] For the data at each time point in the space-time grid, the Kriging interpolation method is used for spatial interpolation to generate complete spatial distribution data. Kriging interpolation is a spatial interpolation method based on geostatistics that can generate high-precision interpolation results based on the spatial correlation of data. In the specific implementation process, the semivariogram of the data is first calculated, the spatial correlation model (such as a spherical model or a Gaussian model) is fitted, and then the target grid cell is interpolated. Through Kriging interpolation, the missing data in space can be filled and the complete spatial distribution data at each time point can be generated to provide support for subsequent time series analysis.

[0096] Step 303: Time series analysis based on LSTM

[0097] Time series data is extracted for each spatial location (i.e., each grid cell) in the spatially distributed data, and LSTM (Long Short-Term Memory Network) is used to predict and interpolate the time series to fill in missing values ​​in time and smooth time series fluctuations. LSTM is a deep learning model suitable for processing time series data, which can capture short-term changes and long-term trends in data. In the specific implementation process, each time series is first normalized, and then the time series is input into the pre-trained LSTM model to predict and interpolate missing values ​​within the time interval, and at the same time smooth abnormal fluctuations in the data to generate time analysis data. The use of LSTM can effectively improve the accuracy and robustness of time series analysis.

[0098] Step 304: Application of spatiotemporal data fusion and dynamic assessment model

[0099] The spatial distribution data generated by Kriging interpolation is fused with the time analysis data obtained based on LSTM time series analysis. During the fusion process, the time series results in the time analysis data are matched with the spatial distribution data according to the timestamp and spatial coordinates, and the overlapping parts are weighted fused (such as simple average or weighted average). Finally, a complete fused spatiotemporal data set is generated, which contains the ecological and environmental attribute values ​​at each time point and spatial location. Subsequently, the fused spatiotemporal data set is input into the CNN-LSTM combined model for dynamic evaluation. The CNN part extracts spatial features and the LSTM part captures time series features, thereby obtaining the prediction results of future ecological and environmental changes, providing a scientific basis for subsequent optimization management strategies.

[0100] Furthermore, the time series analysis based on LSTM in this embodiment is as follows:

[0101] The time series is extracted from the data of each spatial location (i.e. each grid unit) in the spatial distribution data according to the timestamp to form a data series with time as the dimension. For example, for a certain grid unit, the ecological environment attribute values ​​(such as NDVI, AQI, etc.) at different time points (such as daily and monthly) are extracted to form the corresponding time series.

[0102] The extracted time series data is input into the LSTM model for prediction and interpolation operations. LSTM captures the short-term dynamic changes and long-term trends of the time series through its memory units, and can predict missing values ​​within the time interval. Specifically, the LSTM model learns the rules of the time series through complete historical data during the training phase, and predicts missing values ​​by inputting incomplete time series during the interpolation phase. At the same time, the LSTM model can also smooth abnormal fluctuations in the time series and generate more stable time analysis data.

[0103] Furthermore, the CNN-LSTM combination model of the dynamic evaluation model is as follows:

[0104] CNN (Convolutional Neural Network) is used to extract spatial features from fused spatiotemporal data sets. Specifically, the spatial distribution data in the spatiotemporal data (such as the grid data at each time point) is input into the CNN model, and spatial features are extracted through convolution operations, such as the spatial distribution pattern of the ecological environment, hot spots, etc. The convolution kernel of CNN can capture local spatial features, while the pooling layer can reduce the dimensionality of the features and retain key spatial information.

[0105] LSTM is used to capture time series features in spatiotemporal data. The spatial features extracted by CNN are input into the LSTM model in chronological order. LSTM learns the dynamic change rules of time series through its memory units, thereby predicting future ecological environment change trends. The combination of CNN and LSTM can capture spatial and temporal features at the same time, improving the accuracy and prediction ability of the dynamic evaluation model.

