A method and system for evaluating the effectiveness of river and lake construction

Abstract

This invention provides a method and system for evaluating the effectiveness of river and lake construction, relating to the field of computer application technology. The method includes: Step 1, acquiring monitoring data of rivers and lakes, including satellite remote sensing data, UAV monitoring data, video surveillance data, and social network data; Step 2, based on the spatial distribution characteristics of the monitoring data, selecting hydrological monitoring stations, automatic water quality monitoring stations, and fixed shoreline markers in the rivers and lakes to construct a spatial coverage area, spatially partitioning the coverage area, optimizing the spatial geometric reference benchmark of each partition by performing circular geometric fitting on key monitoring points within each partition, and generating a spatial correction factor based on the optimized spatial distribution characteristics of each partition. This invention achieves a comprehensive, accurate, and all-encompassing evaluation of the effectiveness of river and lake construction.

Description

Technical Field

[0001] This invention relates to the field of computer application technology, and in particular to a method and system for evaluating the effectiveness of river and lake construction. Background Technology

[0002] As river and lake construction moves towards refinement and comprehensiveness, there is an urgent need for an evaluation system that can take into account multiple dimensions such as ecological health, flood control safety, and management efficiency. Existing evaluation methods mostly rely on single data from fixed locations such as hydrological monitoring stations and automatic water quality monitoring stations, supplemented by periodic manual verification data to conduct assessments.

[0003] For example, in evaluating the effectiveness of river and lake construction in suburban lake clusters, some methods used water quality and hydrological data from fixed monitoring stations along the lakes, as well as records of semi-annual artificial shoreline ecological patrols. The evaluation results indicated that the water quality of the lake clusters had improved, shoreline protection had met standards, and the overall construction effectiveness was excellent. However, comparison with satellite remote sensing images revealed undetected early signs of cyanobacterial blooms in the shallow areas of the lake center. Furthermore, the spatial reference standards between fixed monitoring data and artificial patrol records were inconsistent, leading to deviations in the quantitative assessment of the ecological restoration effectiveness of some shorelines. This approach highlights the core defects of existing technologies: the inability to effectively integrate multi-source heterogeneous data such as satellite remote sensing, drones, and social networks; the lack of spatial partitioning optimization and geometric correction processing for monitoring data; the difficulty in achieving blind-spot-free monitoring of the entire river and lake area; and the absence of a linkage mechanism between health status assessment and risk warning. Consequently, the evaluation results lacked comprehensiveness and accuracy, failing to provide reliable technical support for precise policy implementation and closed-loop management of river and lake construction. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for evaluating the effectiveness of river and lake construction, so as to achieve a comprehensive, accurate and complete evaluation of the effectiveness of river and lake construction.

[0005] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0006] Firstly, a method for evaluating the effectiveness of river and lake construction, the method comprising:

[0007] Step 1: Obtain monitoring data for rivers and lakes. The monitoring data includes satellite remote sensing data, drone monitoring data, video surveillance data, and social network data.

[0008] Step 2: Based on the spatial distribution characteristics of the detection data, select hydrological monitoring stations, automatic water quality monitoring stations and shoreline fixed markers in rivers and lakes to construct a spatial coverage area. Perform spatial partitioning on the spatial coverage area, optimize the spatial geometric reference benchmark of the partition by performing circular geometric fitting on the key monitoring points in each partition, and generate a spatial correction factor based on the spatial distribution characteristics of each partition after optimization.

[0009] Step 3: Based on the detection data and the spatial correction factor, the detection data is fused, and the fused data is spatially corrected using the spatial correction factor to obtain an optimized dataset;

[0010] Step 4: Based on the optimized dataset, assess the health status of rivers and lakes using the river and lake health diagnostic index model to obtain the assessment results of river and lake health status.

[0011] Step 5: Based on the assessment results of river and lake health status, predict and analyze the health risks of rivers and lakes through a risk warning model to obtain river and lake health risk warning information;

[0012] Step 6: Based on the assessment results of river and lake health status and the early warning information of river and lake health risks, conduct a comprehensive evaluation of the effectiveness of river and lake construction and obtain a river and lake construction effectiveness evaluation report.

[0013] Further, step 2 includes:

[0014] Receive detection data and perform spatial coverage analysis based on the spatial distribution characteristics of the detection data to identify the density distribution characteristics of monitoring data and the distribution of spatial coverage blind spots within the river and lake area;

[0015] Based on the density distribution characteristics of monitoring data and the distribution of spatial coverage blind spots, hydrological monitoring stations, automatic water quality monitoring stations, and fixed shoreline markers were selected as key reference points in the river and lake area to construct an initial spatial coverage area to cover the spatial coverage blind spots.

[0016] Based on the initial spatial coverage area, combined with the geographical characteristics of rivers and lakes and monitoring needs, the initial spatial coverage area is spatially partitioned, dividing the river and lake area into multiple logical partitions with continuous spatial coverage characteristics.

[0017] Based on each logical partition, circular geometric fitting is performed on the key monitoring points distributed within each partition to calculate the final geometric center position and coverage radius parameters of each partition.

[0018] Based on the final geometric center location and coverage radius parameters of each partition, optimize the spatial geometric reference benchmark of each partition, and determine the precise spatial positioning parameters and spatial coverage of each partition;

[0019] Based on the precise spatial positioning parameters and spatial coverage of each zone, the spatial distribution characteristics of each zone after optimization are analyzed, including zone area parameters, shape coefficient parameters and monitoring point density parameters, and the corresponding spatial correction factors are obtained.

[0020] Furthermore, based on each logical partition, circular geometric fitting is performed on the key monitoring points distributed within each partition to calculate the final geometric center position and coverage radius parameters of each partition, including:

[0021] Based on the precise spatial coordinate data of the key monitoring points distributed within each logical partition, the set of spatial coordinates of the key monitoring points in each partition is obtained; based on the set of spatial coordinates of the key monitoring points, the spatial distance relationship matrix between all key monitoring points in each partition is calculated, and the spatial distribution density characteristics of each monitoring point are identified.

[0022] By using the spatial distance relationship matrix and spatial distribution density characteristics, initial circular geometry fitting is performed on the key monitoring points in each partition to determine the candidate positions of the initial geometric center of each partition; using the candidate positions of the initial geometric center, the radial distance from all key monitoring points in each partition to the initial geometric center is calculated, and the statistical distribution characteristics of the radial distance are analyzed.

[0023] Based on the statistical distribution characteristics of radial distance, the optimized geometric center position is obtained by iteratively correcting the initial candidate geometric center position. Based on the optimized geometric center position, the distance from each key monitoring point to the optimized geometric center is recalculated, and the maximum distance value is determined as the initial coverage radius parameter.

[0024] Based on the initial coverage radius parameter, the coverage integrity of the circular geometric fit for key monitoring points in each partition is evaluated. When the coverage integrity does not meet the preset threshold, the optimized geometric center position and coverage radius parameter are adjusted to obtain the final geometric center position and coverage radius parameter.

