Strategy analysis method and system for eutrophic water body treatment

Abstract

The invention discloses a strategy analysis method and system for eutrophication water body treatment, and relates to the technical field of data analysis, and the method comprises the steps: carrying out pollution load trend analysis on each monitoring point area; analyzing associated data of the pollution source and water quality based on the correlation coefficient matrix, and determining an initial water treatment strategy of each monitoring point area based on the pollution load trend data and the associated data; performing water treatment simulation based on the initial water treatment strategy in combination with a digital twinborn technology; carrying out collaborative conflict analysis on water treatment of each monitoring point area based on a water treatment simulation result in combination with pollution migration analysis; determining an auxiliary treatment strategy based on the water treatment simulation result; adjusting the initial water treatment strategy based on the collaborative conflict data; and treating the eutrophic water body based on the target water body treatment strategy and the auxiliary treatment strategy. The treatment effect of the eutrophic water body is effectively improved, and the water quality of the water body can be continuously kept in a good state for a long time.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, and in particular to a strategy analysis method and system for the treatment of eutrophic water bodies. Background Technology

[0002] Due to rapid socio-economic development and increasing human activities altering nature, eutrophication of water bodies has become increasingly severe. Eutrophication seriously damages aquatic ecosystems, making its remediation extremely important. Currently, eutrophication remediation strategies typically assess the degree of eutrophication solely based on pollutant concentrations, matching remediation strategies accordingly. However, this approach fails to comprehensively reflect the pollution load of the water body, resulting in a lack of targeted remediation strategies. Furthermore, most current remediation strategies lack consideration for pollutant migration, potentially leading to excessive pollutant accumulation in certain areas and continuous pollution load input. This can render the remediation strategy ineffective in addressing the complex flow conditions within eutrophic water bodies, diluting or even negating the remediation's benefits. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art. This invention provides a strategy analysis method and system for the treatment of eutrophic water bodies, which effectively improves the treatment effect of eutrophic water bodies, better maintains the balance of the aquatic ecosystem, and enables the water quality to remain in a good state for a long time.

[0004] To address the aforementioned technical problems, this invention provides a strategy analysis method for the treatment of eutrophic water bodies, the method comprising:

[0005] Pollution load trend analysis was conducted on each monitoring point area of ​​eutrophic water bodies to obtain pollution load trend data.

[0006] The correlation coefficient matrix was used to analyze the correlation data between pollution sources and water quality, and the initial water treatment strategy for each monitoring point area was determined based on pollution load trend data and correlation data.

[0007] Water body management simulation is conducted based on the initial water body management strategy combined with digital twin technology to obtain water body management simulation results;

[0008] Based on the simulation results of water body treatment and pollution migration analysis, a collaborative conflict analysis of water body treatment in each monitoring point area was conducted to obtain collaborative conflict data.

[0009] Determine auxiliary treatment strategies based on water body treatment simulation results;

[0010] The initial water body treatment strategy is adjusted based on collaborative conflict data to obtain the target water body treatment strategy;

[0011] Eutrophic water bodies are treated based on target water body treatment strategies and auxiliary treatment strategies.

[0012] Optionally, the pollution load trend analysis of each monitoring point area in the eutrophic water body to obtain pollution load trend data includes:

[0013] The water quality data and pollutant concentration data of each monitoring point area are segmented and processed to obtain segmented water quality data and pollutant concentration data.

[0014] Based on the segmented pollutant concentration data, the pollutant factor transformation trend analysis was performed to obtain pollutant factor transformation trend data.

[0015] Based on the segmented water quality data and pollutant concentration data, an analysis of the impact of pollutants was conducted to obtain data on the impact of pollutants.

[0016] Pollution load trend analysis is conducted based on pollution factor transformation trend data and pollution factor impact data, combined with the correlation of pollution factors, to obtain pollution load trend data.

[0017] Optionally, the step of analyzing the correlation data between pollution sources and water quality based on the correlation coefficient matrix, and determining the initial water treatment strategy for each monitoring point area based on pollution load trend data and correlation data, includes:

[0018] The concentration change trend of pollutants is determined based on the segmented pollutant concentration data, and a correlation coefficient matrix is ​​constructed based on the concentration change trend.

[0019] Water quality change analysis is performed based on segmented water quality data and pollutant concentration data to obtain water quality change data, and a water quality change time series diagram is generated based on the water quality change data.

[0020] Based on water quality change data and pollutant concentration change trends, a spatiotemporal distribution map of pollutants is determined, and the spatial distribution relationship between pollutants and pollution sources is determined based on the spatiotemporal distribution map.

[0021] The correlation data between pollution sources and water quality were determined based on the correlation coefficient matrix, water quality change time series diagram, and spatial distribution relationship.

[0022] Pollutant reduction data are determined based on pollution load trend data and correlation data. Source control and interception strategies and ecological restoration strategies are determined based on pollutant reduction data, pollution load trend data and correlation data. Initial water treatment strategies for each monitoring point area are determined based on source control and interception strategies and ecological restoration strategies.

[0023] Optionally, constructing the correlation coefficient matrix based on the concentration change trend includes:

[0024] Based on the concentration change trend, the characteristic coefficients of pollutants are analyzed to obtain the corresponding characteristic coefficient sequence, and the cross-correlation function is determined based on the characteristic coefficient sequence.