[0106] Through the above steps, this embodiment finally realizes the spatiotemporal data fusion of the cleaned data, and generates future ecological environment change results through the CNN-LSTM dynamic evaluation model, providing scientific support for subsequent optimization management.

[0107] Preferably, the calculation formula of the ecological environment quality index is:

[0108] EQI=w1·NDVI+w2·AQI+w3·WQI+w4·LUI+w5·SEI

[0109] Among them: EQI is the ecological environment quality index, ranging from 0 to 1, and the higher the value, the better the ecological environment quality; NDVI is the normalized vegetation index, which reflects the vegetation coverage; AQI is the air quality index, which reflects the degree of air pollution; WQI is the water quality index, which reflects the degree of water pollution; LUI is the land use intensity index, which reflects the intensity of human activities on land resources; SEI is the socio-economic index, which reflects the impact of socio-economic development on the ecological environment; w1, w2, w3, w4 and w5 are weight coefficients, which indicate the relative importance of each indicator to the ecological environment quality, satisfying w1+w2+w3+w4+w5=1.

[0110] Demonstratively, based on historical ecological environment data, this embodiment uses the principal component analysis (PCA) method to determine the weight coefficient. Specifically, after the multi-source ecological environment data (NDVI, AQI, WQI, LUI, SEI) are standardized, the covariance matrix of each indicator is calculated, and the principal component is extracted. By analyzing the eigenvalues ​​and eigenvectors of each principal component, the contribution rate of each indicator in the principal component is determined and normalized into a weight coefficient. The PCA method can objectively extract the importance of each indicator from the data and avoid the influence of human intervention on the weight distribution.

[0111] Specifically, the future ecological environment change results of this embodiment include the ecological environment quality change trend and spatial distribution characteristics of the target area within a specific time range in the future (such as the next 1 year, 5 years or 10 years), including the predicted value of the ecological environment quality index (EQI), the change trend of each key indicator (such as NDVI, AQI, WQI, LUI, SEI), the dynamic changes of ecological environment hot spots and cold spots, and possible environmental risks (such as areas of increased pollution or ecological degradation) and improved areas (such as vegetation restoration or water quality improvement areas). These results provide scientific basis and forward-looking guidance for ecological environment protection and management.

[0112] Preferably, the spatiotemporal statistical analysis method is based on the Mann-Kendall trend test method.

[0113] Specifically, step 500 of this embodiment includes:

[0114] Step 501: Calculation of Ecological Environment Quality Index (EQI)

[0115] First, based on the fused spatiotemporal dataset, the key indicator data of each grid unit at different time points are extracted, including NDVI, AQI, WQI, LUI and SEI. These indicators are normalized and their values ​​are converted to the same range (such as 0 to 1) for unified calculation. Then, according to the predetermined weight coefficient, each indicator is weighted and summed according to its relative importance to the ecological environment quality, and the ecological environment quality index (EQI) of each grid unit at different time points is calculated. The calculation results of EQI can reflect the distribution of ecological environment quality in space and time in the target area.

[0116] Step 502: Preparation for Mann-Kendall trend test

[0117] After calculating the EQI of each grid cell, extract its time series data to form the EQI time series of each grid cell. The Mann-Kendall trend test is a non-parametric statistical method that is suitable for analyzing the changing trend of time series data, so there is no need to assume the distribution characteristics of the data. In order to perform the test, the EQI time series of each grid cell needs to be arranged in chronological order and the statistical parameters for the test (such as time series length and data value) need to be prepared.

[0118] Step 503: Implementation of Mann-Kendall trend test

[0119] The Mann-Kendall trend test is performed on the EQI time series of each grid cell to determine whether its trend is significantly increasing, significantly decreasing, or no significant change. Specifically, the test method calculates the trend statistic by comparing the size relationship of the data points in the time series, and judges the significance of the trend in combination with the significance level (such as 0.05 or 0.01). The test results can be marked as "upward trend", "downward trend" or "no significant trend", and these trend information are associated with the spatial coordinates of the grid cell.