[0025] Furthermore, based on the detection data and the spatial correction factor, the detection data is fused, and the fused data is spatially corrected using the spatial correction factor to obtain an optimized dataset, including:

[0026] Based on the detection data and spatial correction factor, the detection data of each partition is spatially normalized to obtain the preliminary fused dataset of each partition; based on the preliminary fused dataset, combined with the partition area parameter, shape coefficient parameter and monitoring point density parameter in the spatial correction factor, the data of each partition is spatially weighted and fused to obtain an aligned dataset with a unified spatial benchmark.

[0027] By combining the aligned dataset with the precise spatial positioning parameters and coverage of each partition, spatial interpolation and smoothing are performed to obtain a smooth dataset that eliminates the discontinuity of partition boundaries. By applying a spatial correction factor to the smooth dataset and performing spatial coordinate transformation and correction, sub-datasets of river and lake health monitoring for each partition with a consistent spatial reference system are obtained.

[0028] The sub-datasets of river and lake health monitoring in each region were integrated to form an optimized dataset.

[0029] Furthermore, based on the optimized dataset, the health status of rivers and lakes is assessed using a river and lake health diagnostic index model, yielding the following assessment results:

[0030] Based on the optimized dataset, multi-dimensional monitoring indicator data related to river and lake health diagnosis are extracted to form a health diagnosis input data set;

[0031] The health diagnosis input data set is input into the preset river and lake health diagnosis index model. According to the built-in index weight system and health level classification rules of the model, the indicators are standardized and mapped to health scores to generate preliminary health status scores for each zone.

[0032] Based on the preliminary health status score, and combined with the spatial attributes of each zone and the completeness of the monitoring data, the score is corrected for spatial consistency and weighted for reliability to obtain the corrected health status score for each zone.

[0033] Based on the corrected health status score, and following an evaluation strategy that combines overall and regional assessments of rivers and lakes, the health status level is determined and the spatial distribution characteristics are analyzed to obtain structured river and lake health status assessment results, including overall health level, regional health level distribution, and identification information of major health problems.

[0034] Furthermore, based on the assessment results of river and lake health status, a risk warning model is used to predict and analyze river and lake health risks, resulting in river and lake health risk warning information, including:

[0035] By extracting health status indicators, historical trends and spatial distribution anomalies related to risk warning from the structured river and lake health status assessment results, the initial input data for risk warning is obtained.

[0036] The initial input data for risk warning is input into the preset river and lake health risk warning model. Based on the risk evolution law and multi-threshold judgment rules embedded in the model, the risk probability of each zone is calculated and the risk level is initially determined.

[0037] Based on risk probability and preliminary risk level, combined with external environmental forecast information and human activity impact data, risk spatiotemporal evolution simulation and multi-scenario prediction analysis are carried out to obtain dynamic risk evolution maps of each region in the future.

[0038] Based on the dynamic risk evolution map, high-risk areas, risk diffusion paths and key risk triggering factors are identified, and river and lake health risk warning information is generated according to the preset warning level standards.

[0039] Furthermore, based on the assessment results of river and lake health status and the early warning information on river and lake health risks, a comprehensive evaluation of the effectiveness of river and lake construction is conducted, resulting in a river and lake construction effectiveness evaluation report, including:

[0040] Based on the results of the river and lake health status assessment and the river and lake health risk early warning information, a comprehensive analysis dataset is constructed by spatiotemporal alignment and information fusion.

[0041] Based on the comprehensive analysis dataset, from four dimensions—health level, risk status, construction progress, and sustainability—pre-set evaluation indicators and weights are selected to calculate the multi-dimensional effectiveness scores of the river and lake as a whole and its various sub-districts, resulting in multi-dimensional effectiveness scores.

[0042] Based on multi-dimensional performance scoring, combined with management objectives and historical performance comparison, and weighted integration and rating determination, the overall construction performance rating and comprehensive score of the river and lake as a whole and each zone are formed.

[0043] Based on the construction effectiveness level and comprehensive score, areas with outstanding achievements, weak links and directions for improvement are identified, and key evaluation findings, major risk warnings and targeted suggestions are integrated to obtain a river and lake construction effectiveness evaluation report.

[0044] Secondly, a river and lake construction effectiveness evaluation system includes:

[0045] The acquisition module is used to acquire monitoring data of rivers and lakes, including satellite remote sensing data, drone monitoring data, video surveillance data, and social network data.

[0046] The fitting module is used to construct a spatial coverage area in rivers and lakes by selecting hydrological monitoring stations, automatic water quality monitoring stations and shoreline fixed markers based on the spatial distribution characteristics of the detection data. The spatial coverage area is then spatially partitioned. By performing circular geometric fitting on key monitoring points in each partition, the spatial geometric reference benchmark of the partition is optimized. Based on the spatial distribution characteristics of each partition after optimization, a spatial correction factor is generated.

[0047] The correction module is used to fuse the detection data based on the detection data and the spatial correction factor, and to perform spatial correction on the fused data through the spatial correction factor to obtain an optimized dataset.

[0048] The assessment module is used to assess the health status of rivers and lakes based on the optimized dataset and the river and lake health diagnostic index model, and obtain the assessment results of the river and lake health status.

[0049] The early warning module is used to predict and analyze the health risks of rivers and lakes based on the assessment results of the health status of rivers and lakes, and obtain early warning information on the health risks of rivers and lakes.

[0050] The processing module is used to comprehensively evaluate the effectiveness of river and lake construction based on the assessment results of river and lake health status and the early warning information of river and lake health risks, and to obtain a river and lake construction effectiveness evaluation report.

[0051] Thirdly, a computing device, comprising:

[0052] One or more processors;

[0053] A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method.

[0054] Fourthly, a computer-readable storage medium storing a program that, when executed by a processor, implements the method.

[0055] The above-described solution of the present invention has at least the following beneficial effects:

[0056] By employing multi-source heterogeneous data acquisition technologies integrating satellite remote sensing, drone monitoring, video surveillance, and social networks, combined with spatial coverage analysis, logical partitioning, and spatial refinement processing technologies for generating spatial correction factors through circular geometric fitting of key monitoring points, and utilizing spatial correction technologies such as multi-source data normalization and weighted fusion, precise assessment technologies of river and lake health diagnostic indicator models, dynamic prediction technologies of risk warning models, and comprehensive evaluation technologies encompassing health levels, risk situations, construction progress, and sustainability, this approach effectively overcomes the technical problems of insufficient multi-source data integration, uneven spatial coverage, inconsistent data spatial references, and disconnect between health assessment and risk warning in existing evaluation methods. These problems result in insufficient comprehensiveness and accuracy of evaluation results and the inability to achieve full-area, blind-spot-free monitoring. Consequently, it achieves comprehensive and all-round perception of river and lake construction achievements, reliable data processing, accurate determination of health status, dynamic risk warning, and multi-dimensional scientific evaluation, forming a closed-loop system encompassing data acquisition, spatial optimization, health assessment, risk warning, and comprehensive evaluation. This provides efficient and reliable technical support for the implementation of the river and lake chief system, precise ecological restoration policies, and closed-loop supervision. Attached Figure Description

[0057] Figure 1 This is a flowchart illustrating a method for evaluating the effectiveness of river and lake construction, provided by an embodiment of the present invention.