[0025] A symmetric matrix is ​​constructed based on the cross-correlation function, and the correlation coefficient matrix is ​​determined based on the symmetric matrix.

[0026] Optionally, the step of simulating water body treatment based on the initial water body treatment strategy combined with digital twin technology to obtain water body treatment simulation results includes:

[0027] Digital twin models of each monitoring point area in eutrophic water bodies were constructed based on the water convection and diffusion model.

[0028] Based on the digital twin model and the initial water treatment strategy, water treatment simulation was conducted to obtain the simulation results.

[0029] Optionally, the construction of digital twin models of each monitoring point area of ​​the eutrophic water body based on the water convection and diffusion model includes:

[0030] A water convection-diffusion model was constructed based on hydrological and meteorological change data of each monitoring point area.

[0031] A grid is set based on the boundary data of each monitoring point area in eutrophic water bodies, and a physical field model is constructed based on the hydrological data and pollutant data of each monitoring point area.

[0032] Digital twin models of each monitoring point area were constructed based on the water convection diffusion model, grid volume, and physical field model.

[0033] Optionally, the analysis of collaborative conflict in water body treatment at each monitoring point based on water body treatment simulation results combined with pollution migration analysis, to obtain collaborative conflict data, includes:

[0034] Water flow patterns are analyzed based on a seasonal autoregressive integral moving average model to obtain water flow pattern data.

[0035] Based on water flow pattern data and water treatment simulation results, pollution migration analysis was conducted in the areas of each monitoring point to obtain pollution migration data.

[0036] Based on the simulation results of water body treatment, simulated water pollution detection data and collaborative treatment effect data of each monitoring point area are extracted;

[0037] Based on pollution migration data, simulated water pollution detection data, and collaborative governance effect data, a collaborative conflict analysis was conducted on the regional water body governance at each monitoring point to obtain collaborative conflict data.

[0038] Optionally, determining auxiliary treatment strategies based on water body treatment simulation results includes:

[0039] Microbial activity data were determined based on the collaborative treatment effect data from water body treatment simulation results, and aeration auxiliary data were determined based on the microbial activity data.

[0040] Based on the simulation results of water body management, auxiliary data for the maintenance of aquatic ecosystems are determined, and auxiliary management strategies are determined based on the aeration auxiliary data and the auxiliary data for the maintenance of aquatic ecosystems.

[0041] Optionally, adjusting the initial water body treatment strategy based on collaborative conflict data to obtain the target water body treatment strategy includes:

[0042] Constraints and reward functions are set based on collaborative conflict data, and a reinforcement learning-driven optimization model is constructed based on the constraints and reward functions.

[0043] Based on the optimization model, the source control and pollution interception strategies and ecological restoration strategies in the initial water body treatment strategy are adjusted to obtain the target water body treatment strategy.

[0044] In addition, the present invention also provides a strategy analysis system for the treatment of eutrophic water bodies, the system comprising:

[0045] The load trend analysis module is used to perform pollution load trend analysis on each monitoring point area of ​​eutrophic water bodies and obtain pollution load trend data.

[0046] The governance strategy analysis module is used to analyze the correlation data between pollution sources and water quality based on the correlation coefficient matrix, and to determine the initial water body governance strategy for each monitoring point area based on pollution load trend data and correlation data.

[0047] Water treatment simulation module: used to simulate water treatment based on the initial water treatment strategy and digital twin technology, and obtain water treatment simulation results;

[0048] Collaborative Conflict Analysis Module: This module is used to conduct collaborative conflict analysis of water body treatment at various monitoring points based on water treatment simulation results and pollution migration analysis, and to obtain collaborative conflict data.

[0049] The auxiliary governance strategy module is used to determine auxiliary governance strategies based on the simulation results of water body governance.

[0050] Strategy adjustment module: used to adjust the initial water body treatment strategy based on collaborative conflict data to obtain the target water body treatment strategy;

[0051] Water treatment module: Used to treat eutrophic water bodies based on target water treatment strategies and auxiliary treatment strategies.

[0052] In this embodiment of the invention, pollution load trend analysis is performed on each monitoring point area of ​​the eutrophic water body. The obtained pollution load trend data can better reflect the pollution load of the water body. Correlation coefficient matrix analysis is used to analyze the relationship between pollution sources and water quality. Based on the pollution load trend data and correlation data, initial water treatment strategies for each monitoring point area are determined, enabling more targeted matching of the required water treatment strategies. Based on water treatment simulation results and pollution migration analysis, synergistic conflict analysis of water treatment in each monitoring point area is conducted. The initial water treatment strategy is adjusted based on the synergistic conflict data, taking into account pollution migration analysis and synergistic conflicts between monitoring point areas to avoid excessive pollutant accumulation in any area of ​​the water body. This ensures that the derived target water treatment strategy can cope with the complex flow conditions in eutrophic water bodies. Treatment of eutrophic water bodies based on the target water treatment strategy and auxiliary treatment strategies effectively improves the treatment effect, better maintains the balance of the aquatic ecosystem, and ensures that the water quality remains in a good state for a long time. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a flowchart illustrating the strategy analysis method for treating eutrophic water bodies in an embodiment of the present invention.

[0055] Figure 2 This is a flowchart illustrating a strategy analysis method for treating eutrophic water bodies according to another embodiment of the present invention.

