A river health assessment and health warning method

Abstract

The present invention relates to the technical field of river health assessment, and in particular to a river health assessment, health warning model and method. The method for constructing the river health assessment and health warning model comprises the following steps: obtaining basic data such as the physical form, hydrology and water resources, water quality, biological conditions and service functions of the target river; performing progressive cumulative increment calculations based on various types of target river data and calculating five types of river health indexes to obtain five types of river health indexes; performing correlation analysis based on various types of river health indexes, and calculating the pollution sensitivity index and pollution diffusion degree to obtain pollution sensitivity index and pollution diffusion degree data; constructing a river health warning model for the pollution sensitivity index and pollution diffusion degree data to obtain a multi-factor collaborative model of river health. The present invention optimizes the river health assessment and warning technology to make the river health assessment and warning more perfect.

Description

Technical Field

[0001] The present invention relates to the technical field of river health assessment, and in particular to a river health assessment and health early warning method. Background Art

[0002] Water is the source of life, the key to production, and the foundation of ecology. As the most important source of freshwater, rivers are not only a form of water available for human development and utilization, but also the living environment for tens of thousands of aquatic organisms. The health of rivers is the material foundation and guarantee for human survival and economic development. River systems exhibit systemic characteristics such as comprehensive integrity, organic interconnectedness, dynamic development, orderly development, and resistance to interference. These systemic characteristics are reflected in the structure and function of river systems, which determine their state. Furthermore, the structure and function of river systems are interconnected and mutually constrained, and their health is determined by their structure and function. Therefore, river health is essentially the health of the river system itself, requiring both the healthy structure of the river and the healthy functions of the river, ensuring that both the structure and functions of the river system are in good condition. A healthy river system not only maintains a reasonable structure and properly performs its various functions in the natural ecological and social evolution, but also maintains the sustainable development of the river itself, thereby ensuring the sustainable development and utilization of river resources. In the process of human development and utilization of rivers, due to inadequate protection or excessive use, many rivers have become polluted, dry, and depleted, degrading river ecosystems. This has impacted their natural and social functions, damaged the human ecological environment, and even led to a serious, irreversible ecological crisis, posing a serious threat to sustainable social development. Small and medium-sized rivers in southern China have complex flows, complex river networks, dense geometric networks, numerous tributaries, and complex cross-sectional morphologies. These rivers also exhibit complex and unstable geometry, with large fluctuations in flood peaks, and most rivers exhibit seasonal characteristics. River basins are small, with severely uneven precipitation, short rapids, poor storage capacity, and limited water diversion capabilities. Rivers are prone to siltation, requiring cross-sectional adjustments to restore their original structure. Furthermore, in recent years, rapid economic and social development in economically developed southern provinces has been accompanied by a continuous deterioration of river water environments, frequent damage to river ecosystems, and particularly prominent issues with river ecosystem health. However, traditional river health assessment and health warning methods suffer from inaccurate real-time river status analysis, resulting in significant errors in river health assessments and health warnings. Summary of the Invention

[0003] Based on this, it is necessary to provide a river health assessment and health warning method to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a river health assessment and health warning method is provided, the method comprising the following steps:

[0005] Step S1: Acquire target river physical morphology data, target river hydrological and water resource data, target river water quality status data, and target river biological status data;

[0006] Step S2: Analyzing the riverbank scour effect along the target river based on the target river hydrological and water resource data on the target river physical morphology data to obtain riverbank scour effect data along the target river; performing progressive cumulative increment calculation based on the riverbank scour effect data along the target river to obtain river sediment cumulative increment data; and calculating the river physical morphology health index based on the river sediment cumulative increment data to obtain the river physical morphology health index.

[0007] Step S3: Calculate theoretical runoff based on the target river's hydrological and water resource data to obtain theoretical runoff data for the target river; calculate cross-sectional flow fluctuation based on the river's physical morphological health index to obtain cross-sectional flow fluctuation data; perform flow-sedimentation rate fluctuation correlation analysis on the river's sediment accumulation increment data based on the cross-sectional flow fluctuation data to obtain spatially heterogeneous regression data for flow-sedimentation rate;

[0008] Step S4: Identify the organic matter content of the target river water quality status data to obtain the target river organic matter content data; perform decomposition effect compensation on the target river organic matter content data to obtain organic matter spatial decomposition efficiency compensation data; calculate the pollution sensitivity index of the target river biological condition data to obtain pollution sensitivity index data; calculate the pollution diffusion degree of the pollution sensitivity index data based on the river physical morphology health index and the flow-sedimentation rate spatial heterogeneity regression data to obtain pollution diffusion degree data;

[0009] Step S5: Based on the deep Q-network algorithm, a river health early warning model is constructed for the river physical morphology health index, flow-sedimentation rate spatial heterogeneous regression data, and pollution diffusion degree data to obtain a river health multi-factor collaborative model; the river health status is assessed according to the river health multi-factor collaborative model to obtain river health status assessment data.

[0010] This method acquires physical morphological data of target rivers, including information such as river channel shape, cross-section, and water depth. This data is crucial for assessing river stability, hydraulic properties, and land use impacts. Hydrological and water resource data, including information such as flow, water level, and runoff, can help understand a river's hydrodynamic characteristics, flood risk, and its impact on ecosystems and human activities. Water quality data reflects the concentration of pollutants in a river and their potential impacts on ecosystems and human health, and is an important basis for assessing river ecosystem health. Biological data, typically including information such as aquatic biodiversity, population size, and distribution, can assess a river's ecological health and biodiversity. Analyzing the scouring effects of river hydrological and water resource data on riverbanks can help understand riverbank erosion or sedimentation, assessing river channel stability, and assessing soil erosion levels. Accumulated sedimentation data can be used to track and quantify sediment trends in rivers, assessing river channel sedimentation and dredging, and thus impacting hydrodynamics and aquatic ecosystems. By integrating the above data analysis results into a comprehensive river physical morphological health index, the overall health of a river can be assessed. This index can provide important quantitative information to decision makers, helping to formulate conservation and management strategies to ensure the sustainable development and ecological health of rivers. Calculating theoretical runoff can quantify the hydrological response of rivers at different timescales. This is of great significance for water resource management and hydrological forecasting, particularly in flood management and water resource allocation. Analyzing the degree of cross-sectional flow fluctuation helps understand the hydrodynamic response of rivers under varying conditions. This data can help determine river stability and sediment transport characteristics, which in turn influence river ecological health and land use planning. Analyzing the spatially heterogeneous regression relationship between flow and sedimentation rate provides insight into the complexity and variability of river sedimentation processes. This helps predict changes in sediment quality under varying hydrological conditions, providing a scientific basis for river management and land use decisions. Identifying the organic matter content in target rivers helps assess the extent and sources of water pollution. This data provides crucial information for developing water quality improvement measures and environmental protection policies. Analyzing the spatial compensation of organic matter decomposition efficiency reveals the potential and limitations for river water quality improvement. This data is crucial for assessing ecosystem resilience and the sustainable use of water resources. Calculating a pollution sensitivity index can assess the response of aquatic organisms to water quality changes. This helps determine the potential ecological risk and impact range of specific pollutants in water bodies. By combining river physical health indices and spatially heterogeneous flow-sedimentation rate regression data to analyze the spatial distribution and variation of the pollution sensitivity index, we can quantify the extent of pollutant diffusion and spread in rivers. This provides a scientific basis for formulating pollution prevention and control strategies and protecting the ecological environment.The Deep Q-Network algorithm effectively integrates and processes the diverse data obtained in steps S3 and S4, including river physical health indices, spatially heterogeneous flow-sedimentation regression data, and pollution diffusion data. By comprehensively considering these data, the model can comprehensively understand the dynamics of river systems and their impacts on ecological health. Using the Deep Q-Network algorithm, the model can analyze and model the complex relationships and interactions among multiple factors. This collaborative analysis helps identify the key factors influencing river health and reveals the nonlinear correlations and dynamic changes between them. The Deep Q-Network algorithm possesses powerful predictive capabilities, enabling it to predict future river health based on historical data and current conditions. This helps identify potential ecological risks and environmental issues in advance, providing decision makers with timely warnings and response measures. Continuous optimization of the Deep Q-Network model can enhance its accuracy and stability. Model optimization involves adjusting algorithm parameters, selecting data features, and optimizing the model structure to ensure its continued effectiveness under complex environmental conditions. Based on this multi-factor collaborative model, a comprehensive assessment of river health can be conducted. This is not simply an assessment of a single indicator, but rather a comprehensive analysis that integrates multiple factors, including physical form, hydrological dynamics, water quality changes, and ecological responses. The assessment results provide quantitative river health status data, providing a scientific basis for decision makers and managers. These data can not only reflect the current health of the river, but also predict future problems and risks, so that corresponding management and protection measures can be taken. The assessment data provides an important reference for formulating effective river management strategies and environmental policies. Decision makers can prioritize which aspects of protection and improvement measures to take based on the assessment results to ensure the sustainable development and ecological health of the river. Therefore, the present invention is an improvement on a traditional river health assessment and health warning method, which solves the problem that a traditional river health assessment and health warning method has inaccurate real-time river status analysis, resulting in large errors in river health assessment and health warning, improves the accuracy of real-time river status analysis, and reduces the problem of large errors in river health assessment and health warning.

[0011] Preferably, step S2 comprises the following steps:

[0012] Step S21: analyzing the scouring effect of the riverbank along the target river based on the target river's hydrological and water resource data and the target river's physical morphological data to obtain the scouring effect data along the riverbank;

[0013] Step S22: Calculating the river curvature trend based on the target river physical morphology data to obtain river curvature trend data;

[0014] Step S23: simulating the river sedimentation effect based on the riverbank scouring effect data and the river curvature trend data to obtain river sedimentation effect simulation data;

[0015] Step S24: performing progressive cumulative increment calculation on the river sedimentation effect simulation data to obtain river sedimentation cumulative increment data;

[0016] Step S25: evaluating the connectivity and obstruction status of the river based on the river sediment accumulation increment data and the river sinuosity trend data to obtain the connectivity and obstruction status data of the river;

[0017] Step S26: Calculate the river physical morphology health index based on the river sediment accumulation increment data and the river connectivity and obstruction status data to obtain the river physical morphology health index.