[0058] Figure 2 This is a schematic diagram of a river and lake construction effectiveness evaluation system provided by an embodiment of the present invention. Detailed Implementation

[0059] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0060] like Figure 1 As shown in the figure, an embodiment of the present invention proposes a method for evaluating the effectiveness of river and lake construction, the method comprising the following steps:

[0061] Step 1: Obtain monitoring data for rivers and lakes. The monitoring data includes satellite remote sensing data, drone monitoring data, video surveillance data, and social network data.

[0062] Step 2: Based on the spatial distribution characteristics of the detection data, select hydrological monitoring stations, automatic water quality monitoring stations and shoreline fixed markers in rivers and lakes to construct a spatial coverage area. Perform spatial partitioning on the spatial coverage area, optimize the spatial geometric reference benchmark of the partition by performing circular geometric fitting on the key monitoring points in each partition, and generate a spatial correction factor based on the spatial distribution characteristics of each partition after optimization.

[0063] Step 3: Based on the detection data and the spatial correction factor, the detection data is fused, and the fused data is spatially corrected using the spatial correction factor to obtain an optimized dataset;

[0064] Step 4: Based on the optimized dataset, assess the health status of rivers and lakes using the river and lake health diagnostic index model to obtain the assessment results of river and lake health status.

[0065] Step 5: Based on the assessment results of river and lake health status, predict and analyze the health risks of rivers and lakes through a risk warning model to obtain river and lake health risk warning information;

[0066] Step 6: Based on the assessment results of river and lake health status and the early warning information of river and lake health risks, conduct a comprehensive evaluation of the effectiveness of river and lake construction and obtain a river and lake construction effectiveness evaluation report.

[0067] In this embodiment of the invention, by employing acquisition technologies for multi-source heterogeneous data from satellite remote sensing, UAV monitoring, video surveillance, and social networks, combined with spatial optimization techniques such as selecting key reference points based on the spatial distribution characteristics of multi-source data to construct spatial coverage areas, performing spatial partitioning and conducting circular geometric fitting of key monitoring points within the partitions to generate spatial correction factors, and a full-process technical approach including multi-source data fusion and spatial correction, river and lake health diagnostic indicator model evaluation, risk warning model prediction and analysis, and comprehensive evaluation combining both, the invention effectively overcomes the technical problems of insufficient comprehensiveness and low accuracy in existing river and lake construction effectiveness evaluations, such as single data sources, uneven spatial coverage, inconsistent data spatial benchmarks, and disconnect between health status assessment and risk warning. This achieves comprehensive integration and spatial optimization of river and lake health monitoring data, accurately obtains river and lake health status assessment results and dynamic risk warning information, and scientifically completes the comprehensive evaluation of river and lake construction effectiveness, providing reliable technical support for river and lake management decisions, ecological protection and restoration, and closed-loop supervision.

[0068] In a preferred embodiment of the present invention, step 1 above may include:

[0069] Step 1.1: Acquire satellite remote sensing image data of the river and lake area, and perform reception, preprocessing, and standardization. Based on the satellite remote sensing image data, identify the water body range, shoreline changes, and key monitoring areas of the river and lake, and trigger UAV monitoring tasks. According to the key monitoring areas, control the UAV to perform patrol monitoring, collect high-resolution images and near-ground water quality parameters, and simultaneously access video surveillance data deployed along the river and lake. Combine this with text and image information related to the river and lake environment extracted from social network platforms, and perform real-time acquisition and structured processing. Perform spatiotemporal alignment, format unification, and outlier cleaning on the satellite remote sensing data, UAV monitoring data, video surveillance data, and data extracted from social networks to form a unified spatiotemporal benchmark. The detection dataset includes: First, high-resolution satellite remote sensing image data covering the entire target river and lake area is continuously received through satellite remote sensing data receiving equipment. Preprocessing is carried out immediately after reception. Radiometric correction eliminates the influence of atmospheric scattering and sensor errors on the image data. Geometric correction corrects geometric distortions in the image to ensure spatial accuracy. Then, image cropping is performed to retain only the image portion containing the target river and lake area. Next, grayscale stretching and contrast enhancement techniques are used to optimize the visual effect of the image and improve detail recognition. Finally, the preprocessed satellite remote sensing image data is converted into a unified format according to the system's preset image data format standards to complete the standardization process.

[0070] Next, in-depth analysis was performed on the standardized satellite remote sensing image data. Based on the differences in spectral characteristics between water and non-water areas in the images, the boundaries of rivers and lakes were precisely delineated, and the specific distribution areas of the water bodies were clarified. At the same time, historical satellite remote sensing image data from the same period of the river and lake were retrieved, and the historical images were compared and analyzed pixel by pixel with the current images to track changes in the shoreline position and mark specific segments where the shoreline extended, receded, or changed its shape. Furthermore, the monitoring data density of each area in the image was calculated using computer algorithms. When the monitoring data density of a certain area was less than 50, that area was designated as a key monitoring area. The key monitoring area must fully cover the areas of shoreline change at the edge of the water body and areas with low data density to ensure that no monitoring is missed.

[0071] Once the key monitoring area is delineated, a monitoring task trigger command is automatically sent to the UAV dispatch center. The command details the spatial coordinates of the key monitoring area, the cruise route planning requirements, and the data acquisition parameter standards. After receiving the command, the UAV dispatch center quickly queries the available UAVs that are currently in standby mode and closest to the target river or lake, sends a task execution command to the UAV, and transmits relevant planning information. After receiving the command, the UAV starts its power system and autonomously flies to the key monitoring area according to the planned cruise route. After reaching the designated area, it starts its onboard high-resolution camera and continuously collects high-resolution images of the area at a frequency of once every 30 seconds. At the same time, it starts its onboard water quality sensor, inserts the sensor probe into the water to ensure full contact with the water, and collects near-surface water quality parameters such as dissolved oxygen content, pH, ammonia nitrogen concentration, total phosphorus concentration, and total nitrogen concentration in real time at a frequency of once every 10 seconds. During the collection process, the data is transmitted back in real time to ensure data synchronization.

[0072] While the drone is performing monitoring tasks, it establishes a stable connection with video surveillance equipment deployed along the river and lake through a dedicated network communication link. These video surveillance devices are distributed in key locations such as river and lake banks, dams, entrances and exits, and bridges. The drone continuously receives real-time video stream data captured by each video surveillance device in accordance with the real-time data transmission protocol. During the reception process, the integrity of each video stream data is verified to check whether the data is lost or damaged. The video surveillance data that passes the verification is directly stored in the database for temporary storage. At the same time, the installation location information of the monitoring device corresponding to each video data and the specific data collection timestamp are recorded in detail to ensure data traceability.