[0056] Figure 3 This is a schematic diagram of the structural composition of a strategy analysis system for eutrophic water body treatment in an embodiment of the present invention. Detailed Implementation

[0057] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] Example 1

[0059] Please see Figure 1 , Figure 1 This is a flowchart illustrating a strategy analysis method for eutrophic water body treatment according to an embodiment of the present invention, the method comprising:

[0060] S11: Conduct pollution load trend analysis on each monitoring point area of ​​eutrophic water bodies to obtain pollution load trend data;

[0061] In the specific implementation of this invention, the step of conducting pollution load trend analysis on each monitoring point area of ​​the eutrophic water body to obtain pollution load trend data includes: segmenting the water quality data and pollutant concentration data of each monitoring point area to obtain segmented water quality data and pollutant concentration data; conducting pollution factor transformation trend analysis based on the segmented pollutant concentration data to obtain pollution factor transformation trend data; conducting pollution factor impact analysis based on the segmented water quality data and pollutant concentration data to obtain pollution factor impact data; and conducting pollution load trend analysis based on the pollution factor transformation trend data and pollution factor impact data combined with the correlation of pollution factors to obtain pollution load trend data.

[0062] Specifically, water quality data and pollutant concentration data for each monitoring point area in eutrophic water bodies are acquired for each time period. Water quality data includes characteristic data reflecting the water quality conditions of each monitoring point area, such as transparency. Pollutant concentration data includes the concentration data of different pollutants in the monitoring point area. The water quality data and pollutant concentration data for each monitoring point area are segmented according to a preset time period to obtain segmented water quality data and pollutant concentration data. Based on the segmented pollutant concentration data, a pollutant factor change trend analysis is performed. Pollutants are different pollutants affecting water quality, and pollutant factor change trends are the changing trends of different pollutants, such as the gradual dissipation of sludge pollutant concentration and the gradual increase of effluent concentration. By comparing the segmented pollutant concentration data, the change trends of pollutants in different time periods are obtained, i.e., pollutant factor change trend data. Pollution factor impact analysis is conducted based on segmented water quality and pollutant concentration data. This data is input into a pollution factor impact analysis model, which is a convergent model trained on a deep neural network using the sample dataset. The analysis examines the impact of pollutant concentration changes on water quality changes, yielding pollution factor impact data. Furthermore, pollution load trend analysis is performed by combining pollution factor change trend data and pollution factor impact data with pollution factor correlations. These correlations represent the relationships between pollutants, such as a positive correlation between ammonia nitrogen and total phosphorus. A deep learning model is used to analyze the continuous pollution trends of various pollutants in the water bodies at each monitoring point area using pollution factor change trend data, pollution factor impact data, and pollution factor correlations, thus obtaining pollution load trend data.

[0063] S12: Analyze the correlation data between pollution sources and water quality based on the correlation coefficient matrix, and determine the initial water treatment strategy for each monitoring point area based on pollution load trend data and correlation data;

[0064] In the specific implementation of this invention, the step of analyzing the correlation data between pollution sources and water quality based on the correlation coefficient matrix, and determining the initial water treatment strategy for each monitoring point area based on pollution load trend data and correlation data, includes: determining the concentration change trend of pollutants based on the segmented pollutant concentration data, and constructing a correlation coefficient matrix based on the concentration change trend; performing water quality change analysis based on the segmented water quality data and pollutant concentration data to obtain water quality change data, and generating a water quality change time series diagram based on the water quality change data; determining the spatiotemporal distribution map of pollutants based on the water quality change data and pollutant concentration change trend, and determining the spatial distribution relationship between pollutants and pollution sources based on the spatiotemporal distribution map; determining the correlation data between pollution sources and water quality based on the correlation coefficient matrix, water quality change time series diagram, and spatial distribution relationship; determining pollutant reduction data based on pollution load trend data and correlation data, and determining source control and interception strategies and ecological restoration strategies based on pollutant reduction data, pollution load trend data, and correlation data, and determining the initial water treatment strategy for each monitoring point area based on the source control and interception strategies and ecological restoration strategies.

[0065] Furthermore, the step of constructing a correlation coefficient matrix based on the concentration change trend includes: performing characteristic coefficient analysis on the pollutants based on the concentration change trend to obtain the corresponding characteristic coefficient sequence, and determining the cross-correlation function based on the characteristic coefficient sequence; constructing a symmetric matrix based on the cross-correlation function, and determining the correlation coefficient matrix based on the symmetric matrix.

[0066] Specifically, the concentration change trends of pollutants are determined based on the segmented pollutant concentration data. Mathematical statistical methods, including exponential smoothing and trend fitting, are used to analyze these trends. Based on these concentration change trends, characteristic coefficient analysis is performed. The concentration change trends of each pollutant are preprocessed using a weighted sliding window method. This preprocessing removes random fluctuations from the concentration change trend data and extracts trend signals reflecting the overall direction of pollutant change, thus obtaining preprocessed concentration change trend data. Wavelet transform is then applied to the preprocessed concentration change trend data, and several layers of wavelet coefficients with the highest energy proportions are selected. These wavelet coefficients are used as the characteristic coefficient sequences for each pollutant, thus obtaining the corresponding characteristic coefficient sequences. Based on these characteristic coefficient sequences, a cross-correlation function is determined. Specifically, the cross-correlation function between the characteristic coefficient sequences of any two pollutants is calculated using the cross-correlation function formula. The expression for the cross-correlation function is:

[0067] R(m) = ∫x(n)*y(n+m)dt,

[0068] Where R is the cross-correlation function, x is the characteristic coefficient sequence of the first pollutant, y is the characteristic coefficient sequence of the second pollutant, n is time, and m is the time delay. A symmetric matrix is ​​constructed based on the cross-correlation function. The correlation coefficient is obtained by dividing the value of the cross-correlation function at zero time delay by the product of the standard deviations of the two characteristic coefficient sequences. The expression for the correlation coefficient is:

[0069]

[0070] Where C is the correlation coefficient between the two pollutants, R(0) is the value of the cross-correlation function at zero time delay, σi is the standard deviation of the characteristic coefficient sequence of the first pollutant, and σj is the standard deviation of the characteristic coefficient sequence of the second pollutant. The correlation coefficient is a statistical indicator that measures the degree of linear correlation between two variables. Using the correlation coefficient as matrix elements, a symmetric matrix is ​​constructed. Each matrix element in the obtained symmetric matrix quantifies the similarity of the concentration change trends of the two pollutants. Based on the symmetric matrix, the correlation coefficient matrix is ​​determined, that is, the symmetric matrix is ​​used as the correlation coefficient matrix. The expression of the correlation coefficient matrix can be:

[0071]

[0072] Where A is the correlation coefficient matrix, C ijThe correlation coefficient is the correlation coefficient between two pollutants. This correlation coefficient matrix can represent the degree of association between changes in the concentrations of different pollutants. Water quality change analysis is performed based on segmented water quality data and pollutant concentration data. This involves analyzing significant abrupt changes and recovery times in water quality based on the segmented water quality data and pollutant concentration data, thus obtaining water quality change data. A time series diagram of water quality changes is then generated based on this data, i.e., the water quality change time series diagram is plotted based on the water quality change data and its corresponding time points. Based on water quality change data and pollutant concentration change trends, a spatiotemporal distribution map of pollutants is determined. This involves analyzing the changes in pollutant concentration over time and space, such as an increase in pollutant concentration over time indicating a significant abrupt change in water quality. Based on this data, a spatiotemporal distribution map of pollutants is determined, and the spatial distribution relationship between pollutants and pollution sources is established. This results in a spatial distribution map of pollution sources, reflecting their distribution across monitoring areas and their impact on each region. Kriging interpolation, an algorithm for observing the spatial correlation of regionalized variables, is then used to fit the spatiotemporal distribution map of pollutants to the emission distribution of pollution sources. This spatial distribution relationship represents the relationship between the spatial distribution of pollutants and the emission distribution of pollution sources. The correlation data between pollution sources and water quality is determined based on the correlation coefficient matrix, water quality change time series diagram, and spatial distribution relationship. Specifically, the influence coefficient of pollutant discharge from pollution sources on water quality changes is analyzed based on the correlation coefficient matrix, water quality change time series diagram, and spatial distribution relationship. The correlation coefficient matrix, water quality change time series diagram, and spatial distribution relationship can be input into the multilayer perceptron model to output the change influence coefficient, thus obtaining the correlation data.Pollutant reduction data is determined based on pollution load trend data and correlation data. Specifically, the target reduction amount of pollutants is determined according to these data, which constitutes the pollutant reduction data. Based on this data, pollution load trend data, and correlation data, source control and interception strategies and ecological restoration strategies are determined. Source control and interception strategies include outfall treatment strategies, the establishment of outfall buffer and purification zones, and surface runoff pollution control strategies. Outfall treatment strategies can utilize outfall particulate separators and end-of-pipe surface flow constructed wetlands as treatment processes. The establishment of outfall buffer and purification zones includes the number and distribution of buffer zones. Surface runoff pollution control strategies may include sponge city green spaces. The ecological restoration strategy includes in-situ high-efficiency enhanced purification engineering, aquatic ecosystem construction engineering, and ecological revetment engineering. In-situ high-efficiency enhanced purification engineering involves the installation of aquatic plants and netting measures. Aquatic ecosystem construction engineering includes the modification of water system layout, the engineering installation of zooplankton communities, and the installation of submerged, emergent, and floating-leaved plant communities. The installation of emergent plant communities can provide a good root zone environment for microorganisms, increasing their activity and biomass. Ecological revetment engineering includes the modification of revetments. Based on the source control and pollution interception strategy and the ecological restoration strategy, the initial water treatment strategy for each monitoring point area is determined.

[0073] S13: Based on the initial water treatment strategy and combined with digital twin technology, water treatment simulation is carried out to obtain water treatment simulation results;

[0074] In the specific implementation of this invention, the water body management simulation based on the initial water body management strategy combined with digital twin technology to obtain water body management simulation results includes: constructing digital twin models of each monitoring point area of ​​eutrophic water body based on the water convection diffusion model; and performing water body management simulation based on the digital twin models combined with the initial water body management strategy to obtain water body management simulation results.

[0075] Furthermore, the construction of digital twin models for each monitoring point area of ​​the eutrophic water body based on the water convection diffusion model includes: constructing a water convection diffusion model based on hydrological data and meteorological change data of each monitoring point area; setting up a grid based on the boundary data of each monitoring point area of ​​the eutrophic water body; constructing a physical field model based on the hydrological data and pollutant data of each monitoring point area; and constructing a digital twin model for each monitoring point area based on the water convection diffusion model, the grid, and the physical field model.