[0120] Step 504: Spatial visualization and analysis of dynamic change trends

[0121] The results of the Mann-Kendall test are mapped to the spatial grid of the target area to generate a spatial distribution map of the changing trend of the ecological environment quality. For example, different colors can be used to represent areas with an upward trend, a downward trend, and no significant trend, thereby intuitively displaying the dynamic trend of ecological environment quality. In addition, the hotspot analysis method can be combined to identify key areas of ecological environment change (such as areas of significant improvement or degradation), providing a scientific basis and decision-making support for ecological environment protection and management.

[0122] Preferably, the multi-objective optimization algorithm is a particle swarm optimization algorithm.

[0123] Specifically, step 600 of this embodiment includes:

[0124] Step 601: Formulate optimization objectives and constraints

[0125] According to the future ecological environment change results, the ecological environment quality index (EQI) and dynamic change trends, combined with the ecological environment management goals, the optimization objective function and constraints are clarified. The optimization goals can include improving the ecological environment quality index (such as maximizing EQI), reducing pollution (such as minimizing AQI), improving water quality (such as maximizing WQI), reducing land use intensity (such as minimizing LUI), etc. Constraints are set according to actual conditions, such as budget constraints, land use planning requirements, and socio-economic development goals. Clear goals and constraints provide a clear direction for subsequent optimization calculations.

[0126] Step 602: Particle swarm initialization and parameter setting

[0127] The particle swarm optimization algorithm (PSO) is used for optimization. First, the particle swarm is initialized. Each particle in the particle swarm represents a possible ecological environment management strategy, and its position represents the specific parameter value of the strategy (such as pollution control investment, vegetation restoration area, etc.). During initialization, the position and speed of the particle swarm are randomly generated, and the key parameters of PSO are set, including the size of the particle swarm, the maximum number of iterations, the inertia weight, the acceleration factor, etc. The reasonable setting of these parameters can affect the convergence speed and optimization effect of the algorithm.

[0128] Step 603: Design and calculation of fitness function

[0129] A fitness function is designed for each particle to evaluate the pros and cons of its corresponding management strategy. The fitness function is designed based on the optimization goal and constraints, such as comprehensive consideration of the improvement of EQI, the reduction of pollutants, and the control of economic costs. For each particle, its position (i.e., management strategy parameter) is substituted into the fitness function for calculation to obtain the fitness value. The higher the fitness value, the closer the management strategy corresponding to the particle is to the optimization goal.

[0130] Step 604: Iterative optimization of particle swarm

[0131] In each iteration, the speed and position of each particle are updated according to the fitness value of the particle swarm. The position update of the particle follows the core mechanism of PSO, that is, adjusting the direction under the guidance of the global optimal solution and the individual optimal solution, while combining the inertia weight to control the exploration and development capabilities of the particle. Through multiple iterations, the particle swarm gradually converges to the global optimal solution and finds the optimal management strategy that meets the optimization objectives and constraints.

[0132] Step 605: Generate optimal management plan

[0133] When the particle swarm reaches the maximum number of iterations or meets the convergence condition, the algorithm stops running and outputs the global optimal solution. The particle position corresponding to the optimal solution is the parameter value of the optimal management plan, such as specific measures for pollution control, area allocation for vegetation restoration, and optimal planning for land use. Combined with these parameter values, a specific ecological environment management plan is generated, and the optimization results are displayed through visualization tools to provide scientific basis and implementation guidance for decision makers. The final management plan can meet the ecological environment management goals while taking into account the multiple needs of the economy, society and environment to achieve sustainable development of the ecological environment.