[0073] Meanwhile, by accessing mainstream social networking platforms in real time, including various social forums, blogs, and short video platforms, and with built-in keyword filtering rules, the crawler program comprehensively searches for text and image information containing relevant terms on various social networking platforms based on these keywords. After collection, the text information is segmented to remove meaningless stop words, extracting core semantic content related to the river and lake environment, and identifying whether the images contain relevant scenes of the target river or lake. Subsequently, according to information classification standards, the processed text and image information are categorized and organized to complete structured processing, while also recording the publication time, location, and account information of each piece of information.

[0074] Finally, comprehensive processing was carried out on satellite remote sensing data, UAV monitoring data, video surveillance data, and structured data extracted from social networks. In the spatiotemporal alignment stage, the acquisition timestamps of satellite remote sensing data were used as a unified benchmark to convert the acquisition times of UAV monitoring data, the shooting times of video surveillance data, and the posting times of social network information into the same time format, ensuring consistency in the time dimension. Simultaneously, using the nationally unified geodetic coordinate system as the spatial benchmark, the spatial location information corresponding to various types of data was uniformly converted into coordinate data under this coordinate system, achieving spatial dimension alignment. In the format unification stage, according to the preset unified data storage format, satellite remote sensing image data was converted into a standard raster format, high-resolution images acquired by UAVs were converted into the same image format, water quality parameters were converted into a standard numerical format, and video surveillance data was converted into a standard video format. In this process, text and image information from social networks are converted into standard text and image formats, respectively, to ensure uniformity in all data formats. For outlier cleaning, for numerical data such as dissolved oxygen content and pH, the average and standard deviation of each parameter are calculated. If a data value exceeds the range of the average plus or minus three times the standard deviation, it is considered an outlier and removed. For image and video data, a quality assessment algorithm is used to detect issues such as blurriness, occlusion, and excessive noise. Data with a quality assessment score below 80 is considered outlier and removed. For text and image information, false information or information unrelated to the target river or lake is screened out, and information that fails verification is removed. After the above spatiotemporal alignment, format unification, and outlier cleaning processes, all valid data are integrated and summarized to form a detection dataset under a unified spatiotemporal benchmark.

[0075] In this embodiment of the invention, by employing comprehensive technical means such as satellite remote sensing image data preprocessing and standardization, triggering precise drone patrol monitoring based on satellite remote sensing identification results, synchronously accessing video surveillance data and extracting social network-related information and performing structured processing, and carrying out spatiotemporal alignment, format unification, and outlier cleaning for four types of multi-source data, the technical problems of low data availability and inability to comprehensively and accurately reflect the actual state of rivers and lakes caused by the fragmented sources, inconsistent spatiotemporal benchmarks, chaotic formats, and abnormal interference of traditional river and lake monitoring data are effectively overcome. This results in a high-quality detection dataset under a unified spatiotemporal benchmark, achieving comprehensive coverage and accurate collection of information such as the water body range, shoreline changes, water quality parameters, and public feedback of rivers and lakes.

[0076] In a preferred embodiment of the present invention, step 2 above may include:

[0077] Step 2.1: Receive the detection data and perform spatial coverage analysis based on the spatial distribution characteristics of the detection data to identify the density distribution characteristics of monitoring data and the distribution of spatial coverage blind spots within the river and lake area. Specifically, this includes: First, receiving the detection dataset after spatiotemporal alignment, format unification, and outlier cleaning. This dataset contains satellite remote sensing data, UAV monitoring data, video surveillance data, and structured social network data. Then, based on the spatial distribution characteristics of the detection data, conduct spatial coverage analysis. First, divide the entire target river and lake area into several uniform spatial analysis units with a grid size of 100 meters × 100 meters, ensuring that the spatial extent of each unit is clear and non-overlapping. Next, count the number of valid monitoring data entries contained in each spatial analysis unit. Effective monitoring data must meet the requirements of data integrity, absence of outliers, and accurate spatial coordinate information. Based on statistical results, the density distribution characteristics of monitoring data are identified, and the number of monitoring data entries in each unit is divided into three levels: high-density areas with more than 50 data entries, medium-density areas with 20 to 49 data entries, and low-density areas with fewer than 20 data entries. At the same time, spatial analysis units with zero data entries are marked as spatial coverage blind spots. Geographic information visualization technology is used to present the distribution of high-density areas, medium-density areas, low-density areas, and spatial coverage blind spots in the form of layers, clearly identifying the spatial distribution pattern of monitoring data density in the river and lake area and the specific location, range, and shape of spatial coverage blind spots.

[0078] Step 2.2: Based on the density distribution characteristics of monitoring data and the distribution of spatial coverage blind spots, select hydrological monitoring stations, automatic water quality monitoring stations, and fixed shoreline markers as key reference points in the river and lake area to construct the initial spatial coverage area covering the spatial coverage blind spots. Specifically, this includes: selecting key reference points in the river and lake area based on the identified density distribution characteristics of monitoring data and the distribution of spatial coverage blind spots. Priority was given to selecting hydrological monitoring stations and automatic water quality monitoring stations located around spatial coverage blind spots, with stable data transmission and meeting monitoring accuracy standards, to ensure that the selected stations could effectively cover the surrounding blind spots. Simultaneously, fixed, easily identifiable, and spatially fixed landmarks along river and lake shorelines were selected as shoreline fixed landmarks, including bridge piers, river boundary markers, fixed monitoring piles, and shoreline protection engineering turning points. Subsequently, the spatial positions of the selected hydrological monitoring stations, automatic water quality monitoring stations, and shoreline fixed landmarks were verified to ensure that their spatial coordinate data accurately corresponded to the national unified geodetic coordinate system. Next, a buffer zone analysis method was used, with each key reference point as the center, and a buffer zone radius was set according to its monitoring range and data transmission radius. The buffer zone radius for hydrological monitoring stations and automatic water quality monitoring stations was set to 3 kilometers, and the buffer zone radius for shoreline fixed landmarks was set to 1 kilometer. By overlaying the buffer zones of all key reference points, an initial spatial coverage area comprehensively covering all spatial coverage blind spots was constructed.