[0076] Specifically, a water convection-diffusion model is constructed based on hydrological and meteorological change data for each monitoring point area. Hydrological data includes water flow velocity and direction, while meteorological change data includes rainfall, wind speed, and wind direction. These data are input into a pre-defined model template to obtain the water convection-diffusion model. A grid is set based on the boundary data of each monitoring point area in the eutrophic water body. The boundary data represents the boundary range of each monitoring point area. A grid is constructed for each area based on its boundary range. A physical field model is constructed based on the hydrological and pollutant data for each monitoring point area, determining the simulated physical field, such as fluid flow. The physical field model is then constructed in multiphysics software using hydrological, pollutant, meteorological, and water quality data, combined with the simulated physical field and the grid. A digital twin model of each monitoring point area is constructed based on the water convection-diffusion model, the grid, and the physical field model. The physical entities are then connected to the digital model to form a digital twin model of each monitoring point area. Based on the digital twin model and the initial water treatment strategy, water treatment simulation is performed. The initial water treatment strategy is deployed in the simulation platform where the digital twin model is located. The simulation platform is used to simulate the water treatment of each monitoring point area under the initial water treatment strategy to obtain the water treatment simulation results.

[0077] S14: Based on the simulation results of water body treatment and combined with pollution migration analysis, conduct a collaborative conflict analysis of water body treatment in each monitoring point area to obtain collaborative conflict data;

[0078] In the specific implementation of this invention, the step of conducting a collaborative conflict analysis of water body treatment in each monitoring point area based on water body treatment simulation results and pollution migration analysis to obtain collaborative conflict data includes: analyzing water flow patterns based on a seasonal autoregressive integral moving average model to obtain water flow pattern data; conducting pollution migration analysis in each monitoring point area based on water flow pattern data and water body treatment simulation results to obtain pollution migration data; extracting simulated water quality pollution detection data and collaborative treatment effect data for each monitoring point area based on water body treatment simulation results; and conducting a collaborative conflict analysis of water body treatment in each monitoring point area based on pollution migration data, simulated water quality pollution detection data, and collaborative treatment effect data to obtain collaborative conflict data.

[0079] Specifically, water bodies are fluid, and implementing governance strategies in a certain area may alter water flow or nutrient distribution, affecting adjacent areas. Therefore, the synergy and conflicts of water body governance across regions must be considered. This study analyzes water flow patterns based on a seasonal autoregressive integral moving average model. Water flow characteristics are extracted from historical water monitoring images of the eutrophic water body, including dynamic information such as water flow vectors and chlorophyll concentration. A water flow feature map is generated based on these characteristics and rasterized according to a preset grid size to obtain a feature raster map. Since some unknown grid cells remain after rasterization, and the water flow characteristics of these cells are unclear, spline function interpolation is used to interpolate the unknown grid cells in the feature raster map to obtain the target feature raster map. A target feature raster map is used to reflect the spatial variation of water flow characteristics. Water flow time series data is generated by using a preset time period and the target feature raster map. This data is then input into a seasonal autoregressive integral moving average (ARMA) model for water flow pattern analysis. The ARMA model can be used to analyze and predict time series data with seasonal patterns, obtaining water flow pattern data and thus revealing water flow trends and changes. This water flow pattern data can better improve the water flow and diffusion data in water treatment simulations. Based on the water flow pattern data and water treatment simulation results, pollution migration analysis is performed in each monitoring point area. The distribution data of equipment and flora and fauna in each monitoring point area is determined based on the water treatment simulation results. The migration and diffusion analysis of pollutants in each monitoring point area is then performed based on the water flow pattern data and distribution data, analyzing the movement and accumulation of pollutants between areas to obtain pollution migration data. Based on the water body treatment simulation results, simulated water pollution detection data and collaborative treatment effect data for each monitoring point area are extracted. The simulated water pollution monitoring data includes water pollution improvement data for each monitoring point area in the water body treatment simulation results. The collaborative treatment effect data includes data on the collaborative treatment effects of various aquatic plants, microbial species, and aquatic plants. Based on pollution migration data, simulated water pollution detection data, and collaborative treatment effect data, a collaborative conflict analysis of water body treatment in each monitoring point area is conducted. This analysis examines the impact of pollution migration data, simulated water pollution monitoring data, and collaborative treatment effect data on the effects of water pollution improvement and collaborative treatment under the given pollution migration scenario. The impact data includes the dilution values ​​of water quality improvement and collaborative treatment effects, thus obtaining the collaborative conflict data.

[0080] S15: Determine auxiliary treatment strategies based on water body treatment simulation results;

[0081] In the specific implementation of this invention, the step of determining auxiliary governance strategies based on water body governance simulation results includes: determining microbial activity data based on the synergistic governance effect data of water body governance simulation results, and determining aeration auxiliary data based on the microbial activity data; determining aquatic ecosystem maintenance auxiliary data based on water body governance simulation results, and determining auxiliary governance strategies based on the aeration auxiliary data and the aquatic ecosystem maintenance auxiliary data.

[0082] Specifically, based on the synergistic treatment effect data from water body treatment simulation results, microbial activity data is determined. This involves using the synergistic treatment effect data of microbial species and aquatic plants to determine the dissolved oxygen and metabolic activity data required for normal microbial activity. Aeration support data is then determined based on this microbial activity data, including the setup and distribution of aeration support equipment. Aeration increases the oxygen content in the water, promoting the decomposition and degradation of pollutants by microorganisms and effectively improving water quality. Aquatic ecosystem maintenance support data is also determined based on the water body treatment simulation results. This data includes the maintenance setup and cycle of aquatic plant communities, microbial communities, and related equipment within the aquatic ecosystem. Finally, auxiliary treatment strategies are determined based on both the aeration support data and the aquatic ecosystem maintenance support data.