[0134] The beneficial effects of the present invention are as follows:

[0135] (1) The present invention integrates multi-source ecological and environmental data (remote sensing image data, meteorological data, ground monitoring data, and socio-economic data). Through data cleaning, denoising, and format conversion, the quality and consistency of the data are ensured, and the multi-dimensional characteristics of the ecological environment are fully reflected. Through the calculation of the Ecological Environment Quality Index (EQI), a variety of key factors such as vegetation, air, water quality, land use, and socio-economics are comprehensively considered, and the quality of the ecological environment can be comprehensively evaluated.

[0136] (2) The present invention uses spatial interpolation methods and time series analysis methods to perform spatiotemporal data fusion on the cleaned data, which can dynamically capture the spatiotemporal change characteristics of the ecological environment and make up for the shortcomings of static evaluation in traditional methods; through spatiotemporal statistical analysis methods (such as spatiotemporal hotspot analysis and trend analysis), it can identify the dynamic change trend of the ecological environment, discover the hot spots, cold spots and potential problem areas of the ecological environment, and provide a scientific basis for management.

[0137] (3) The present invention uses a trained dynamic assessment model to analyze the fused spatiotemporal data set, which can predict future trends in ecological environmental changes, identify possible environmental risks or improvement areas in advance, and support forward-looking decision-making; through the prediction results, it can provide more accurate time windows and spatial guidance for ecological protection and restoration.

[0138] (4) The present invention combines the future ecological environment change results, ecological environment quality index and dynamic change trends to formulate optimization strategies, and generates optimal management plans through multi-objective optimization algorithms to ensure the scientificity and efficiency of ecological environment management; the multi-objective optimization algorithm can find a balance between ecological protection, resource utilization and social and economic development to achieve sustainable management of the ecological environment.

[0139] (5) The final results of the present invention include optimal management plans and visual displays, which facilitate decision makers to intuitively understand the ecological environment status and its changing trends and support scientific decision-making; by delineating ecological restoration priority areas, optimizing resource allocation plans, and providing targeted policy recommendations, the operability and execution efficiency of management measures are improved.

[0140] (6) The framework of the present invention has strong adaptability and can adjust data sources, weight coefficients and optimization targets according to the ecological and environmental characteristics and management objectives of different regions, and is suitable for a variety of ecological and environmental assessment and management scenarios; the dynamic assessment model and optimization algorithm can be updated and expanded according to actual needs to adapt to complex and changeable ecological and environmental problems.

[0141] (7) The present invention can help managers quickly identify problem areas in the ecological environment (such as pollution hotspots and degraded areas), prioritize targeted restoration measures, and improve the accuracy and efficiency of ecological protection; through dynamic monitoring and prediction, it can provide a scientific basis for the formulation of ecological environmental protection policies and help achieve sustainable development of the ecological environment.

[0142] (8) By optimizing resource allocation and formulating scientific management strategies, the present invention can reduce resource waste and improve the input-output ratio of ecological restoration and environmental protection; the multi-objective optimization algorithm can maximize benefits under limited resource conditions and provide an economical and efficient solution for ecological environment management.

[0143] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0144] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for dynamic assessment and management of ecological environment based on spatiotemporal data analysis, characterized in that: include: Collect multi-source ecological and environmental data; Cleaning the multi-source ecological environment data to obtain cleaned data; Using a spatial interpolation method and a time series analysis method to perform spatiotemporal data fusion on the cleaned data to obtain a fused spatiotemporal data set; Inputting the fused spatiotemporal data set into the trained dynamic assessment model to obtain the future ecological environment change results; Calculating an ecological environment quality index based on the fused spatiotemporal data set, and using a spatiotemporal statistical analysis method to identify a dynamic change trend of the ecological environment on the fused spatiotemporal data set; According to the future ecological environment change results, the ecological environment quality index and the dynamic change trend, combined with the ecological environment management goals, an optimization strategy is formulated, and a multi-objective optimization algorithm is used to optimize the optimization strategy to generate the optimal management plan.