[0018] By analyzing hydrological and water resource data of target rivers, this method can assess riverbank scour and erosion. This helps understand riverbank stability, predict the rate and extent of riverbank erosion, and provide a basis for land use planning and flood control management. Identifying and quantifying the effects of riverbank scour helps determine priorities for riverbank management and protection. This data can help decision makers take measures to reduce scour and protect land and infrastructure from the effects of hydraulic erosion. Calculating river sinuosity trends can assess changes in river channel morphology and their impact on hydrodynamics. Sinuosity trend data can reveal the morphological stability of rivers over long-term evolution, guiding river channel management and ecological restoration efforts. By simulating the sedimentation effects of rivers, the distribution of sediment at the river bottom and banks can be predicted. These simulated data help understand the geomorphological evolution of rivers and the spatial distribution of sediment quality, providing a scientific basis for river management and protection. By calculating progressive cumulative increments, changes in sediment quality at the river bottom and banks can be quantified. This data can help predict the need for river dredging and sediment management, optimizing water resource utilization and environmental management strategies. Analyzing river connectivity and obstruction can identify and assess spatial fragmentation or obstruction in river channels. This assessment data is crucial for protecting and restoring river biodiversity, fish migration, and the health of aquatic ecosystems. A river's morphological health index (MHI) is calculated by comprehensively considering a river's physical morphology, sedimentation effects, sinuosity trends, and connectivity and obstruction. This index quantifies the overall morphological condition and stability of a river, providing comprehensive assessment and decision-making support for river management and ecological protection.

[0019] Preferably, step S21 includes the following steps:

[0020] Step S211: extracting river hydrological flow velocity from target river hydrological and water resource data to obtain river hydrological flow velocity data;

[0021] Step S212: Calculating the scouring velocity along the riverbank based on the physical morphology data of the target river according to the river hydrological velocity data to obtain the scouring velocity data along the riverbank;

[0022] Step S213: analyzing the looseness characteristics of the matrix along the river bank based on the scouring velocity data along the river bank to obtain the looseness characteristics data of the matrix along the river bank;

[0023] Step S214: evaluating the toe scour intensity of the target river based on the looseness characteristic data of the riverbank matrix and the scour velocity data of the riverbank, thereby obtaining the toe scour intensity data of the target river;

[0024] Step S215: scour effect analysis of the riverbank along the target river is performed based on the scour intensity data of the slope foot of the target river and the loose characteristic data of the riverbank matrix along the target riverbank, to obtain scour effect data of the riverbank along the target riverbank.

[0025] The present invention obtains real-time flow velocity information by extracting hydrological velocity data from target rivers. This data serves as the foundation for assessing river dynamics and flow dynamics, providing accurate input for subsequent analysis. Analyzing river hydrological velocity data reveals the distribution of flow velocity at different locations within the river channel. This helps understand the magnitude of the impact of water on riverbanks and channel morphology, as well as its spatial variation. Based on hydrological velocity data, the scour velocity along the riverbanks can be calculated. This data can quantify the erosive potential of water on riverbanks and assess riverbank stability and scour risk. Analyzing scour velocity data along riverbanks can identify the looseness of the riverbank matrix. This helps understand the stability and scour resistance of riverbank soil, providing a basis for riverbank management and ecological restoration. Based on the looseness of the riverbank matrix and scour velocity data, the scour intensity at the toe of the target river can be assessed. This data can quantify the extent of scour in the toe area, providing a basis for designing protective structures and river channel improvement measures. Based on the toe scour intensity data and the looseness of the riverbank matrix, the scour effects along the riverbanks can be analyzed. This helps to comprehensively assess the health of river banks and identify high-risk areas and priority areas for protection.

[0026] Preferably, step S24 includes the following steps:

[0027] Step S241: performing sediment sequence characteristic analysis on the river sedimentation effect simulation data to obtain sediment sequence characteristic data;

[0028] Step S242: performing sequence triangulation on the river sedimentation effect simulation data according to the sediment sequence characteristic data to obtain river sediment sequence triangulation data;

[0029] Step S243: performing structured grid division on the river sedimentation effect simulation data according to the river sedimentary sequence triangulation data to obtain river sedimentation effect grid data;

[0030] Step S244: performing a numerical continuous flux calculation of the sedimentation effect on the river sedimentation effect grid data based on the finite volume method to obtain numerical continuous flux data of the sedimentation effect;

[0031] Step S245: Perform progressive cumulative increment calculation based on the numerical continuous flux data of the sedimentation effect to obtain river sedimentation cumulative increment data.

[0032] By analyzing the stratigraphic characteristics of sedimentation effect simulation data, the present invention can identify and extract key features of river sediment sequences, such as sediment thickness, composition, and structure. This data helps understand the temporal changes and spatial distribution characteristics of the sedimentation process. Based on the sediment sequence characteristic data, the river sedimentation effect simulation data is triangulated. This step converts the complex sedimentation effect data into a more manageable triangular mesh model, facilitating subsequent numerical calculations and analysis. Using the river sedimentation sequence triangulation data, the sedimentation effect simulation data is structured and meshed. Structured meshes can more accurately describe the spatial distribution and changes of river sedimentation effects, providing more accurate boundary conditions and initial states for numerical simulations. Based on the finite volume method, numerical continuous flux calculations are performed on the river sedimentation effect grid data. This step can quantify the sediment movement rate and flux at the river bottom and riverbank, revealing the dynamic changes and regional distribution during the sedimentation process. Based on the numerical continuous flux data of the sedimentation effect, a progressive cumulative increment calculation is performed. This analysis can predict the accumulation of river sediments and their spatial distribution, providing an important basis for river management and water resources planning.

[0033] Preferably, step S3 comprises the following steps:

[0034] Step S31: Calculating theoretical runoff volume based on the hydrological and water resource data of the target river to obtain theoretical runoff volume data of the target river;

[0035] Step S32: calculating the runoff deviation degree of the target river theoretical runoff data according to the river physical morphology health index to obtain river runoff deviation degree data;

[0036] Step S33: calculating the cross-sectional flow fluctuation degree based on the river runoff deviation degree data to obtain cross-sectional flow fluctuation degree data;

[0037] Step S34: performing flow-sedimentation rate fluctuation correlation analysis on the river sediment accumulation increment data according to the cross-section flow fluctuation degree data to obtain flow-sedimentation rate fluctuation correlation data;

[0038] Step S35: performing spatial heterogeneous regression analysis on the flow-sedimentation rate fluctuation correlation data to obtain flow-sedimentation rate spatial heterogeneous regression data.

[0039] The present invention calculates theoretical runoff data for a target river by calculating its theoretical runoff based on its hydrological and water resource data. This data serves as the foundation for assessing river water volume fluctuations and water resource management, providing accurate input for subsequent hydrological models and forecasts. Based on the river's physical health index, the theoretical runoff data for the target river is calculated to obtain runoff deviation data. This data quantifies the difference between actual runoff and predicted theoretical runoff, reflecting the true state of river water volume fluctuations. The runoff deviation data is then used to calculate cross-sectional flow fluctuations. This step helps analyze flow fluctuations at different river sections and reveals the spatial distribution of river water volume fluctuations. Based on the cross-sectional flow fluctuation data, a flow-sedimentation rate fluctuation correlation analysis is performed on the river's cumulative sedimentation data. This data helps understand the impact of water volume fluctuations on sediment transport and deposition rates, providing a quantitative basis for analyzing the dynamics of river sedimentation processes. Spatially heterogeneous regression analysis is performed on the flow-sedimentation rate fluctuation correlation data. This analysis can explore the relationship between flow and deposition rate variations within different geographical regions of a river, helping to identify factors influencing spatial heterogeneity in river sedimentation processes.

[0040] Preferably, step S34 includes the following steps:

[0041] Step S341: performing time series segmentation on the cross-sectional flow fluctuation degree data to obtain cross-sectional flow time series segmentation data;

[0042] Step S342: performing cumulative incremental nonlinear analysis on the river sediment cumulative incremental data to obtain cumulative incremental nonlinear data;

[0043] Step S343: performing nonlinear incremental variance calculation on the river sediment cumulative incremental data according to the cumulative incremental nonlinear data to obtain sediment cumulative nonlinear incremental variance data;

[0044] Step S344: performing multivariate statistical analysis on the sediment accumulation nonlinear incremental variance data based on the cross-sectional flow time series segmented data to obtain flow segmentation-sediment accumulation multivariate analysis data;

[0045] Step S345: performing flow-deposition rate fluctuation correlation analysis based on the flow segmentation-deposition accumulation multivariate analysis data to obtain flow-deposition rate fluctuation correlation data.

[0046] The present invention segments cross-sectional flow fluctuation data into time series segments, obtaining segmented cross-sectional flow time series data for different time periods. This segmented data helps analyze patterns and trends in river flow over different time periods, revealing the seasonal or cyclical characteristics of river flow fluctuations. Cumulative incremental nonlinear analysis is performed on river sediment accumulation data to obtain nonlinear data reflecting the complexity of the sedimentation process. This data can identify the presence of nonlinear effects in the sedimentation process and help understand the heterogeneous distribution of sediments in time and space. Based on the cumulative incremental nonlinear data, the nonlinear incremental variance of the river sediment accumulation is calculated. This metric quantifies the uncertainty and volatility in the sedimentation process, providing quantitative support for understanding sediment movement patterns. Based on the segmented cross-sectional flow time series data, multivariate statistical analysis is performed on the cumulative nonlinear incremental variance data. These results reveal multivariate relationships in the sedimentation process under different flow conditions, helping to understand the impact of water volume fluctuations on the complexity of the sedimentation process. Based on the flow segmentation-sediment accumulation multivariate analysis data, flow-sedimentation rate fluctuation correlation analysis is performed. This analysis can further explore how water volume fluctuations affect the deposition rate and spatial distribution of sediments, providing a deep understanding and quantitative analysis of the dynamic changes in river sedimentation processes.

[0047] Preferably, step S35 includes the following steps:

[0048] Step S351: performing spatial heterogeneity analysis on the flow-sedimentation rate fluctuation correlation data to obtain flow-sedimentation rate fluctuation spatial heterogeneity data;

[0049] Step S352: constructing an adjacency matrix between different spatial structure points of the flow-deposition rate fluctuation correlation data according to the flow-deposition rate fluctuation spatial heterogeneous data to obtain a flow-deposition rate spatial heterogeneous matrix;

[0050] Step S353: Calculate the spatial autocorrelation coefficient between different spatial structure points of the flow-sedimentation rate spatial heterogeneous matrix to obtain the spatial autocorrelation coefficient;

[0051] Step S354: performing a multivariate spatial heterogeneous regression analysis on the flow-sedimentation rate spatial heterogeneity matrix according to the spatial autocorrelation coefficient to obtain flow-sedimentation rate spatial heterogeneous regression data.