[0083] S16: Adjust the initial water body treatment strategy based on collaborative conflict data to obtain the target water body treatment strategy;

[0084] In the specific implementation of this invention, the step of adjusting the initial water body treatment strategy based on collaborative conflict data to obtain the target water body treatment strategy includes: setting constraints based on collaborative conflict data, setting a reward function, and constructing a reinforcement learning-driven optimization model based on the constraints and reward function; adjusting the source control and pollution interception strategy and the ecological restoration strategy in the initial water body treatment strategy based on the optimization model to obtain the target water body treatment strategy.

[0085] Specifically, constraints are set based on collaborative conflict data. These constraints aim to maximize water quality index improvement and minimize bioremediation costs, using the dilution values ​​from the collaborative conflict data as the primary conditions. A reward function is then established, and a reinforcement learning-driven optimization model is constructed based on these constraints and the reward function. This optimization model is a neural network model driven by reinforcement learning. The initial water treatment strategy, including pollution source control and interception, and ecological restoration, is adjusted based on this optimization model and the collaborative conflict data. Adjustments are made to parameters such as aquatic plant settings, particulate separator settings, and microbial settings. These parameters are then used to refine the initial water treatment strategy, resulting in the target water treatment strategy.

[0086] S17: Treat eutrophic water bodies based on target water body treatment strategies and auxiliary treatment strategies.

[0087] In the specific implementation of this invention, according to the source control and interception strategy and the ecological restoration strategy in the target water body treatment strategy, corresponding discharge outlet pollutant particle separators, surface flow artificial wetlands, discharge outlet buffer purification zones, netting measures and sponge green spaces are set up in each monitoring point area of ​​the eutrophic water body. The water system layout is modified, and aquatic plant communities and microbial communities are planted in each monitoring point area. According to the auxiliary treatment strategy, aeration auxiliary equipment is set up in each monitoring point area, and biological communities and equipment maintenance parameters are deployed to achieve the treatment of eutrophic water bodies, realize the biological self-purification of water bodies and maintain water quality stability.

[0088] In this embodiment of the invention, pollution load trend analysis is performed on each monitoring point area of ​​the eutrophic water body. The obtained pollution load trend data can better reflect the pollution load of the water body. Correlation coefficient matrix analysis is used to analyze the relationship between pollution sources and water quality. Based on the pollution load trend data and correlation data, initial water treatment strategies for each monitoring point area are determined, enabling more targeted matching of the required water treatment strategies. Based on water treatment simulation results and pollution migration analysis, synergistic conflict analysis of water treatment in each monitoring point area is conducted. The initial water treatment strategy is adjusted based on the synergistic conflict data, taking into account pollution migration analysis and synergistic conflicts between monitoring point areas to avoid excessive pollutant accumulation in any area of ​​the water body. This ensures that the derived target water treatment strategy can cope with the complex flow conditions in eutrophic water bodies. Treatment of eutrophic water bodies based on the target water treatment strategy and auxiliary treatment strategies effectively improves the treatment effect, better maintains the balance of the aquatic ecosystem, and ensures that the water quality remains in a good state for a long time.

[0089] Example 2

[0090] Please see Figure 2 , Figure 2 This is a flowchart illustrating a strategy analysis method for eutrophic water body treatment according to another embodiment of the present invention, the method comprising:

[0091] S201: Segment the water quality data and pollutant concentration data of each monitoring point area to obtain segmented water quality data and pollutant concentration data;

[0092] S202: Based on the segmented pollutant concentration data, perform pollutant factor transformation trend analysis to obtain pollutant factor transformation trend data;

[0093] S203: Based on the segmented water quality data and pollutant concentration data, conduct pollution factor impact analysis to obtain pollution factor impact data;

[0094] S204: Based on the pollution factor transformation trend data and pollution factor impact data, combined with the correlation of pollution factors, pollution load trend analysis is performed to obtain pollution load trend data;

[0095] S205: Analyze the correlation data between pollution sources and water quality based on the correlation coefficient matrix, and determine the initial water treatment strategy for each monitoring point area based on pollution load trend data and correlation data;

[0096] S206: Based on the initial water treatment strategy and combined with digital twin technology, simulate water treatment to obtain water treatment simulation results;

[0097] S207: Based on the simulation results of water body treatment and combined with pollution migration analysis, conduct a collaborative conflict analysis of water body treatment in each monitoring point area to obtain collaborative conflict data;

[0098] S208: Determine auxiliary treatment strategies based on water body treatment simulation results;

[0099] S209: Adjust the initial water body treatment strategy based on collaborative conflict data to obtain the target water body treatment strategy;

[0100] S210: Treat eutrophic water bodies based on target water body treatment strategies and auxiliary treatment strategies.