2. The method for dynamic assessment and management of ecological environment based on spatiotemporal data analysis according to claim 1 is characterized in that: The multi-source ecological environment data include remote sensing image data, meteorological data, ground monitoring data and socio-economic data.

3. The method for dynamic assessment and management of ecological environment based on spatiotemporal data analysis according to claim 1 is characterized in that: The multi-source ecological environment data is cleaned to obtain cleaned data, including: The multi-source ecological environment data are grouped according to a preset collection period to obtain a plurality of data groups; Calculate the difference coefficient between the current data group and the previous data group in sequence; Determine whether the value of the coefficient of difference is within a preset range; If the value of the difference coefficient is not within the preset range, the corresponding data group is removed; If the value of the difference coefficient is within a preset range, the corresponding data group is retained until all data groups are traversed to obtain the cleaned data.

4. The method for dynamic assessment and management of ecological environment based on spatiotemporal data analysis according to claim 3 is characterized in that: The coefficient of difference calculation formula is: Among them, p X,Y is the coefficient of difference, cov(X,Y) represents the covariance between the current data set X and the previous data set Y, α X represents the mean of the current data set X, β Y Represents the mean of the previous data set Y.

5. The method for dynamic assessment and management of ecological environment based on spatiotemporal data analysis according to claim 1 is characterized in that: The cleaned data is subjected to spatiotemporal data fusion using a spatial interpolation method and a time series analysis method to obtain a fused spatiotemporal data set, including: Unifying the cleaned data into a standard space-time grid format, and adding a timestamp and spatial coordinates to each data point in the space-time grid; Based on the Kriging interpolation method, spatial interpolation is performed on the data at each time point in the space-time grid to generate complete spatial distribution data; Performing time series analysis on the data of each spatial position in the spatial distribution data to fill in missing values ​​in time and smooth the time series to obtain time analysis data; The spatial distribution data and the time analysis data are subjected to spatiotemporal data fusion to obtain the fused spatiotemporal data set.

6. The method for dynamic assessment and management of ecological environment based on spatiotemporal data analysis according to claim 5 is characterized in that: Performing time series analysis on the data of each spatial location in the spatial distribution data to fill in the missing values ​​in time and smooth the time series to obtain time analysis data, including: Extracting time series from data at each spatial location; The time series is predicted and interpolated according to the LSTM long short-term memory network, missing values ​​in the time interval are filled, and time series fluctuations are smoothed to obtain the time analysis data.

7. The method for dynamic assessment and management of ecological environment based on spatiotemporal data analysis according to claim 1 is characterized in that: The dynamic evaluation model is a CNN-LSTM combined model.

8. The method for dynamic assessment and management of ecological environment based on spatiotemporal data analysis according to claim 1 is characterized in that: The calculation formula of the ecological environment quality index is: EQI=w1·NDVI+w2·AQI+w3·WQI+w4·LUI+w5·SEI Among them: EQI is the ecological environment quality index, ranging from 0 to 1, and the higher the value, the better the ecological environment quality; NDVI is the normalized vegetation index, which reflects the vegetation coverage; AQI is the air quality index, which reflects the degree of air pollution; WQI is the water quality index, which reflects the degree of water pollution; LUI is the land use intensity index, which reflects the intensity of human activities on land resources; SEI is the socio-economic index, which reflects the impact of socio-economic development on the ecological environment; w1, w2, w3, w4 and w5 are weight coefficients, which indicate the relative importance of each indicator to the ecological environment quality, satisfying w1+w2+w3+w4+w5=1.

9. The method for dynamic assessment and management of ecological environment based on spatiotemporal data analysis according to claim 1 is characterized in that: The spatiotemporal statistical analysis method is based on the Mann-Kendall trend test method.

10. The method for dynamic assessment and management of ecological environment based on spatiotemporal data analysis according to claim 1, characterized in that: The multi-objective optimization algorithm is a particle swarm optimization algorithm.

Images