[0052] The present invention can reveal the spatial differences and distribution patterns between flow changes and sedimentation rate changes in different geographical regions by performing spatial heterogeneity analysis on flow-sedimentation rate fluctuation correlation data. This helps to understand the geographical characteristics and spatial heterogeneity of river sedimentation processes in different regions. Based on the flow-sedimentation rate fluctuation spatial heterogeneous data, an adjacency matrix between different spatial structure points is constructed. This matrix reflects the spatial correlation relationship between different locations and helps to identify the similarities or differences in sedimentation rate responses of adjacent or close areas. The spatial autocorrelation coefficients of the flow-sedimentation rate spatial heterogeneous matrix are calculated. These coefficients quantify the similarity or correlation degree of sedimentation rate changes between different spatial structure points, helping to understand the spatial autocorrelation characteristics of river sedimentation processes. Based on the spatial autocorrelation coefficients, a multivariate spatial heterogeneous regression analysis is performed on the flow-sedimentation rate spatial heterogeneous matrix. This analysis explores the complex relationship between flow changes and sedimentation rate fluctuations between different spatial structure points, further revealing the impact of the geographical environment on the river sedimentation process.

[0053] Preferably, step S4 comprises the following steps:

[0054] Step S41: performing organic matter content identification on the target river water quality status data to obtain the target river organic matter content data;

[0055] Step S42: estimating the spatial decomposition efficiency of the target river organic matter content data based on the flow-sedimentation rate spatial heterogeneity regression data to obtain organic matter spatial decomposition efficiency data;

[0056] Step S43: performing decomposition effect compensation on the organic matter spatial decomposition efficiency data according to the river physical morphology health index to obtain organic matter spatial decomposition efficiency compensation data;

[0057] Step S44: Calculating the benthic diatom index of the target river biological status data to obtain the benthic diatom index of the target river;

[0058] Step S45: calculating the pollution sensitivity index of the biological condition data of the target river according to the benthic diatom index of the target river to obtain pollution sensitivity index data;

[0059] Step S46: Calculate the pollution diffusion degree of the pollution sensitivity index data based on the river physical morphology health index and the flow-sedimentation rate spatial heterogeneity regression data to obtain pollution diffusion degree data.

[0060] The present invention identifies the organic matter content of target rivers by analyzing their water quality data to obtain accurate data on their organic matter content. This data is crucial for assessing the degree of water pollution and water quality. Spatially heterogeneous flow-sedimentation rate regression data is used to estimate the spatial decomposition efficiency of the target river's organic matter content data. This step helps determine the organic matter degradation efficiency at different locations, thereby understanding geographical differences in the water purification process. Spatial decomposition efficiency data is compensated for using the river's physical health index. This factor influencing topography, water flow, and sediment on organic matter degradation improves the accuracy of the spatial decomposition efficiency estimate. By calculating the benthic diatom index based on the biological status data of the target river, an important indicator reflecting the biodiversity and ecological health of the water body is obtained. The benthic diatom index is commonly used to assess the nutrient status of water bodies and the health of ecosystems. Based on the benthic diatom index of the target river, a pollution sensitivity index is calculated for the biological status data. This index reflects the response of benthic organisms to environmental pollution and provides important data for assessing the impact of water pollution on ecosystems. The pollution sensitivity index data is combined with the river's physical health index and spatially heterogeneous flow-sedimentation rate regression data to calculate the extent of pollution spread. This analysis helps to understand the propagation and diffusion patterns of pollutants in water bodies and assess the impact of pollution sources on aquatic ecology.

[0061] Preferably, step S46 includes the following steps:

[0062] Step S461: performing pollution diffusion simulation on the pollution sensitivity index data according to the river physical morphology health index and the flow-sedimentation rate spatial heterogeneity regression data to obtain pollution diffusion simulation data;

[0063] Step S462: performing diffusion distribution azimuth analysis on the pollution diffusion simulation data to obtain diffusion distribution azimuth data;

[0064] Step S463: performing pollution diffusion directionality analysis on the pollution diffusion simulation data according to the diffusion distribution azimuth data to obtain pollution diffusion directionality data;

[0065] Step S464: performing pollution accumulation effect analysis on the pollution diffusion simulation data according to the pollution diffusion directionality data to obtain pollution accumulation effect data;

[0066] Step S465: Calculate the pollution diffusion degree based on the pollution accumulation effect data to obtain pollution diffusion degree data.

[0067] This invention uses data from the river's physical health index and spatially heterogeneous flow-sedimentation rate regression to perform pollution diffusion simulation on pollution sensitivity index data. This simulation can predict the spread and distribution of pollutants in water bodies, helping to understand the diffusion characteristics of pollutants under different geographical conditions. Diffusion distribution azimuth analysis is performed on the pollution diffusion simulation data to determine the primary directions and trends of pollutant diffusion. This analysis reveals the dominant directions of pollutant diffusion in water bodies and provides a preliminary assessment of environmental impacts. Based on the diffusion distribution azimuth data, the pollution diffusion simulation data is further subjected to directional analysis. This step helps determine the specific directions and trends of pollutant diffusion, providing a basis for further analysis of pollutant diffusion paths in water bodies. Based on the pollution diffusion directional data, the pollution diffusion simulation data is subjected to pollution accumulation effect analysis. This analysis assesses the accumulation of pollutants in specific directions, revealing the formation of concentrated pollution areas or hotspots, and assisting in decision-making for environmental protection and resource management. Finally, the pollution diffusion extent is calculated based on the pollution accumulation effect data. This data quantifies the extent of pollutant diffusion and the impact range in water bodies, providing a scientific basis for assessing the extent of environmental pollution and taking appropriate measures.

[0068] Preferably, step S5 comprises the following steps:

[0069] Step S51: Based on the deep Q-network algorithm, multi-factor synergistic impact learning is performed on the river physical morphology health index, flow-sedimentation rate spatial heterogeneous regression data, and pollution diffusion degree data to obtain multi-factor synergistic impact data of river status;

[0070] Step S52: constructing a river health early warning model based on the multi-factor collaborative impact data of river status to obtain a river health multi-factor collaborative model;

[0071] Step S53: Perform river health status assessment based on the river health multi-factor collaborative model to obtain river health status assessment data.

[0072] The present invention utilizes a deep Q-network algorithm, combined with river physical morphology health index, flow-sedimentation rate spatial heterogeneous regression data, and pollution diffusion degree data, to conduct multi-factor synergistic impact learning. This process can comprehensively consider the complex impacts of different factors on river health and extract the interaction patterns and correlation levels between them. Based on the multi-factor synergistic impact data of river status obtained in step S51, a river health early warning model is constructed. This model can predict the changing trends and risks of river health status and detect environmental problems or water quality deterioration in advance. The river health status is evaluated using the multi-factor synergistic model of river health constructed in step S52. This process can quantify the health level of the river and provide scientifically based health assessment data based on a comprehensive multi-factor impact analysis.

[0073] The present invention provides beneficial effects by acquiring physical morphological data of target rivers. Physical morphological data includes information such as river channel shape, cross-section, and water depth. This data is crucial for assessing river stability, hydraulic characteristics, and land use impacts. Hydrological and water resource data, including information such as flow, water level, and runoff, can help understand a river's hydrodynamic characteristics, flood risk, and its impact on ecosystems and human activities. Water quality data reflects the concentration of pollutants in a river and their potential impacts on ecosystems and human health, and is an important basis for assessing the health of river ecosystems. Biological status data, which typically includes information such as aquatic biodiversity, population size, and distribution, can assess the ecological health and biodiversity of a river. Analyzing the scouring effects of river hydrological and water resource data on riverbanks can help understand riverbank erosion or sedimentation, and assess river channel stability and soil erosion levels. Based on sediment accumulation data, it is possible to track and quantify the changing trends of river sedimentation, assess river channel sedimentation and dredging, and thus, their impact on hydrodynamics and aquatic ecosystems. By integrating the river physical morphological health index and the above data analysis results, the overall health of a river can be assessed. This index provides important quantitative information for decision-makers, helping to formulate conservation and management strategies to ensure the sustainable development and ecological health of rivers. By calculating theoretical runoff, the hydrological response capacity of rivers at different time scales can be quantified. This is of great significance for water resources management and hydrological forecasting, particularly in flood management and water resource allocation. Analyzing the degree of cross-sectional flow fluctuation helps understand the hydrodynamic response of rivers under varying conditions. This data can help determine river stability and sediment transport characteristics, which in turn influence river ecological health and land use planning. Analyzing the spatially heterogeneous regression relationship between flow and sedimentation rate provides insights into the complexity and variability of river sedimentation processes. This helps predict changes in sediment quality under varying hydrological conditions, providing a scientific basis for river management and land use decisions. Identifying the organic matter content in target rivers helps assess the extent and sources of water pollution. These data provide crucial information for developing water quality improvement measures and environmental protection policies. Analyzing the spatial compensation of organic matter decomposition efficiency can reveal the potential and limitations for river water quality improvement. These data are crucial for assessing ecosystem resilience and the sustainable use of water resources. By calculating the Pollution Sensitivity Index (PSI), we can assess the responsiveness of aquatic organisms to changes in water quality. This helps determine the potential ecological risk and impact of specific pollutants in water bodies. By combining data from the River Physical Health Index and spatially heterogeneous flow-sedimentation rate regression, we can analyze the spatial distribution and variation of the PSI and quantify the extent of pollutant diffusion and spread within rivers. This provides a scientific basis for developing pollution prevention and control strategies and protecting the ecological environment.The Deep Q-Network algorithm effectively integrates and processes the diverse data obtained in steps S3 and S4, including river physical health indices, spatially heterogeneous flow-sedimentation regression data, and pollution diffusion data. By comprehensively considering these data, the model can comprehensively understand the dynamics of river systems and their impacts on ecological health. Using the Deep Q-Network algorithm, the model can analyze and model the complex relationships and interactions among multiple factors. This collaborative analysis helps identify the key factors influencing river health and reveals the nonlinear correlations and dynamic changes between them. The Deep Q-Network algorithm possesses powerful predictive capabilities, enabling it to predict future river health based on historical data and current conditions. This helps identify potential ecological risks and environmental issues in advance, providing decision makers with timely warnings and response measures. Continuous optimization of the Deep Q-Network model can enhance its accuracy and stability. Model optimization involves adjusting algorithm parameters, selecting data features, and optimizing the model structure to ensure its continued effectiveness under complex environmental conditions. Based on this multi-factor collaborative model, a comprehensive assessment of river health can be conducted. This is not simply an assessment of a single indicator, but rather a comprehensive analysis that integrates multiple factors, including physical form, hydrological dynamics, water quality changes, and ecological responses. The assessment results provide quantitative river health status data, providing a scientific basis for decision makers and managers. These data can not only reflect the current health of the river, but also predict future problems and risks, so that corresponding management and protection measures can be taken. The assessment data provides an important reference for formulating effective river management strategies and environmental policies. Decision makers can prioritize which aspects of protection and improvement measures to take based on the assessment results to ensure the sustainable development and ecological health of the river. Therefore, the present invention is an improvement on a traditional river health assessment and health warning method, which solves the problem that a traditional river health assessment and health warning method has inaccurate real-time river status analysis, resulting in large errors in river health assessment and health warning, improves the accuracy of real-time river status analysis, and reduces the problem of large errors in river health assessment and health warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic diagram of the steps of a river health assessment and health warning method;

[0075] Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0076] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0077] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0078] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0079] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0080] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0081] To achieve this, please refer to Figures 1 to 3 , a river health assessment and health warning method, the method comprising the following steps:

[0082] Step S1: Acquire target river physical morphology data, target river hydrological and water resource data, target river water quality status data, and target river biological status data;

[0083] Step S2: Analyzing the riverbank scour effect along the target river based on the target river hydrological and water resource data on the target river physical morphology data to obtain riverbank scour effect data along the target river; performing progressive cumulative increment calculation based on the riverbank scour effect data along the target river to obtain river sediment cumulative increment data; and calculating the river physical morphology health index based on the river sediment cumulative increment data to obtain the river physical morphology health index.