[0079] Step 2.3: Based on the initial spatial coverage area, and combined with the geographical characteristics of rivers and lakes and monitoring needs, the initial spatial coverage area is spatially partitioned, dividing the river and lake area into multiple logical partitions with continuous spatial coverage characteristics. Specifically, this includes: firstly collecting geographical feature data of the target rivers and lakes, including basic geographical information such as watershed boundaries, topographic and geomorphological types, river course, lake bay distribution, and shoreline vegetation coverage areas; and secondly clarifying monitoring needs, covering specific monitoring directions such as key areas for water quality monitoring, key sections for shoreline ecological protection, and core areas for flood control safety. Based on the initial spatial coverage area, spatial zoning is carried out according to the principles of consistency of geographical features and relevance of monitoring needs. For river-type rivers and lakes, the main tributary confluence points and topographic turning points within the basin are used as boundaries to divide the river into several continuous river segment zones. The length of each river segment zone is controlled between 5 and 10 kilometers to ensure that the river course and topographic features within the zone are relatively consistent. For lake-type rivers and lakes, the lakes are divided into several continuous lake area zones according to geographical features such as lake bay distribution, water depth differences, and shoreline utilization types. The area of ​​each lake area zone does not exceed 5 square kilometers to avoid the zone being too large, which would make it difficult to accurately analyze the monitoring data. During the zoning process, it is necessary to ensure that each logical zone has continuous spatial coverage characteristics, that the zone boundaries are consistent with the geographical features of the river and lake, and that each zone contains a certain number of key reference points, while covering the corresponding high-density, medium-density monitoring areas and spatial coverage blind spots.

[0080] Step 2.4: Based on each logical partition, perform circular geometry fitting on the key monitoring points distributed within each partition to calculate the final geometric center position and coverage radius parameters of each partition. Specifically, this includes: First, extracting the precise spatial coordinate data of all key reference points within each logical partition. The coordinate data is based on the national unified geodetic coordinate system, accurate to 0.1 meters, forming an independent set of spatial coordinates for key monitoring points in each partition. Based on the coordinate set, calculate the straight-line distance between all key monitoring points within each partition, constructing a complete spatial distance relationship matrix. Use the matrix data to identify the spatial distribution density characteristics of each monitoring point, determining the relatively concentrated core area and relatively dispersed edge area of ​​the monitoring points. Then, based on the spatial distance relationship matrix and spatial distribution density characteristics, perform initial circular geometry fitting on the key monitoring points within each partition. Use the center position of the core area with the highest monitoring point density as the candidate position for the initial geometric center, ensuring that the distance to most surrounding monitoring points is relatively balanced. Next, calculate the radial distance from all key monitoring points within each partition to the candidate position for the initial geometric center. The mean, standard deviation, maximum, and minimum values ​​of these radial distances are calculated to analyze their statistical distribution characteristics and determine whether the initial geometric center candidate position is located at the spatial distribution center of the monitoring points within the partition. Based on the statistical distribution characteristics of the radial distance, if the standard deviation of the radial distance is greater than 5 meters, the initial geometric center candidate position is iteratively corrected. Each correction adjusts the position by 0.5 meters according to the bias direction of the radial distance distribution until the standard deviation of the radial distance is less than or equal to 5 meters, thus obtaining the optimized geometric center position. Based on the optimized geometric center position, the distance from each key monitoring point to the center is recalculated, and the maximum distance value is selected as the initial coverage radius parameter. Then, the coverage integrity of the circular geometric fitting for the key monitoring points within each partition is evaluated, and the proportion of the number of key monitoring points within the initial coverage radius to the total number of key monitoring points in that partition is counted. If this proportion is less than 95%, the initial coverage radius is increased by 10%, and the coverage integrity is recalculated. This adjustment is repeated until the coverage integrity reaches 95% or higher, finally determining the final geometric center position and coverage radius parameter for each partition.

[0081] Step 2.5: Based on the final geometric center position and coverage radius parameters of each partition, optimize the spatial geometric reference datum of each partition to determine the precise spatial positioning parameters and spatial coverage range of each partition. Specifically, this includes: optimizing the spatial geometric reference datum of each partition based on the final geometric center position and coverage radius parameters; first, setting the final geometric center position as the origin of the spatial geometric reference datum of that partition, establishing a local spatial coordinate system for that partition, with the X-axis parallel to the east longitude direction and the Y-axis parallel to the north latitude direction; then, calibrating the local spatial coordinate system of the partition in conjunction with a unified geodetic coordinate system, calculating the transformation parameters between the local coordinate system and the geodetic coordinate system to ensure accurate alignment of the two coordinate systems; based on the calibrated local coordinates... Based on the system and final coverage radius parameters, the precise spatial positioning parameters for each partition are determined, including the origin coordinates, coordinate axis directions, and scale in the local coordinate system of the partition. The origin coordinates are accurate to 0.1 meters, and the scale error is controlled within 0.01%. At the same time, based on the final geometric center position and coverage radius parameters, the spatial coverage range of each partition is calculated, and the four boundary coordinates of the partition are determined: the easternmost east longitude coordinate, the westernmost east longitude coordinate, the southernmost north latitude coordinate, and the northernmost north latitude coordinate. This ensures that the coverage range completely includes all key monitoring points, monitoring data distribution areas, and spatial coverage blind spots within the partition, and that the partition boundary has no overlap or gap with the coverage range of surrounding partitions. Finally, precise and unique spatial positioning parameters and spatial coverage range are formed for each partition.

[0082] Step 2.6: Based on the precise spatial positioning parameters and spatial coverage of each partition, analyze the spatial distribution characteristics of each partition after optimization, including partition area parameters, shape coefficient parameters, and monitoring point density parameters, to obtain the corresponding spatial correction factors. Specifically, this includes: based on the precise spatial positioning parameters and spatial coverage of each partition, conducting an analysis of the spatial distribution characteristics of each partition after optimization. First, calculate the partition area parameter. Using geographic information analysis technology, perform polygon fitting on the spatial coverage boundary of the partition, and use the polygon area calculation formula to accurately calculate the actual area of ​​each partition, with the result accurate to 1 square meter. Next, calculate the shape coefficient parameter. First, measure the total perimeter of the partition boundary, accurate to 0.1 meters, and then calculate according to the shape coefficient calculation logic: shape coefficient = 4π × partition area ÷ the square of partition perimeter. The shape coefficient value ranges between 0 and 1; the closer it is to 1, the closer the partition shape is to a circle, with the calculation result accurate to 0.001. Then, calculate the monitoring point density parameter, and count the number of monitoring points contained in each partition. The total number of key monitoring points is divided by the area of ​​each zone, converted to square kilometers, to obtain the monitoring point density for each zone, expressed as points per square kilometer, accurate to 0.1 points per square kilometer. Finally, a corresponding spatial correction factor is generated based on the zone area parameter, shape coefficient parameter, and monitoring point density parameter. The three parameters are weighted and summed with weights of 0.3, 0.4, and 0.3 respectively. The weighted sum is the spatial correction factor for that zone. The numerical range of the spatial correction factor is controlled between 0.8 and 1.2, accurate to 0.001, to ensure that the correction factor accurately reflects the spatial distribution characteristics of the zone.