[0101] In this embodiment of the invention, pollution load trend analysis is performed on each monitoring point area of ​​the eutrophic water body. The obtained pollution load trend data can better reflect the pollution load of the water body. Correlation coefficient matrix analysis is used to analyze the relationship between pollution sources and water quality. Based on the pollution load trend data and correlation data, initial water treatment strategies for each monitoring point area are determined, enabling more targeted matching of the required water treatment strategies. Based on water treatment simulation results and pollution migration analysis, synergistic conflict analysis of water treatment in each monitoring point area is conducted. The initial water treatment strategy is adjusted based on the synergistic conflict data, taking into account pollution migration analysis and synergistic conflicts between monitoring point areas to avoid excessive pollutant accumulation in any area of ​​the water body. This ensures that the derived target water treatment strategy can cope with the complex flow conditions in eutrophic water bodies. Treatment of eutrophic water bodies based on the target water treatment strategy and auxiliary treatment strategies effectively improves the treatment effect, better maintains the balance of the aquatic ecosystem, and ensures that the water quality remains in a good state for a long time.

[0102] Example 3

[0103] Please see Figure 3 , Figure 3 This is a schematic diagram of the structural composition of a strategy analysis system for eutrophic water body treatment according to an embodiment of the present invention. The system includes:

[0104] Load trend analysis module 31: used to perform pollution load trend analysis on each monitoring point area of ​​eutrophic water bodies and obtain pollution load trend data;

[0105] Governance strategy analysis module 32: It is used to analyze the correlation data between pollution sources and water quality based on the correlation coefficient matrix, and to determine the initial water body governance strategy for each monitoring point area based on pollution load trend data and correlation data.

[0106] Water treatment simulation module 33: used to simulate water treatment based on the initial water treatment strategy and digital twin technology, and obtain water treatment simulation results;

[0107] Collaborative Conflict Analysis Module 34: This module is used to conduct collaborative conflict analysis of water body treatment at various monitoring points based on water treatment simulation results and pollution migration analysis, and to obtain collaborative conflict data.

[0108] Module 35 for auxiliary governance strategies: used to determine auxiliary governance strategies based on water body governance simulation results;

[0109] Strategy adjustment module 36: used to adjust the initial water body treatment strategy based on collaborative conflict data to obtain the target water body treatment strategy;

[0110] Water treatment module 37: Used for the treatment of eutrophic water bodies based on target water treatment strategies and auxiliary treatment strategies.

[0111] In the specific implementation of this invention, the specific implementation methods of the system items can be referred to the implementation methods of the above-mentioned method items, and will not be repeated here.

[0112] In this embodiment of the invention, pollution load trend analysis is performed on each monitoring point area of ​​the eutrophic water body. The obtained pollution load trend data can better reflect the pollution load of the water body. Correlation coefficient matrix analysis is used to analyze the relationship between pollution sources and water quality. Based on the pollution load trend data and correlation data, initial water treatment strategies for each monitoring point area are determined, enabling more targeted matching of the required water treatment strategies. Based on water treatment simulation results and pollution migration analysis, synergistic conflict analysis of water treatment in each monitoring point area is conducted. The initial water treatment strategy is adjusted based on the synergistic conflict data, taking into account pollution migration analysis and synergistic conflicts between monitoring point areas to avoid excessive pollutant accumulation in any area of ​​the water body. This ensures that the derived target water treatment strategy can cope with the complex flow conditions in eutrophic water bodies. Treatment of eutrophic water bodies based on the target water treatment strategy and auxiliary treatment strategies effectively improves the treatment effect, better maintains the balance of the aquatic ecosystem, and ensures that the water quality remains in a good state for a long time.

[0113] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

[0114] Furthermore, the above provides a detailed description of a strategy analysis method and system for eutrophic water body treatment provided by the embodiments of the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A strategy analysis method for the treatment of eutrophic water bodies, characterized in that, The method includes: Pollution load trend analysis was conducted on each monitoring point area of ​​eutrophic water bodies to obtain pollution load trend data. The correlation coefficient matrix was used to analyze the correlation data between pollution sources and water quality, and the initial water treatment strategy for each monitoring point area was determined based on pollution load trend data and correlation data. Water body management simulation is conducted based on the initial water body management strategy combined with digital twin technology to obtain water body management simulation results; Based on the simulation results of water body treatment and pollution migration analysis, a collaborative conflict analysis of water body treatment in each monitoring point area was conducted to obtain collaborative conflict data. Determine auxiliary treatment strategies based on water body treatment simulation results; The initial water body treatment strategy is adjusted based on collaborative conflict data to obtain the target water body treatment strategy; Eutrophic water bodies are treated based on target water body treatment strategies and auxiliary treatment strategies.

2. The strategy analysis method for eutrophic water body treatment according to claim 1, characterized in that, The pollution load trend analysis of each monitoring point area in the eutrophic water body was conducted to obtain pollution load trend data, including: The water quality data and pollutant concentration data of each monitoring point area are segmented and processed to obtain segmented water quality data and pollutant concentration data. Based on the segmented pollutant concentration data, the pollutant factor transformation trend analysis was performed to obtain pollutant factor transformation trend data. Based on the segmented water quality data and pollutant concentration data, an analysis of the impact of pollutants was conducted to obtain data on the impact of pollutants. Pollution load trend analysis is conducted based on pollution factor transformation trend data and pollution factor impact data, combined with the correlation of pollution factors, to obtain pollution load trend data.