[0084] Step S3: Calculate theoretical runoff based on the target river's hydrological and water resource data to obtain theoretical runoff data for the target river; calculate cross-sectional flow fluctuation based on the river's physical morphological health index to obtain cross-sectional flow fluctuation data; perform flow-sedimentation rate fluctuation correlation analysis on the river's sediment accumulation increment data based on the cross-sectional flow fluctuation data to obtain spatially heterogeneous regression data for flow-sedimentation rate;

[0085] Step S4: Identify the organic matter content of the target river water quality status data to obtain the target river organic matter content data; perform decomposition effect compensation on the target river organic matter content data to obtain organic matter spatial decomposition efficiency compensation data; calculate the pollution sensitivity index of the target river biological condition data to obtain pollution sensitivity index data; calculate the pollution diffusion degree of the pollution sensitivity index data based on the river physical morphology health index and the flow-sedimentation rate spatial heterogeneity regression data to obtain pollution diffusion degree data;

[0086] Step S5: Based on the deep Q-network algorithm, a river health early warning model is constructed for the river physical morphology health index, flow-sedimentation rate spatial heterogeneous regression data, and pollution diffusion degree data to obtain a river health multi-factor collaborative model; the river health status is assessed according to the river health multi-factor collaborative model to obtain river health status assessment data.

[0087] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a river health assessment and health warning method of the present invention. In this example, the river health assessment and health warning method includes the following steps:

[0088] Step S1: Acquire target river physical morphology data, target river hydrological and water resource data, target river water quality status data, and target river biological status data;

[0089] In this embodiment of the present invention, laser scanners (LiDAR) and multi-band remote sensing imaging technology are used to measure river cross-sections and longitudinal profiles. Laser scanners perform high-precision measurements of riverbanks and bottoms, generating three-dimensional point cloud data. This data is used to describe the topographic features of the riverbed and banks. Remote sensing imaging technology provides surface cover information for the river area, which is used to analyze changes in the river's surrounding environment. Automated flow measurement instruments, including velocity meters and flow meters, are installed in the target river to record real-time flow and velocity data. These devices should have high-frequency data acquisition capabilities to capture flow fluctuations over time. Rain gauges and weather stations are also installed to collect meteorological data such as precipitation and evaporation. This data helps understand changes in the river's hydrological environment. Water quality sensors are installed at various points along the river to monitor major pollutants in the water, such as suspended matter, dissolved oxygen, and ammonia nitrogen, in real time. Water quality sensors require regular calibration to ensure data accuracy, and sampling and analysis are used to verify data quality to ensure that the acquired water quality data accurately reflects the river's actual water quality. Underwater cameras and biological samplers are used to collect biological data in the river. Underwater cameras observe the riverbed and water, recording the types and numbers of organisms in the river ecosystem. Biological samplers regularly collect samples from the river, analyzing fish, plankton, and other organisms in the water to assess the health of organisms and population changes.

[0090] Step S2: Analyzing the riverbank scour effect along the target river based on the target river hydrological and water resource data on the target river physical morphology data to obtain riverbank scour effect data along the target river; performing progressive cumulative increment calculation based on the riverbank scour effect data along the target river to obtain river sediment cumulative increment data; and calculating the river physical morphology health index based on the river sediment cumulative increment data to obtain the river physical morphology health index.

[0091] In this embodiment of the present invention, river velocity, flow rate, and riverbank physical characteristics are input into a computational fluid dynamics (CFD) model to simulate riverbank scour under different flow conditions. A high-resolution gridded model is used to perform detailed numerical simulation of the riverbank and analyze the erosive effects of water flow on riverbank soil. The output is riverbank scour effect data along the river, including scour depth and scour rate data under different flow rates and hydrological conditions. This riverbank scour effect data along the riverbank is input into a progressive cumulative increment calculation model to calculate the cumulative change in river scour effect. By integrating the time series of riverbank scour effect data, river sediment accumulation data is obtained, generating river sediment accumulation increment data. This process requires the use of numerical integration methods to gradually update river sediment changes. Based on the river sediment accumulation increment data, a river morphological health index is calculated. A standardized method is used to convert the sediment accumulation data into a river morphological health index, which reflects the physical health of the river. The calculation considers sediment influencing factors, such as sediment particle size and distribution, as well as changes in riverbank stability. The resulting river morphological health index is used to assess the stability and health of the river under current environmental conditions.

[0092] Step S3: Calculate theoretical runoff based on the target river's hydrological and water resource data to obtain theoretical runoff data for the target river; calculate cross-sectional flow fluctuation based on the river's physical morphological health index to obtain cross-sectional flow fluctuation data; perform flow-sedimentation rate fluctuation correlation analysis on the river's sediment accumulation increment data based on the cross-sectional flow fluctuation data to obtain spatially heterogeneous regression data for flow-sedimentation rate;

[0093] In this embodiment of the present invention, a hydrological model is used to calculate theoretical runoff for a river basin. Inputs include rainfall data, basin soil type, topographic parameters, and river channel characteristics. The model uses the Soil Conservation Service Curve Number (SCS-CN) method or a similar calculation formula to calculate runoff for each rainfall event. The output is theoretical runoff data for the target river, reflecting the expected flow rate under specific rainfall conditions. Combined with the river's physical health index, flow fluctuations at river sections are analyzed. Using measured cross-sectional flow data and health index data, flow fluctuations are assessed using a fluctuation analysis model (such as standard deviation or coefficient of variation calculation). The output cross-sectional flow fluctuation data reveals the stability of flow changes at the river section. Cross-sectional flow fluctuation data and river sediment accumulation increment data are input into a flow-sedimentation rate fluctuation correlation analysis model. Regression analysis techniques are used to examine the relationship between flow fluctuations and sedimentation rate. The specific method involves establishing a regression equation and analyzing the impact of flow variations on sediment accumulation. The output is spatially heterogeneous flow-sedimentation rate regression data, describing the spatially varying relationship between flow and sedimentation rate.

[0094] Step S4: Identify the organic matter content of the target river water quality status data to obtain the target river organic matter content data; perform decomposition effect compensation on the target river organic matter content data to obtain organic matter spatial decomposition efficiency compensation data; calculate the pollution sensitivity index of the target river biological condition data to obtain pollution sensitivity index data; calculate the pollution diffusion degree of the pollution sensitivity index data based on the river physical morphology health index and the flow-sedimentation rate spatial heterogeneity regression data to obtain pollution diffusion degree data;

[0095] In an embodiment of the present invention, HPLC is used to analyze the organic matter content in river water samples. After filtration and pretreatment, the water samples are separated and quantified using an HPLC instrument. Based on the chromatogram and calibration curve, organic matter concentration data is determined to generate organic matter content data for the target river. Spatial decomposition effects are compensated for on the organic matter content data. Spatial interpolation methods (such as kriging) are used to decompose the data and compensate for environmental factors (such as watershed characteristics and pollution source distribution) to generate data compensated for spatial decomposition efficiency. This process adjusts for errors caused by spatial variation and improves data accuracy. A pollution sensitivity index is calculated for the biological status data of the target river. Based on the species, abundance, and health of organisms, ecological indicators (such as the biotic index) are used to calculate the pollution sensitivity of biological communities to pollution, providing a quantitative assessment of the ecological health of the river. The pollution sensitivity index data is combined with spatially heterogeneous regression data on the river's physical morphological health index and flow-sedimentation rate to calculate the degree of pollution diffusion. A multi-factor weighted model comprehensively considers morphological health, flow variation, and sedimentation to calculate the degree of pollutant diffusion in the river. The final data on the degree of pollution diffusion are obtained, which reflects the scope and intensity of the impact of pollution on the river ecosystem.

[0096] Step S5: Based on the deep Q-network algorithm, a river health early warning model is constructed for the river physical morphology health index, flow-sedimentation rate spatial heterogeneous regression data, and pollution diffusion degree data to obtain a river health multi-factor collaborative model; the river health status is assessed according to the river health multi-factor collaborative model to obtain river health status assessment data.

[0097] In an embodiment of the present invention, a deep Q-network algorithm is used to construct a river health early warning model. First, the river physical morphology health index, flow-sedimentation rate spatial heterogeneous regression data, and pollution diffusion degree data are input into the Q-network model. The model is trained based on historical data and real-time monitoring data through a reinforcement learning algorithm to optimize the decision-making strategy. Specifically, it includes selecting an appropriate network structure, setting training parameters, and improving model accuracy through multiple rounds of training and verification. The constructed multi-factor collaborative model of river health is used to assess the health status. The data input to the model include the river's health index, flow-sedimentation rate data, and pollution diffusion degree. The model analyzes these input data, outputs river health status assessment data, and provides a comprehensive assessment result of the river's health status. These results include health status scores and warning levels, which are used to guide management decisions and formulate protection measures.

[0098] Preferably, step S2 includes the following steps:

[0099] Step S21: analyzing the scouring effect of the riverbank along the target river based on the target river's hydrological and water resource data and the target river's physical morphological data to obtain the scouring effect data along the riverbank;

[0100] Step S22: Calculating the river curvature trend based on the target river physical morphology data to obtain river curvature trend data;

[0101] Step S23: simulating the river sedimentation effect based on the riverbank scouring effect data and the river curvature trend data to obtain river sedimentation effect simulation data;

[0102] Step S24: performing progressive cumulative increment calculation on the river sedimentation effect simulation data to obtain river sedimentation cumulative increment data;

[0103] Step S25: evaluating the connectivity and obstruction status of the river based on the river sediment accumulation increment data and the river sinuosity trend data to obtain the connectivity and obstruction status data of the river;

[0104] Step S26: Calculate the river physical morphology health index based on the river sediment accumulation increment data and the river connectivity and obstruction status data to obtain the river physical morphology health index.