[0083] In this embodiment of the invention, a series of technical means are employed, including receiving detection data and conducting spatial coverage analysis to identify data density distribution and spatial coverage blind spots; selecting key reference points to construct the initial spatial coverage area of ​​the coverage blind spots; combining river and lake geographical features with monitoring needs to perform spatial zoning; performing circular geometric fitting on key monitoring points in each zone to calculate the final geometric center and coverage radius; optimizing the spatial geometric reference benchmark and determining precise spatial parameters; and analyzing the spatial distribution characteristics of the zones to generate spatial correction factors. Therefore, the technical problems of blind spots in spatial coverage, lack of rationality in zoning, and inconsistent spatial reference benchmarks in traditional river and lake monitoring, which lead to poor spatial consistency and insufficient accuracy in subsequent data processing, are effectively overcome. This allows for the precise delineation of logical zones and precise spatial ranges for river and lake monitoring, and the generation of spatial correction factors that fit the actual zoning.

[0084] In a preferred embodiment of the present invention, step 2.4 above may include:

[0085] Step 2.41: Based on the precise spatial coordinate data of key monitoring points distributed within each logical partition, obtain the set of spatial coordinates of key monitoring points for each partition; based on the set of spatial coordinates of key monitoring points, calculate the spatial distance relationship matrix between all key monitoring points within each partition, and identify the spatial distribution density characteristics of each monitoring point. Specifically, this includes: First, extracting the precise spatial coordinate data of all key monitoring points within each logical partition. These key monitoring points include hydrological monitoring stations, automatic water quality monitoring stations, and shoreline fixed markers. Their spatial coordinates are all based on the national unified geodetic coordinate system, with coordinate values ​​accurate to 0.1 meters, ensuring the accuracy of the spatial location information of each monitoring point, thereby forming an independent set of spatial coordinates of key monitoring points for each partition. The set clearly records the unique identifier of each monitoring point and its corresponding east longitude and north latitude coordinates; Next, for each partition's set of spatial coordinates of key monitoring points, calculate the straight-line distance between all monitoring points within the set. The spatial distance calculation method involves determining the actual straight-line distance between any two key monitoring points within a given zone, accurate to 0.1 meters, using their coordinate data and a geospatial distance calculation method. A complete spatial distance matrix is ​​constructed by arranging all the straight-line distances between each pair of monitoring points in a fixed order. The rows and columns of the matrix correspond to the key monitoring points within the zone, and each element represents the straight-line distance between the corresponding two monitoring points. Finally, the spatial distribution density characteristics of each monitoring point are analyzed based on the spatial distance matrix. The number of other key monitoring points within a 1-kilometer radius of each monitoring point is counted. If the number of other monitoring points within a 1-kilometer radius of a monitoring point is greater than or equal to 8, the area where that monitoring point is located is determined to be a high-density area; if the number is between 3 and 7, it is a medium-density area; and if the number is less than 3, it is a low-density area. This method clearly identifies the spatial distribution density of key monitoring points within each zone.

[0086] Step 2.42: Using the spatial distance relationship matrix and spatial distribution density characteristics, perform initial circular geometric fitting on the key monitoring points within each partition to determine the candidate positions of the initial geometric center for each partition. Using these candidate positions, calculate the radial distance from all key monitoring points within each partition to the initial geometric center and analyze the statistical distribution characteristics of the radial distance. Specifically, this includes: performing initial circular geometric fitting on the key monitoring points within each partition based on the obtained spatial distance relationship matrix and spatial distribution density characteristics; preferentially selecting the center position of the high-density spatial distribution area within the partition as the candidate position of the initial geometric center. Specifically, calculate the average coordinates of all key monitoring points within the high-density area, and determine the spatial position corresponding to the average value as the candidate position of the initial geometric center, ensuring that this candidate position... The initial geometric center candidate location is located as close as possible to the area where monitoring points are relatively concentrated within the partition. Then, using the initial geometric center candidate location as a benchmark, the radial distance from each key monitoring point within the partition to that center location is calculated, with the radial distance calculation accurate to 0.1 meters, forming a set of radial distances for each partition. Next, a statistical analysis is performed on the radial distance set, calculating the mean, standard deviation, maximum, minimum, and median of the radial distances. The mean reflects the average distance from all monitoring points to the initial center, the standard deviation reflects the dispersion of the radial distances, the maximum and minimum values ​​define the distance range, and the median helps determine the balance of the distance distribution. Through this comprehensive analysis of the statistical distribution characteristics of the radial distances, it is determined whether the initial geometric center candidate location is located in the core area of ​​the spatial distribution of key monitoring points within the partition.

[0087] Step 2.43: Based on the radial distance statistical distribution characteristics, the initial geometric center candidate positions are iteratively corrected to obtain the optimized geometric center position. Based on the optimized geometric center position, the distances from each key monitoring point to the optimized geometric center are recalculated, and the maximum distance value is determined as the initial coverage radius parameter. Specifically, this includes: based on the analyzed radial distance statistical distribution characteristics, using the standard deviation of the radial distance as the core judgment indicator, the initial geometric center candidate positions are iteratively corrected; a qualified threshold of 5 meters for the radial distance standard deviation is set. If the radial distance standard deviation corresponding to the initial geometric center candidate position is greater than 5 meters, it indicates that the candidate position is not in the optimal position and needs to be corrected; during correction, the radial distance distribution bias is considered. To adjust the candidate positions, if the radial distance in a certain direction is too large overall, the initial geometric center candidate position is moved 0.5 meters in that direction to form a new candidate position. Then, the radial distances from all key monitoring points in the partition to the new candidate position are recalculated, and the standard deviation of the radial distance is calculated again. The above process of correction and standard deviation calculation is repeated until the standard deviation of the radial distance is less than or equal to 5 meters. The candidate position obtained at this time is the optimized geometric center position. Subsequently, based on the optimized geometric center position, the radial distances from each key monitoring point to the center position are recalculated. All radial distance values ​​are compared one by one, and the maximum distance value is selected as the initial coverage radius parameter of the partition. The initial coverage radius parameter is accurate to 0.1 meters.

[0088] Step 2.44: Based on the initial coverage radius parameter, evaluate the coverage integrity of the circular geometric fit for key monitoring points in each partition. When the coverage integrity does not meet the preset threshold, adjust the optimized geometric center position and coverage radius parameter to obtain the final geometric center position and coverage radius parameter. Specifically, this includes: First, based on the determined initial coverage radius parameter, evaluate the coverage integrity of the circular geometric fit for key monitoring points in each partition. The coverage integrity is calculated by counting the number of key monitoring points within the initial coverage radius, dividing the number of key monitoring points by the total number of key monitoring points in the partition, and obtaining the coverage integrity percentage, accurate to 0.1%. The preset threshold for coverage integrity is set to 95%. If the calculated coverage integrity percentage is greater than or equal to 95%, it means that the initial coverage radius and the optimized geometric center position can effectively cover the vast majority of key monitoring points within the partition. No adjustment is needed, and the geometric center position and initial coverage radius parameters are directly determined as the final geometric center position and coverage radius parameters. If the coverage integrity percentage is less than 95%, the initial coverage radius parameter is first increased by 10%, and the coverage integrity is recalculated. If the coverage integrity still does not reach 95% after the increase, the coverage radius is continued to be increased by 10% until the coverage integrity reaches 95% or above. If the coverage integrity still does not meet the standard after increasing the coverage radius multiple times, the optimized geometric center position is fine-tuned based on the increased radius. The direction of each fine-tuning is determined according to the concentrated distribution direction of the uncovered monitoring points, and the fine-tuning distance is 0.3 meters. After adjustment, the coverage integrity is recalculated until the coverage integrity meets the preset threshold of 95%. Finally, the final geometric center position and coverage radius parameters of each partition are determined.