3. The strategy analysis method for eutrophic water body treatment according to claim 1, characterized in that, The process involves analyzing the correlation coefficient matrix to determine the relationship between pollution sources and water quality, and then using pollution load trend data and correlation data to determine the initial water treatment strategy for each monitoring point area. This includes: The concentration change trend of pollutants is determined based on the segmented pollutant concentration data, and a correlation coefficient matrix is ​​constructed based on the concentration change trend. Water quality change analysis is performed based on segmented water quality data and pollutant concentration data to obtain water quality change data, and a water quality change time series diagram is generated based on the water quality change data. Based on water quality change data and pollutant concentration change trends, a spatiotemporal distribution map of pollutants is determined, and the spatial distribution relationship between pollutants and pollution sources is determined based on the spatiotemporal distribution map. The correlation data between pollution sources and water quality were determined based on the correlation coefficient matrix, water quality change time series diagram, and spatial distribution relationship. Pollutant reduction data are determined based on pollution load trend data and correlation data. Source control and interception strategies and ecological restoration strategies are determined based on pollutant reduction data, pollution load trend data and correlation data. Initial water treatment strategies for each monitoring point area are determined based on source control and interception strategies and ecological restoration strategies.

4. The strategy analysis method for eutrophic water body treatment according to claim 3, characterized in that, The construction of the correlation coefficient matrix based on the concentration change trend includes: Based on the concentration change trend, the characteristic coefficients of pollutants are analyzed to obtain the corresponding characteristic coefficient sequence, and the cross-correlation function is determined based on the characteristic coefficient sequence. A symmetric matrix is ​​constructed based on the cross-correlation function, and the correlation coefficient matrix is ​​determined based on the symmetric matrix.

5. The strategy analysis method for eutrophic water body treatment according to claim 1, characterized in that, The water body management simulation based on the initial water body management strategy combined with digital twin technology yields water body management simulation results, including: Digital twin models of each monitoring point area in eutrophic water bodies were constructed based on the water convection and diffusion model. Based on the digital twin model and the initial water treatment strategy, water treatment simulation was conducted to obtain the simulation results.

6. The strategy analysis method for eutrophic water body treatment according to claim 5, characterized in that, The digital twin models of each monitoring point area of ​​the eutrophic water body, constructed based on the water convection and diffusion model, include: A water convection-diffusion model was constructed based on hydrological and meteorological change data of each monitoring point area. A grid is set based on the boundary data of each monitoring point area in eutrophic water bodies, and a physical field model is constructed based on the hydrological data and pollutant data of each monitoring point area. Digital twin models of each monitoring point area were constructed based on the water convection diffusion model, grid volume, and physical field model.

7. The strategy analysis method for treating eutrophic water bodies according to claim 1, characterized in that, The analysis of collaborative conflict in water body treatment at each monitoring point area, based on water treatment simulation results and pollution migration analysis, yields collaborative conflict data, including: Water flow patterns are analyzed based on a seasonal autoregressive integral moving average model to obtain water flow pattern data. Based on water flow pattern data and water treatment simulation results, pollution migration analysis was conducted in the areas of each monitoring point to obtain pollution migration data. Based on the simulation results of water body treatment, simulated water pollution detection data and collaborative treatment effect data of each monitoring point area are extracted; Based on pollution migration data, simulated water pollution detection data, and collaborative governance effect data, a collaborative conflict analysis was conducted on the regional water body governance at each monitoring point to obtain collaborative conflict data.

8. The strategy analysis method for eutrophic water body treatment according to claim 1, characterized in that, The determination of auxiliary treatment strategies based on water body treatment simulation results includes: Microbial activity data were determined based on the collaborative treatment effect data from water body treatment simulation results, and aeration auxiliary data were determined based on the microbial activity data. Based on the simulation results of water body management, auxiliary data for the maintenance of aquatic ecosystems are determined, and auxiliary management strategies are determined based on the aeration auxiliary data and the auxiliary data for the maintenance of aquatic ecosystems.

9. The strategy analysis method for treating eutrophic water bodies according to claim 1, characterized in that, The adjustment of the initial water body treatment strategy based on collaborative conflict data to obtain the target water body treatment strategy includes: Constraints and reward functions are set based on collaborative conflict data, and a reinforcement learning-driven optimization model is constructed based on the constraints and reward functions. Based on the optimization model, the source control and pollution interception strategies and ecological restoration strategies in the initial water body treatment strategy are adjusted to obtain the target water body treatment strategy.

10. A strategy analysis system for the treatment of eutrophic water bodies, characterized in that, The system includes: The load trend analysis module is used to perform pollution load trend analysis on each monitoring point area of ​​eutrophic water bodies and obtain pollution load trend data. The governance strategy analysis module is used to analyze the correlation data between pollution sources and water quality based on the correlation coefficient matrix, and to determine the initial water body governance strategy for each monitoring point area based on pollution load trend data and correlation data. Water treatment simulation module: used to simulate water treatment based on the initial water treatment strategy and digital twin technology, and obtain water treatment simulation results; Collaborative Conflict Analysis Module: This module is used to conduct collaborative conflict analysis of water body treatment at various monitoring points based on water treatment simulation results and pollution migration analysis, and to obtain collaborative conflict data. The auxiliary governance strategy module is used to determine auxiliary governance strategies based on the simulation results of water body governance. Strategy adjustment module: used to adjust the initial water body treatment strategy based on collaborative conflict data to obtain the target water body treatment strategy; Water treatment module: Used to treat eutrophic water bodies based on target water treatment strategies and auxiliary treatment strategies.

Images