[0105] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0106] Step S21: analyzing the scouring effect of the riverbank along the target river based on the target river's hydrological and water resource data and the target river's physical morphological data to obtain the scouring effect data along the riverbank;

[0107] In this embodiment of the present invention, the flow and velocity of the target river are measured using a flow meter and a tachometer to obtain basic hydrological data. This data is then input into a CFD model, which should include the geometric characteristics of the riverbank and soil properties. Simulation conditions, such as flow velocity, flow rate, and riverbank material properties, are set within the CFD model. The model is used to simulate the riverbank scour effect under different flow rates and flow rates, outputting the riverbank scour depth and rate. These simulation results serve as the riverbank scour effect data along the route, describing the extent of riverbank scour under different hydrological conditions.

[0108] Step S22: Calculating the river curvature trend based on the target river physical morphology data to obtain river curvature trend data;

[0109] In an embodiment of the present invention, when calculating the trend of river tortuosity, it is necessary to first obtain the physical morphological data of the target river, including the river's cross-section and channel shape data. This data can be obtained through remote sensing imagery and terrestrial laser scanning. The specific steps include: using remote sensing imagery and laser scanners to obtain river cross-sectional data and channel shape data. This data should include the curve characteristics of the river and its changes. The data is analyzed using a tortuosity calculation formula (such as the channel tortuosity index). Based on the river cross-sectional and shape data, the trend of river tortuosity changes is calculated. The output river tortuosity trend data reflects the degree of tortuosity of the river channel and its changing trend, and is used to evaluate the evolution of river morphology.

[0110] Step S23: simulating the river sedimentation effect based on the riverbank scouring effect data and the river curvature trend data to obtain river sedimentation effect simulation data;

[0111] In this embodiment of the present invention, high-resolution remote sensing imagery and digital elevation models (DEMs) are used to analyze the target river using a geographic information system (GIS) platform. Riverbank scour data are used to determine changes in river banks and areas of riverbed siltation in various sections. Combined with river sinuosity trend data, the river's curve radius, changes in water velocity, and water and sediment movement characteristics are analyzed. Subsequently, numerical simulation software (such as fluid dynamics models) is used to simulate riverbed sedimentation under different flow conditions, simulating changes in riverbed sedimentation under different flow conditions and predicting the spatial distribution and trends of riverbed siltation and scour.

[0112] Step S24: performing progressive cumulative increment calculation on the river sedimentation effect simulation data to obtain river sedimentation cumulative increment data;

[0113] In this embodiment of the present invention, a progressive cumulative increment calculation is performed on the simulated river sedimentation data. This step utilizes numerical analysis methods using the simulated river sedimentation data. Using numerical integration or differential algorithms, the amount of sedimentation in the riverbed is cumulatively calculated based on the changes in sedimentation and scour data within each time step. By gradually calculating the sedimentation increments for each section of the riverbed, the accumulation of riverbed sediment at each time point is determined, providing data support for subsequent connectivity and obstruction assessments.

[0114] Step S25: evaluating the connectivity and obstruction status of the river based on the river sediment accumulation increment data and the river sinuosity trend data to obtain the connectivity and obstruction status data of the river;

[0115] In this embodiment of the present invention, river connectivity and obstruction status are assessed based on cumulative sedimentation data and river sinuosity trend data. By analyzing the cumulative sedimentation data, siltation nodes or bottleneck areas within the river channel are identified. Combined with river sinuosity trend data, the impact of these areas on water connectivity is assessed, and flow paths and obstructions under different flow conditions are analyzed. Network analysis tools, such as river network models or connectivity analysis algorithms, are used to quantitatively assess the connectivity of each river segment and identify flow obstructions.

[0116] Step S26: Calculate the river physical morphology health index based on the river sediment accumulation increment data and the river connectivity and obstruction status data to obtain the river physical morphology health index.

[0117] In this embodiment of the present invention, a river's physical health index is calculated based on cumulative sedimentation data and river connectivity and obstruction data. This data is integrated with numerical calculation models or indicator evaluation methods to calculate the river's physical health index. This index quantitatively assesses the current health of a river by considering factors such as the degree of river sedimentation, the smoothness of water flow, and the stability of its morphology. These data and indicators can provide a scientific basis for river management and protection, helping decision-makers develop effective river management measures and ecological restoration strategies.

[0118] In another embodiment, the river physical morphology health index is calculated based on the river sediment accumulation increment data and the river connectivity and obstruction status data. First, the sediment accumulation increment and connectivity and obstruction status data are combined to set a health index calculation model, which comprehensively considers the impact of sediments on the physical morphology of the river, changes in connectivity and its potential threat to the ecosystem. In a specific implementation, the calculation formula of the health index is first defined. The formula should include a weighted combination of sediment accumulation, connectivity and obstruction degree, and other relevant indicators. Using data analysis tools, the sediment accumulation increment data and connectivity and obstruction status data are input into the calculation formula to obtain the health index of the river's physical morphology. The output results include the health index value and its corresponding health assessment level, which help to conduct a comprehensive assessment and early warning of the river's health status. Among them, the calculation formula for the health index is defined as:

[0119]

[0120] in, represents the river physical health index, represents the normalized value of the cumulative increment of river sedimentation, represents the maximum value of the cumulative sedimentation increment, A standardized value indicating the connectivity and obstruction of a river. Indicates the maximum value of the connectivity blocking condition, represents the river sinuosity interval, Indicates the maximum interval curvature value of the river curvature, Indicates the indicator weighted threshold.

[0121] Preferably, step S21 includes the following steps:

[0122] Step S211: extracting river hydrological flow velocity from target river hydrological and water resource data to obtain river hydrological flow velocity data;

[0123] Step S212: Calculating the scouring velocity along the riverbank based on the physical morphology data of the target river according to the river hydrological velocity data to obtain the scouring velocity data along the riverbank;

[0124] Step S213: analyzing the looseness characteristics of the matrix along the river bank based on the scouring velocity data along the river bank to obtain the looseness characteristics data of the matrix along the river bank;

[0125] Step S214: evaluating the toe scour intensity of the target river based on the looseness characteristic data of the riverbank matrix and the scour velocity data of the riverbank, thereby obtaining the toe scour intensity data of the target river;

[0126] Step S215: scour effect analysis of the riverbank along the target river is performed based on the scour intensity data of the slope foot of the target river and the loose characteristic data of the riverbank matrix along the target riverbank, to obtain scour effect data of the riverbank along the target riverbank.

[0127] In an embodiment of the present invention, river hydrological velocity extraction is performed on the hydrological and water resource data of a target river. First, water velocity measurements are performed at different sections of the river using hydrological measuring instruments to obtain water velocity data under different flow conditions. Accurate velocity data is obtained using velocity measuring equipment, such as electromagnetic current meters or buoy tracking methods. By performing measurements at multiple sections and taking into account flow rate variations, comprehensive river hydrological velocity data is obtained. This data provides a basis for subsequent analysis of river physical morphology data and calculation of scour flow velocities along the riverbanks. Based on the river hydrological velocity data, scour flow velocities along the riverbanks are calculated for the physical morphology data of the target river. Using the acquired hydrological velocity data, combined with the geometric characteristics of the river channel and hydraulic principles, the scour flow velocities along the riverbanks are calculated. Using hydraulic formulas and numerical simulation methods, the flow dynamics under different flow conditions are modeled to predict the velocity distribution of the water flow within the river channel. Using this data, the scour potential of the riverbanks and the impact of velocity variations on the physical morphology of the river channel are assessed, providing data support for subsequent analysis of the looseness of the matrix. Analyze the looseness of the riverbank matrix along the route based on scour velocity data. Utilize the measured scour velocity data to analyze the looseness of the matrix along the riverbank. Obtain riverbank geological information and soil types through field surveys or remote sensing image analysis. Combined with the scour velocity data, assess the stability and scour resistance of the riverbank matrix. Utilize geomechanics and soil mechanics principles to quantitatively analyze the looseness of the lithology and soil along the route, as well as their susceptibility to scour, providing a basis for subsequent assessment of toe scour intensity. Based on the looseness of the matrix along the route and the scour velocity data, assess the toe scour intensity of the target river's physical morphology. Integrating the looseness of the matrix and scour velocity data, analyze the toe scour risk of different areas along the river. Calculate the scour intensity index for each bank segment through numerical simulation or statistical analysis to assess the stability and changing trends of the bank slope topography. These data provide a foundation for analyzing the scour effects along the route and help understand the physical mechanisms behind changes in river channel morphology. Scour effects along the target riverbanks are analyzed based on data on scour intensity at the toe of the target river and the looseness of the riverbank matrix. Using these data, the scour effects along the riverbanks are analyzed. Through numerical simulations or field observations, the impact of scour on riverbank morphology is quantitatively described, and riverbank erosion and sedimentation are predicted under varying scour intensities. These results provide a basis for river health assessments and scientific support for river managers in developing protection and restoration measures.

[0128] Preferably, step S24 includes the following steps:

[0129] Step S241: performing sediment sequence characteristic analysis on the river sedimentation effect simulation data to obtain sediment sequence characteristic data;

[0130] Step S242: performing sequence triangulation on the river sedimentation effect simulation data according to the sediment sequence characteristic data to obtain river sediment sequence triangulation data;

[0131] Step S243: performing structured grid division on the river sedimentation effect simulation data according to the river sedimentary sequence triangulation data to obtain river sedimentation effect grid data;

[0132] Step S244: performing a numerical continuous flux calculation of the sedimentation effect on the river sedimentation effect grid data based on the finite volume method to obtain numerical continuous flux data of the sedimentation effect;

[0133] Step S245: Perform progressive cumulative increment calculation based on the numerical continuous flux data of the sedimentation effect to obtain river sedimentation cumulative increment data.