[0089] In this embodiment of the invention, a series of technical means are employed, including obtaining the precise spatial coordinate set of key monitoring points within each logical partition, calculating the spatial distance relationship matrix between monitoring points and identifying spatial distribution density characteristics, performing initial circular geometric fitting based on the above data to determine the candidate position of the initial geometric center, iteratively correcting the geometric center through the radial distance statistical distribution characteristics, and adjusting parameters with the maximum distance as the initial coverage radius and in combination with the preset threshold for coverage integrity. Therefore, the technical problems of lacking accurate data support, large deviation between the geometric center and the coverage radius, and difficulty in fully covering key monitoring points within the partition in the traditional determination of partition geometric parameters are effectively overcome, thereby accurately obtaining the final geometric center position and coverage radius parameters of each partition.

[0090] In a preferred embodiment of the present invention, step 3 above may include:

[0091] Step 3.1: Based on the detection data and spatial correction factors, perform spatial normalization processing on the detection data of each partition to obtain a preliminary fused dataset for each partition. Using the preliminary fused dataset as a basis, and combining the partition area parameter, shape factor parameter, and monitoring point density parameter in the spatial correction factors, perform spatial weighted fusion on the data of each partition to obtain an aligned dataset with a unified spatial reference. Specifically, this includes: First, retrieving the detection dataset after spatiotemporal alignment, format unification, and outlier cleaning; simultaneously extracting the spatial correction factors corresponding to each partition to clarify the partition area parameter, shape factor parameter, and monitoring point density parameter for each partition; then, performing spatial normalization processing on the detection data of each partition, using the national unified geodetic coordinate system as a reference, uniformly adjusting the spatial resolution of satellite remote sensing data, UAV monitoring data, video surveillance data, and social network structured data to 10 meters. ×10 meters ensures consistent spatial scale across different data types. For numerical monitoring data, such as dissolved oxygen content and ammonia nitrogen concentration, the numerical range is uniformly mapped to the 0-100 range, preserving the relative magnitude of the data during the mapping process to avoid numerical distortion. For image data, such as satellite remote sensing images and UAV high-resolution images, they are uniformly adjusted to the same pixel depth and color space to ensure the comparability of image data. After completing the spatial normalization of all data, the satellite remote sensing data, UAV monitoring data, video surveillance data, and social network structured data in each partition are linked and integrated according to spatial coordinates to form a preliminary fused dataset for each partition. Each data point in the dataset contains precise spatial coordinates, data type, normalized value, and data source identifier. Based on the preliminary fused dataset, spatial weighted fusion is performed using the three core parameters in the spatial correction factor. The weights of the partition area parameter, shape coefficient parameter, and monitoring point density parameter are set to 0.3, 0.4, and 0.3 respectively. First, the comprehensive weighting coefficient for each data point is calculated: Comprehensive weighting coefficient = Partition area parameter × 0.3 + Shape coefficient parameter × 0.4 + Monitoring point density parameter × 0.3. For multi-source data at the same spatial coordinate in the preliminary fusion dataset, a weighted average is calculated based on the comprehensive weighting coefficient. For example, if both UAV-monitored water quality data and satellite remote sensing water index data exist at a certain spatial coordinate, they are multiplied by their respective comprehensive weighting coefficients, summed, and then divided by the total coefficients to obtain the fused data value at that coordinate. For spatial coordinates with only a single data source, the normalized value of that data source is directly retained as the fusion result. Through weighted fusion processing, data from different sources and scales within each partition are integrated into an aligned dataset with a unified spatial reference.

[0092] Step 3.2 involves combining the aligned dataset with the precise spatial positioning parameters and coverage of each partition, performing spatial interpolation and smoothing to obtain a smoothed dataset that eliminates discontinuities at partition boundaries. By applying a spatial correction factor to the smoothed dataset and performing spatial coordinate transformation and correction, sub-datasets of river and lake health monitoring for each partition with a consistent spatial reference system are obtained. Specifically, this includes: first, retrieving the precise spatial positioning parameters of each partition, including the origin coordinates, coordinate axis directions, scale, and spatial coverage, and associating the aligned dataset with the spatial parameters to clarify the precise location of each fused data point in the partition's local coordinate system; second, performing spatial interpolation on the data at each partition boundary, using effective data within 500 meters on both sides of the partition boundary as the interpolation data source, setting the interpolation node spacing to 10 meters, and calculating the interpolated data in the boundary blank areas to ensure continuous data transition on both sides of the boundary; and third, for areas with relatively sparse data distribution within the partition, the same... This interpolation method is used to supplement data, making the data distribution within the partition uniform. After interpolation, a 3×3 grid moving average method is used to smooth the aligned dataset. The average value of each data point and its eight neighboring data points is calculated, and this average value is used as the smoothed value of the data point to eliminate abrupt outliers in the data, resulting in a smoothed dataset that eliminates discontinuities at partition boundaries. Subsequently, a spatial correction factor is applied to the smoothed dataset to perform spatial coordinate transformation and correction. Using a unified geodetic coordinate system as the target coordinate system, the transformation parameters between the local coordinate system and the geodetic coordinate system for each data point in the smoothed dataset are calculated based on the precise spatial positioning parameters of the partition. These parameters include translation, rotation angle, and scaling. The calculation accuracy of the transformation parameters is controlled within 0.001. The spatial coordinates of all data in the smoothed dataset are transformed from the partition local coordinate system to the national geodetic coordinate system according to the transformation parameters, ensuring that the spatial position of each data point accurately corresponds to its actual geographical location. After the conversion is completed, the data is corrected again by combining the monitoring point density parameter in the spatial correction factor. If the monitoring point density in a certain area is less than 3 points / km², the converted value of that area is corrected by 0.9 times. If the monitoring point density is greater than 8 points / km², the correction is 1.1 times. The values ​​in the intermediate density area remain unchanged to compensate for the differences in data reliability in different density areas. After the above processing, a subset of river and lake health monitoring data with a consistent spatial reference system, continuous and reliable data is obtained.