[0134] In an embodiment of the present invention, sediment sequence characteristics are analyzed for simulated river sedimentation effect data. First, relevant parameters of the sediment sequence, such as sediment thickness, particle size distribution, and sediment type, are extracted from the simulated data. Using geological and sedimentological analysis methods, the spatial and temporal characteristics of the river sediment sequence are analyzed in detail. Through site surveys or remote sensing image interpretation, the formation mechanisms and geological historical background of different sedimentary layers are determined. Combining these data, a quantitative description of the sediment sequence characteristics is established, providing basic data support for subsequent sequence triangulation. Sequence triangulation is performed on the simulated river sedimentation effect data based on the sediment sequence characteristic data. Using a geographic information system (GIS) or professional geological modeling software, the sediment sequence characteristic data is converted into a three-dimensional terrain model. Using a triangulated meshing algorithm, the simulated river sedimentation effect data is converted into discrete triangular meshes, with each triangular mesh representing a sedimentary sequence unit. This triangulation process helps accurately describe the spatial distribution and relative positions of different sedimentary layers, providing an accurate terrain model foundation for subsequent structured meshing. Structured meshing is performed on the simulated river sedimentation effect data based on the triangulated river sediment sequence data. Using finite element analysis or numerical simulation software, the triangular mesh is further divided into a structured mesh. Structured meshing helps simplify numerical simulation calculations and data processing, improving simulation accuracy and efficiency. Through meshing, the sedimentation simulation data is converted into a regular grid structure consisting of nodes and cells, facilitating subsequent numerical continuous flux calculations and sedimentation cumulative increment analysis. Numerical continuous flux calculations of sedimentation are performed on the river sedimentation grid data using the finite volume method. Using finite volume numerical simulation techniques, the mass conservation equations and momentum conservation equations are solved for each node in the structured mesh. Numerical calculations yield the continuous flux distribution of sediment in the river, i.e., the mass flow rate of sediment passing through each cell boundary per unit time. These numerical continuous flux data reflect the distribution and transport of sediment in the river and provide input data for subsequent progressive cumulative increment calculations. Progressive cumulative increment calculations are performed based on the numerical continuous flux data of sedimentation. The calculated numerical continuous flux data are then used to perform a time-step accumulation calculation. Numerical integration or accumulation algorithms are used to calculate the cumulative increment of river sedimentation, i.e., the amount of sediment accumulated within each time step. These data provide key information for river morphological changes and health assessments, helping to understand river sedimentation processes and their impacts on river ecosystems.

[0135] Preferably, step S3 includes the following steps:

[0136] Step S31: Calculating theoretical runoff volume based on the hydrological and water resource data of the target river to obtain theoretical runoff volume data of the target river;

[0137] Step S32: calculating the runoff deviation degree of the target river theoretical runoff data according to the river physical morphology health index to obtain river runoff deviation degree data;

[0138] Step S33: calculating the cross-sectional flow fluctuation degree based on the river runoff deviation degree data to obtain cross-sectional flow fluctuation degree data;

[0139] Step S34: performing flow-sedimentation rate fluctuation correlation analysis on the river sediment accumulation increment data according to the cross-section flow fluctuation degree data to obtain flow-sedimentation rate fluctuation correlation data;

[0140] Step S35: performing spatial heterogeneous regression analysis on the flow-sedimentation rate fluctuation correlation data to obtain flow-sedimentation rate spatial heterogeneous regression data.

[0141] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0142] Step S31: Calculating theoretical runoff volume based on the hydrological and water resource data of the target river to obtain theoretical runoff volume data of the target river;

[0143] In this embodiment of the present invention, theoretical runoff is calculated using hydrological and water resource data for a target river. First, precipitation data and hydrological measurement information, such as precipitation, evaporation, and seepage, are collected for the target river basin. Hydrological models, such as the hydrological balance model or the runoff per unit area calculation method, are used to process and analyze precipitation inputs over different time periods. Through calculation and simulation, theoretical runoff data is derived—that is, the amount of runoff that would naturally occur in the river basin without human interference. This data serves as the basis for subsequent health index calculations, reflecting the fundamental state of the river's natural hydrological processes.

[0144] Step S32: calculating the runoff deviation degree of the target river theoretical runoff data according to the river physical morphology health index to obtain river runoff deviation degree data;

[0145] In this embodiment of the present invention, the runoff deviation of the target river's theoretical runoff data is calculated based on the river's physical health index. Using the calculated theoretical runoff data, combined with a pre-defined health index threshold and assessment method, the degree of deviation between the actual runoff and the theoretical value is analyzed. This involves statistical analysis or calculation of a deviation index to quantify the degree of variation and deviation in the runoff data. This step allows the assessment of the river's hydrological stability and changing trends, providing data support for subsequent calculations of flow fluctuations.

[0146] Step S33: calculating the cross-sectional flow fluctuation degree based on the river runoff deviation degree data to obtain cross-sectional flow fluctuation degree data;

[0147] In this embodiment of the present invention, cross-sectional flow fluctuations are calculated using river runoff deviation data. Based on this runoff deviation data, runoff fluctuations at different cross-sectional locations are analyzed. Time series analysis or frequency distribution methods are used to calculate the amplitude and frequency of cross-sectional flow fluctuations over different time periods. These calculations can assess water volume variations in different river regions, identify any periodic or seasonal fluctuations, and provide a data foundation for subsequent analysis of the correlation between flow and sedimentation rate fluctuations.

[0148] Step S34: performing flow-sedimentation rate fluctuation correlation analysis on the river sediment accumulation increment data according to the cross-section flow fluctuation degree data to obtain flow-sedimentation rate fluctuation correlation data;

[0149] In this embodiment of the present invention, flow-sedimentation rate fluctuation correlation analysis is performed on river sediment accumulation data based on cross-sectional flow fluctuation data. The calculated cross-sectional flow fluctuation data is used to analyze the impact of flow fluctuations on sediment accumulation. Statistical correlation analysis or mathematical modeling are used to assess sedimentation rate changes under different flow fluctuation conditions. This step aims to reveal the correlation between river flow fluctuations and sedimentation processes, providing quantitative analytical support for understanding river health.

[0150] Step S35: performing spatial heterogeneous regression analysis on the flow-sedimentation rate fluctuation correlation data to obtain flow-sedimentation rate spatial heterogeneous regression data.

[0151] In this embodiment of the present invention, spatially heterogeneous regression analysis is performed on flow-sedimentation fluctuation correlation data. Using spatial statistical methods or regression models, the spatially heterogeneous relationship between flow fluctuations and sedimentation rates across different river sections is analyzed. Incorporating Geographic Information System (GIS) technology, the acquired data is subjected to spatial analysis and image processing to reveal the spatial distribution and variation of river hydrological and sedimentation characteristics. This step provides a deeper understanding of the complexity and dynamics of river systems, providing a scientific basis and spatial information support for the development of river health early warning models.

[0152] Preferably, step S34 includes the following steps:

[0153] Step S341: performing time series segmentation on the cross-sectional flow fluctuation degree data to obtain cross-sectional flow time series segmentation data;

[0154] Step S342: performing cumulative incremental nonlinear analysis on the river sediment cumulative incremental data to obtain cumulative incremental nonlinear data;

[0155] Step S343: performing nonlinear incremental variance calculation on the river sediment cumulative incremental data according to the cumulative incremental nonlinear data to obtain sediment cumulative nonlinear incremental variance data;

[0156] Step S344: performing multivariate statistical analysis on the sediment accumulation nonlinear incremental variance data based on the cross-sectional flow time series segmented data to obtain flow segmentation-sediment accumulation multivariate analysis data;

[0157] Step S345: performing flow-deposition rate fluctuation correlation analysis based on the flow segmentation-deposition accumulation multivariate analysis data to obtain flow-deposition rate fluctuation correlation data.

[0158] In an embodiment of the present invention, the cross-sectional flow fluctuation degree data is segmented in time series to obtain cross-sectional flow time series segmented data. First, a data set within a continuous time period is extracted from the measured or simulated cross-sectional flow data. A time series analysis method, such as window sliding or segmented analysis, is used to segment the long-term cross-sectional flow data into shorter time periods. Each time series segment contains cross-sectional flow data within a specific time range for subsequent nonlinear analysis and statistical processing. A cumulative incremental nonlinear analysis is performed on the river sediment cumulative incremental data to obtain cumulative incremental nonlinear data. Nonlinear dynamics or complex system theory is used to perform nonlinear analysis on the calculated sediment cumulative incremental data. Methods such as the Hurst exponent and the Lyapunov exponent are used to evaluate the nonlinear characteristics and long-term correlation in the sediment incremental data. This step helps to identify potential nonlinear behavior in the river sedimentation process and provides theoretical support for subsequent incremental variance calculations. Nonlinear incremental variance calculations are performed on the river sediment cumulative incremental data based on the cumulative incremental nonlinear data to obtain sediment cumulative nonlinear incremental variance data. Based on the analyzed nonlinear characteristics, an appropriate mathematical algorithm or model is used to calculate the nonlinear incremental variance in the sediment cumulative incremental data. This involves statistical processing and mathematical derivation of time series to quantify the variability and uncertainty in river sedimentation. Sediment accumulation nonlinear incremental variance data provide a deeper understanding of nonlinear fluctuations in the sedimentation process, laying the foundation for flow-sedimentation rate correlation analysis. Multivariate statistical analysis of sediment accumulation nonlinear incremental variance data based on segmented flow time series data is performed to generate segmented flow-sedimentation accumulation multivariate analysis data. Combining segmented flow time series data with nonlinear incremental variance data, multivariate statistical methods such as principal component analysis or correlation analysis are used to explore the complex impact of flow variation on sedimentation. This step helps reveal the diversity and interactions of sedimentation processes under different flow conditions, providing a comprehensive data perspective for further analysis of flow-sedimentation rate fluctuation correlations. Flow-sedimentation rate fluctuation correlation analysis is performed based on segmented flow-sedimentation accumulation multivariate analysis data to generate flow-sedimentation rate fluctuation correlation data. Combining the obtained multivariate analysis data, correlation or regression analysis is used to explore the trends and correlations in sedimentation rates under different flow conditions. This step quantifies the extent to which flow variation affects sedimentation rate fluctuations, providing a scientific basis and data support for the development of river health assessment and early warning models.

[0159] Preferably, step S35 includes the following steps:

[0160] Step S351: performing spatial heterogeneity analysis on the flow-sedimentation rate fluctuation correlation data to obtain flow-sedimentation rate fluctuation spatial heterogeneity data;

[0161] Step S352: constructing an adjacency matrix between different spatial structure points of the flow-deposition rate fluctuation correlation data according to the flow-deposition rate fluctuation spatial heterogeneous data to obtain a flow-deposition rate spatial heterogeneous matrix;

[0162] Step S353: Calculate the spatial autocorrelation coefficient between different spatial structure points of the flow-sedimentation rate spatial heterogeneous matrix to obtain the spatial autocorrelation coefficient;

[0163] Step S354: performing a multivariate spatial heterogeneous regression analysis on the flow-sedimentation rate spatial heterogeneity matrix according to the spatial autocorrelation coefficient to obtain flow-sedimentation rate spatial heterogeneous regression data.

[0164] In an embodiment of the present invention, spatial heterogeneity analysis is performed on flow-sedimentation rate fluctuation correlation data to obtain flow-sedimentation rate fluctuation spatial heterogeneity data. First, a spatial data set of flow and sedimentation rate fluctuation correlation is extracted from the previous multivariate analysis data. Spatial statistical analysis methods, such as geographically weighted regression or kriging interpolation, are used to analyze the spatial distribution characteristics of fluctuation correlation between different locations. By calculating the spatial heterogeneity index, the spatial distribution unevenness of fluctuation correlation in the river system is evaluated, and the geographical characteristics and changing trends of fluctuation correlation in different regions are revealed. Based on the flow-sedimentation rate fluctuation spatial heterogeneity data, an adjacency matrix between different spatial structure points of the flow-sedimentation rate fluctuation correlation data is constructed to obtain a flow-sedimentation rate spatial heterogeneity matrix. Using the data obtained from the spatial heterogeneity analysis, an adjacency matrix between different structure points in the river system is constructed. The adjacency matrix reflects the spatial relationship and connection strength between each point, as well as their interaction in the fluctuation correlation. This step uses spatial statistical tools such as the spatial data analysis package in ArcGIS or R to convert the spatial heterogeneity data into a structured adjacency matrix, providing a data basis for subsequent spatial autocorrelation analysis. The spatial autocorrelation coefficients were calculated between points with different spatial structures in the spatially heterogeneous matrix of flow-sedimentation rates to obtain the spatial autocorrelation coefficients. Based on the constructed spatially heterogeneous matrix, spatial autocorrelation statistical indices such as Moran's I or Geary's C were used to calculate the spatial correlation of fluctuation associations between points with different structures. The spatial autocorrelation coefficients assess the degree of spatial correlation of fluctuation associations between different points, revealing the spatial distribution patterns and clustering of fluctuation associations within river systems. This analysis helps understand the spatial structural characteristics and regional differences of fluctuation associations. Based on the spatial autocorrelation coefficients, a multivariate spatial heterogeneous regression analysis was performed on the spatially heterogeneous matrix of flow-sedimentation rates to obtain flow-sedimentation spatial heterogeneity regression data. Based on the calculated spatial autocorrelation coefficients, multivariate spatial regression models, such as spatial lag models or spatial error models, were applied to explore the complex spatial relationships and influencing factors of fluctuation association data. This analysis can quantify the spatial heterogeneity of fluctuation associations between different locations, identify the spatial factors influencing fluctuation associations, and further improve the spatial predictive capabilities of river health assessment and early warning models.

[0165] Preferably, step S4 includes the following steps:

[0166] Step S41: performing organic matter content identification on the target river water quality status data to obtain the target river organic matter content data;

[0167] Step S42: estimating the spatial decomposition efficiency of the target river organic matter content data based on the flow-sedimentation rate spatial heterogeneity regression data to obtain organic matter spatial decomposition efficiency data;

[0168] Step S43: performing decomposition effect compensation on the organic matter spatial decomposition efficiency data according to the river physical morphology health index to obtain organic matter spatial decomposition efficiency compensation data;

[0169] Step S44: Calculating the benthic diatom index of the target river biological status data to obtain the benthic diatom index of the target river;

[0170] Step S45: calculating the pollution sensitivity index of the biological condition data of the target river according to the benthic diatom index of the target river to obtain pollution sensitivity index data;

[0171] Step S46: Calculate the pollution diffusion degree of the pollution sensitivity index data based on the river physical morphology health index and the flow-sedimentation rate spatial heterogeneity regression data to obtain pollution diffusion degree data.

[0172] In one embodiment of the present invention, organic matter content is identified in target river water quality data to obtain target river organic matter content data. First, water quality monitoring data for the target river is obtained from monitoring sites or remote sensing data. This data includes concentration information for various organic compounds. Using chemical analysis methods, such as high-performance liquid chromatography (HPLC) or gas chromatography-mass spectrometry (GC-MS), the water samples are analyzed to identify and measure the content of the target organic compounds. This process provides organic matter content data for each monitoring point, providing basic data support for subsequent spatial decomposition efficiency estimation. Spatial decomposition efficiency is estimated for the target river organic matter content data based on spatially heterogeneous flow-sedimentation rate regression data to obtain spatial decomposition efficiency data. Combined with the results of the previous spatially heterogeneous regression analysis, a geographic information system (GIS) or spatial statistical model is used to assess the decomposition rate and spatial distribution characteristics of organic matter in different regions of the target river. This process utilizes spatial analysis libraries in statistical software, such as R or Python, to calculate organic matter decomposition efficiency at different locations, revealing the spatial distribution patterns and trends of organic matter within the river system. Compensate the spatial decomposition efficiency data for decomposition effects based on the river's physical health index to obtain compensated spatial decomposition efficiency data. Adjust and correct the spatial decomposition efficiency data based on the previously calculated river's physical health index. This step compensates the decomposition efficiency data by establishing a correlation model between physical health and organic matter decomposition efficiency, using regression analysis or other mathematical modeling methods to account for the impact of the river's physical structure on water quality. A benthic diatom index is calculated based on the biological status data of the target river to obtain the target river's benthic diatom index. Benthic samples, specifically diatom communities, are collected and analyzed from the target river. Microscopic observation and classification statistics are used to calculate benthic diatom species abundance and diversity indices, such as the Shannon-Wiener index or the Pielou evenness index. These indices reflect the structure and health of the benthic diatom community in the river ecosystem and provide the biological basis for the subsequent calculation of the pollution sensitivity index. The pollution sensitivity index is calculated based on the target river's benthic diatom index based on the biological status data of the target river to obtain the pollution sensitivity index data. The Pollution Sensitivity Index (PSI) is calculated by combining the diatom index with other benthic monitoring data using biological indicator evaluation methods such as the IBMWP (Benthos Invertebrate Bioassessment Method) or other standardized biological indicator systems. This process reflects the responsiveness of river benthic organisms to water quality changes, providing a comprehensive biological indicator for river health assessment. The pollution diffusion degree is calculated based on the river physical health index and spatially heterogeneous flow-sedimentation rate regression data, resulting in the pollution diffusion degree data. The PHI and spatially heterogeneous regression results are combined to assess the spread and diffusion of pollutants in the river.Mathematical models or statistical analysis methods, such as spatial interpolation or environmental system dynamics models, are used to quantitatively analyze the diffusion paths and impact areas of pollutants at different temporal and spatial scales. This process provides a scientific basis and early warning capabilities for tracing river pollution sources and environmental management.

[0173] Preferably, step S46 includes the following steps:

[0174] Step S461: performing pollution diffusion simulation on the pollution sensitivity index data according to the river physical morphology health index and the flow-sedimentation rate spatial heterogeneity regression data to obtain pollution diffusion simulation data;

[0175] Step S462: performing diffusion distribution azimuth analysis on the pollution diffusion simulation data to obtain diffusion distribution azimuth data;

[0176] Step S463: performing pollution diffusion directionality analysis on the pollution diffusion simulation data according to the diffusion distribution azimuth data to obtain pollution diffusion directionality data;

[0177] Step S464: performing pollution accumulation effect analysis on the pollution diffusion simulation data according to the pollution diffusion directionality data to obtain pollution accumulation effect data;

[0178] Step S465: Calculate the pollution diffusion degree based on the pollution accumulation effect data to obtain pollution diffusion degree data.

[0179] In this embodiment of the present invention, pollution diffusion simulations are conducted based on river physical health indices and spatially heterogeneous flow-sedimentation rate regression data to assess the spread and distribution of pollutants within a river. First, mathematical models (such as finite element models or numerical simulations based on the Navier-Stokes equations) are used to simulate river flow dynamics under different conditions. Combined with flow and sedimentation rate data, the diffusion rates and paths of pollutants within the water column are calculated. Based on fluid dynamics principles and flow field analysis, these simulation data are used to predict the distribution of pollutants at different temporal and spatial scales, providing a quantitative basis for subsequent environmental impact assessments. Diffusion distribution azimuth analysis is performed on the simulated pollution diffusion data to identify the primary diffusion directions and regions of pollutants. Spatial analysis and visualization of the simulated pollutant concentration distribution data is performed using a geographic information system (GIS) or similar tool. This process involves using spatial statistical analysis methods, such as kernel density estimation or directional variation analysis, to identify dominant pollutant diffusion directions and high-concentration areas, providing a basis for further directional analysis. Directional analysis of the pollution diffusion simulation data is performed based on the diffusion distribution azimuth data to determine the directionality of pollutant diffusion. Based on the diffusion distribution azimuth data obtained in the previous analysis, statistical methods or spatial analysis tools are used to quantify the diffusion trends and directional characteristics of pollutants within different regions. This step, through angular distribution and vector analysis, reveals the dominant propagation direction and impact range of pollutants within the river system, providing directional guidance for environmental monitoring and response measures. Based on the pollution diffusion directional data, a pollution accumulation effect analysis is conducted on the pollution diffusion simulation data to assess the accumulation effect of pollutants within the river system. Combined with the directional data, mathematical modeling or statistical analysis methods are used to calculate the accumulation and impact of pollutants within specific river regions. This analysis considers the flow and deposition characteristics of pollutants in the water flow, providing a quantitative basis for identifying and assessing the impact range and cumulative effect of pollution sources. Pollution diffusion degree data is calculated based on the pollution accumulation effect data to obtain pollution diffusion degree data. Based on the previous simulation and analysis results, the diffusion degree of pollutants within the river is calculated by comprehensively considering the diffusion rate, directionality, and accumulation effect of pollutants. This process utilizes mathematical models and data processing tools, such as relevant simulation libraries and statistical functions in MATLAB or Python, to quantify the spatial and temporal spread and impact of pollutants, providing comprehensive environmental warnings and management recommendations for river health assessments.

[0180] Preferably, step S5 includes the following steps:

[0181] Step S51: Based on the deep Q-network algorithm, multi-factor synergistic impact learning is performed on the river physical morphology health index, flow-sedimentation rate spatial heterogeneous regression data, and pollution diffusion degree data to obtain multi-factor synergistic impact data of river status;

[0182] Step S52: constructing a river health early warning model based on the multi-factor collaborative impact data of river status to obtain a river health multi-factor collaborative model;

[0183] Step S53: Perform river health status assessment based on the river health multi-factor collaborative model to obtain river health status assessment data.

[0184] In an embodiment of the present invention, the multi-factor synergistic impact learning of river physical health index, spatially heterogeneous regression data of flow-sedimentation rate, and pollution diffusion degree data, using a deep Q-network algorithm, is specifically implemented as follows: First, river physical morphology data, flow-sedimentation rate spatial data, and pollution diffusion data are collected to construct corresponding datasets. Then, the deep Q-network algorithm, a method that combines deep learning and reinforcement learning, is used to process and learn from these data. The algorithm first preprocesses the data to ensure accuracy and consistency. Then, it uses its built-in neural network structure to analyze and extract the complex relationships between various factors. During training, the algorithm adjusts the network weights and parameters based on preset learning objectives, such as maximizing prediction accuracy or minimizing error rate, to optimize model performance. Ultimately, the algorithm outputs multi-factor synergistic impact data on river health, which comprehensively reflects the combined impact of physical morphology, flow-sedimentation rate, and pollution diffusion on river health. The specific implementation of constructing a river health early warning model based on this multi-factor synergistic impact data on river health is as follows: Using the acquired multi-factor synergistic impact data, the model is constructed using data mining and machine learning techniques. First, an appropriate machine learning algorithm, such as a support vector machine (SVM) or random forest, is selected based on the data characteristics and requirements. The dataset is then divided into a training set and a test set. The model is trained and optimized using the training set, and prediction accuracy is improved by adjusting the model's parameters and hyperparameters. After model training is complete, the test set is used for validation and evaluation to ensure the model's generalization and predictive accuracy. Ultimately, a multi-factor collaborative model capable of providing early warning of river health is constructed. This model can predict and assess river health based on different input conditions, providing a scientific basis for subsequent decision-making. Finally, in step S53, river health assessment is performed based on the constructed multi-factor collaborative model as follows: Using the early warning model established in step S52, newly collected river data is evaluated and analyzed in real time. First, real-time river data, including key data such as physical morphology, flow-sedimentation rate, and pollution dispersion, is input into the early warning model. Based on this data, the model applies the previously learned multi-factor collaborative influence relationships to calculate the current river health assessment data. The assessment results can be used to determine the river's health status, such as good, fair, or poor, based on pre-defined criteria and thresholds. Finally, the results are output as detailed data reports or graphical displays, allowing decision-makers to promptly understand changes in river health and take necessary management and protection measures.

[0185] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0186] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A river health assessment and health warning method, characterized in that: The following steps are involved: Step S1: Acquire the physical morphology data of the target river, the hydrological and water resource data of the target river, the water quality status data of the target river, and the biological status data of the target river; Step S2: Analyze the riverbank scour effect along the target river physical morphology data according to the target river hydrological and water resources data to obtain the riverbank scour effect data along the target river; perform progressive cumulative increment calculation according to the riverbank scour effect data along the target river to obtain the river sediment cumulative increment data; calculate the river physical morphology health index according to the river sediment cumulative increment data to obtain the river physical morphology health index; Step S3: Calculate the theoretical runoff of the target river hydrological and water resource data to obtain the theoretical runoff data of the target river; The cross-sectional flow fluctuation degree is calculated according to the river physical morphology health index to obtain the cross-sectional flow fluctuation degree data; According to the flow fluctuation degree data of the cross section, the flow-sedimentation rate fluctuation correlation analysis was carried out on the river sediment accumulation increment data to obtain the flow-sedimentation rate spatial heterogeneous regression data; Step S4: identifying the organic matter content of the target river water quality status data to obtain the target river organic matter content data; performing decomposition effect compensation on the target river organic matter content data to obtain organic matter spatial decomposition efficiency compensation data; calculating the pollution sensitivity index of the target river biological status data to obtain pollution sensitivity index data; The pollution diffusion degree data were calculated based on the river physical morphology health index and the spatial heterogeneous regression data of flow-sedimentation rate to obtain the pollution diffusion degree data; Step S5: Based on the deep Q network algorithm, a river health early warning model is constructed for the river physical morphology health index, flow-sedimentation rate spatial heterogeneous regression data, and pollution diffusion degree data to obtain a river health multi-factor collaborative model; the river health status is evaluated according to the river health multi-factor collaborative model to obtain river health status evaluation data.

2. The river health assessment and health warning method according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: analyzing the scouring effect of the riverbank along the target river based on the target river hydrological and water resource data to obtain the scouring effect data of the riverbank along the target river; Step S22: Calculating the river curvature trend of the target river physical morphology data to obtain river curvature trend data; Step S23: simulating the river sedimentation effect according to the river bank scouring effect data and the river curvature trend data along the route, and obtaining the river sedimentation effect simulation data; Step S24: performing progressive cumulative increment calculation on the river sedimentation effect simulation data to obtain river sedimentation cumulative increment data; Step S25: evaluating the connectivity and barrier conditions of the river based on the river sediment accumulation increment data and the river curvature trend data to obtain the connectivity and barrier conditions data of the river; Step S26: Calculate the river physical morphology health index based on the river sedimentation cumulative increment data and the river connectivity and barrier status data to obtain the river physical morphology health index.

3. The river health assessment and health warning method according to claim 2 is characterized in that: Step S21 includes the following steps: Step S211: extracting river hydrological flow velocity from target river hydrological and water resource data to obtain river hydrological flow velocity data; Step S212: Calculate the scouring flow velocity along the riverbank based on the physical morphology data of the target river according to the river hydrological flow velocity data, and obtain the scouring flow velocity data along the riverbank; Step S213: analyzing the loose characteristics of the matrix along the river bank based on the scouring velocity data along the river bank to obtain the loose characteristics data of the matrix along the river bank; Step S214: evaluating the slope foot scour intensity of the target river physical morphology data according to the loose characteristic data of the river bank matrix and the scour velocity data of the river bank, and obtaining the slope foot scour intensity data of the target river; Step S215: Analyze the scour effect of the river bank along the line according to the scour intensity data of the target river slope foot and the loose characteristic data of the river bank matrix along the line to obtain the scour effect data of the river bank along the line.

4. The river health assessment and health warning method according to claim 3 is characterized in that: Step S24 includes the following steps: Step S241: performing sediment sequence characteristic analysis on the river sedimentation effect simulation data to obtain sediment sequence characteristic data; Step S242: performing sequence triangulation on the river sedimentation effect simulation data according to the sediment sequence characteristic data to obtain river sediment sequence triangulation data; Step S243: performing structured grid division on the river sedimentation effect simulation data according to the river sedimentation sequence triangulation data to obtain river sedimentation effect grid data; Step S244: performing numerical continuous flux calculation of the sedimentation effect on the river sedimentation effect grid data based on the finite volume method to obtain numerical continuous flux data of the sedimentation effect; Step S245: Perform progressive cumulative increment calculation based on the numerical continuous flux data of the sedimentation effect to obtain the river sedimentation cumulative increment data.

5. The river health assessment and health warning method according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Calculate theoretical runoff volume of the target river hydrological and water resource data to obtain theoretical runoff volume data of the target river; Step S32: calculating the runoff deviation degree of the target river theoretical runoff data according to the river physical morphology health index to obtain the river runoff deviation degree data; Step S33: Calculating the cross-sectional flow fluctuation degree of the river runoff deviation degree data to obtain cross-sectional flow fluctuation degree data; Step S34: performing flow-sedimentation rate fluctuation correlation analysis on the river sedimentation cumulative increment data according to the cross-section flow fluctuation degree data to obtain flow-sedimentation rate fluctuation correlation data; Step S35: Perform spatial heterogeneous regression analysis on the flow-sedimentation rate fluctuation correlation data to obtain flow-sedimentation rate spatial heterogeneous regression data.

6. The river health assessment and health warning method according to claim 5 is characterized in that: Step S34 includes the following steps: Step S341: performing time series segmentation on the cross-sectional flow fluctuation degree data to obtain cross-sectional flow time series segmentation data; Step S342: performing cumulative incremental nonlinear analysis on the river sediment cumulative incremental data to obtain cumulative incremental nonlinear data; Step S343: performing nonlinear incremental variance calculation on the river sediment cumulative incremental data according to the cumulative incremental nonlinear data to obtain sediment cumulative nonlinear incremental variance data; Step S344: performing multivariate statistical analysis on the sediment accumulation nonlinear incremental variance data according to the cross-sectional flow time series segmented data to obtain flow segmentation-sediment accumulation multivariate analysis data; Step S345: performing flow-deposition rate fluctuation correlation analysis based on the flow segmentation-deposition accumulation multivariate analysis data to obtain flow-deposition rate fluctuation correlation data.

7. The river health assessment and health warning method according to claim 5 is characterized in that: Step S35 includes the following steps: Step S351: performing spatial heterogeneity analysis on the flow-sedimentation rate fluctuation correlation data to obtain flow-sedimentation rate fluctuation spatial heterogeneity data; Step S352: constructing an adjacency matrix between different spatial structure points of the flow-deposition rate fluctuation correlation data according to the flow-deposition rate fluctuation spatial heterogeneous data, and obtaining a flow-deposition rate spatial heterogeneous matrix; Step S353: Calculate the spatial autocorrelation coefficients between different spatial structure points of the flow-sedimentation rate spatial heterogeneous matrix to obtain the spatial autocorrelation coefficients; Step S354: Perform multivariate spatial heterogeneous regression analysis on the flow-sedimentation rate spatial heterogeneity matrix according to the spatial autocorrelation coefficient to obtain flow-sedimentation rate spatial heterogeneous regression data.

8. The river health assessment and health warning method according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: identifying the organic matter content of the target river water quality status data to obtain the target river organic matter content data; Step S42: Estimate the spatial decomposition efficiency of the organic matter content data of the target river according to the spatial heterogeneous regression data of flow-sedimentation rate to obtain the spatial decomposition efficiency data of organic matter; Step S43: performing decomposition effect compensation on the organic matter spatial decomposition efficiency data according to the river physical morphology health index to obtain organic matter spatial decomposition efficiency compensation data; Step S44: Calculating the benthic diatom index of the target river biological status data to obtain the benthic diatom index of the target river; Step S45: calculating the pollution sensitivity index of the biological condition data of the target river according to the benthic diatom index of the target river to obtain pollution sensitivity index data; Step S46: Calculate the pollution diffusion degree of the pollution sensitivity index data according to the river physical morphology health index and the flow-sedimentation rate spatial heterogeneous regression data to obtain the pollution diffusion degree data.

9. The river health assessment and health warning method according to claim 8 is characterized in that: Step S46 includes the following steps: Step S461: performing pollution diffusion simulation on the pollution sensitivity index data according to the river physical morphology health index and the flow-sedimentation rate spatial heterogeneous regression data to obtain pollution diffusion simulation data; Step S462: performing diffusion distribution azimuth analysis on the pollution diffusion simulation data to obtain diffusion distribution azimuth data; Step S463: performing pollution diffusion directional analysis on the pollution diffusion simulation data according to the diffusion distribution azimuth data to obtain pollution diffusion directional data; Step S464: performing pollution accumulation effect analysis on the pollution diffusion simulation data according to the pollution diffusion directional data to obtain pollution accumulation effect data; Step S465: Calculate the pollution diffusion degree based on the pollution accumulation effect data to obtain pollution diffusion degree data.

10. The river health assessment and health warning method according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: Based on the deep Q network algorithm, multi-factor synergistic influence learning is performed on the river physical morphology health index, flow-sedimentation rate spatial heterogeneous regression data and pollution diffusion degree data to obtain multi-factor synergistic influence data of river status; Step S52: constructing a river health early warning model based on the multi-factor coordinated impact data of river status to obtain a river health multi-factor coordinated model; Step S53: Perform river health status assessment based on the river health multi-factor collaborative model to obtain river health status assessment data.

Images