[0093] Step 3.3 integrates the river and lake health monitoring subsets from each zone to form an optimized dataset. Specifically, this includes: first, collecting the river and lake health monitoring subsets from all zones, establishing a spatial indexing system covering the entire river and lake area, using a 10m×10m grid as the index unit, and mapping the data of each subset to the corresponding index unit according to spatial coordinates. To address data conflicts in spatially overlapping areas of different subset datasets, a credibility-weighted fusion method was employed. Data credibility weights were set as follows: 0.8 for satellite remote sensing data, 0.7 for UAV monitoring data, 0.6 for video surveillance data, and 0.5 for structured data from social networks. For multiple data points within the same index unit in an overlapping area, a weighted average was calculated as the final data value for that unit. The weighted average was calculated as: (Satellite remote sensing data × 0.8 + UAV data × 0.7 + Video surveillance data × 0.6 + Social network data × 0.5) ÷ the sum of the weights of the data involved in the calculation, ensuring the rationality of the data in overlapping areas. Next, a unified dataset framework was constructed for the entire river and lake area. This framework includes fields such as basic data information (spatial coordinates), data collection time, data type, monitoring indicator values ​​(water quality, hydrology, ecology, and other multi-dimensional indicators), data credibility score, and spatial correction identifiers. The conflict-resolved data from each subset dataset was then organized and filled according to the field requirements of the unified framework, ensuring consistent field formats and complete information across all data. Subsequently, data integrity verification is performed, statistically analyzing the data missingness of each index unit across the entire river and lake area. If the data missing rate of a certain index unit is higher than 5%, it is supplemented using the average data value of the eight surrounding index units; if the missing rate is lower than 5%, the existing data is directly retained. Finally, a global consistency check is performed on the integrated dataset to verify the spatial continuity of the data, ensuring that the data difference between adjacent index units does not exceed 10, the numerical rationality conforms to the normal range of river and lake health monitoring indicators, and the spatial reference uniformity. All data is based on the geodetic coordinate system; if data anomalies are found, the corresponding partition subset is returned for secondary correction. After the above index mapping, conflict handling, frame filling, integrity verification, and consistency check, an optimized dataset is formed.

[0094] In this embodiment of the invention, a series of technical means are employed to overcome the technical problems of inconsistent spatial benchmarks, discontinuous and broken boundary data, and low data fusion accuracy in traditional multi-source data fusion, which make it difficult to form a unified and reliable river and lake monitoring dataset. These means include combining spatial correction factors to perform spatial normalization processing on the detection data of each partition, carrying out spatial weighted fusion based on partition area parameters, shape coefficient parameters, and monitoring point density parameters, and then combining the aligned dataset with the precise spatial parameters of the partition for spatial interpolation and smoothing processing, achieving a unified data spatial reference system through spatial coordinate transformation and correction, and finally integrating the subset datasets of each partition. As a result, an optimized dataset covering the entire river and lake area is successfully constructed, improving the spatial consistency, continuity, and reliability of the monitoring data.

[0095] In a preferred embodiment of the present invention, step 4 above may include:

[0096] Step 4.1: Based on the optimized dataset, extract multi-dimensional monitoring indicator data related to river and lake health diagnosis to form a health diagnosis input data set. Specifically, this includes: First, retrieving the optimized dataset, which covers satellite remote sensing, drone monitoring, video surveillance and social network structured data, and has the characteristics of unified spatial benchmark and continuous reliability. Based on the multi-dimensional needs of river and lake health diagnosis, the monitoring indicator dimensions are clearly extracted, including three core dimensions: ecological health, flood control safety, and management efficiency. This comprehensively covers the key evaluation directions mentioned in the background technology that require overall coordination. The ecological health dimension indicators specifically include water quality indicators, aquatic biological indicators, and shoreline ecological indicators. Water quality indicators extract data such as dissolved oxygen content, pH, ammonia nitrogen concentration, total phosphorus concentration, total nitrogen concentration, and permanganate index, sourced from near-ground monitoring by UAVs and synchronous data from automatic water quality monitoring stations. Aquatic biological indicators extract data such as plankton community structure, benthic biodiversity, and fish population size and distribution, obtained through satellite remote sensing image inversion and integration of field sampling data. Shoreline ecological indicators extract data such as shoreline vegetation coverage, native vegetation retention rate, shoreline hardening rate, and ecological buffer zone width, obtained by analyzing high-resolution UAV imagery and video surveillance data. The flood control safety dimension indicators specifically include dike compliance rate, flood discharge capacity index, and flood risk warning response efficiency. The dike compliance rate is obtained through video surveillance footage of the dike's exterior integrity. The system compares and calculates the dike dimensions monitored by drones with design standards; the flood discharge capacity index is calculated based on hydrological data such as river cross-section dimensions, water depth, and flow velocity, combined with data on the river's flood discharge range extracted by satellite remote sensing; the flood risk warning response efficiency is obtained through analysis of the difference between the warning release time and the emergency response initiation time in historical flood events; specific management efficiency indicators include monitoring coverage, problem rectification completion rate, and public satisfaction. The monitoring coverage rate is calculated based on the ratio of the spatial coverage area of ​​a unified dataset to the total area of ​​rivers and lakes; the problem rectification completion rate is calculated by combining feedback information on river and lake environmental issues extracted from social networks, records of violations discovered by video surveillance, and data from the public announcement of rectification results by relevant departments; public satisfaction is calculated by analyzing the sentiment of text information related to the river and lake environment on social networks, extracting the proportion of positive, neutral, and negative evaluations; the above multi-dimensional monitoring indicator data are classified and organized by region, and each indicator data is associated with corresponding spatial coordinates, data collection time, and data credibility score, forming a structured health diagnosis input data set.

[0097] Step 4.2: Input the health diagnosis input data set into the preset river and lake health diagnosis index model. Based on the model's built-in index weighting system and health level classification rules, standardize the calculations and map health scores for each indicator to generate preliminary health status scores for each zone. Specifically, this includes: First, clarifying the core components of the preset river and lake health diagnosis index model. The model's built-in index weighting system sets the ecological health dimension weight to 0.4 based on the impact of each dimension on river and lake health, with water quality indicators accounting for 0.16, aquatic organism indicators for 0.12, and shoreline ecological indicators for 0.12; the flood control safety dimension weight to 0.3, with dike compliance rate for 0.1, flood discharge capacity index for 0.1, and flood risk warning response efficiency for 0.1; and the management efficiency dimension weight to 0.3, with monitoring coverage rate for 0.1, problem rectification completion rate for 0.1, and public satisfaction for 0.1. The model's built-in health level classification rules... A comprehensive score of 80-100 is considered excellent, 60-79 is good, 40-59 is average, and below 40 is poor. The health diagnosis input data set is then fed into the model, and standardized calculations are performed on each indicator. For positive indicators, such as dissolved oxygen content, vegetation coverage, and compliance rate, a linear normalization method is used to convert the actual values ​​of the indicators into standardized scores from 0 to 100, with higher values ​​corresponding to better health. For negative indicators, such as ammonia nitrogen concentration, total phosphorus concentration, and shoreline hardening rate, a reverse linear normalization method is used to convert the actual values ​​of the indicators into standardized scores from 0 to 100, with lower values ​​corresponding to worse health, ensuring that the standardized scores of all indicators have a unified evaluation direction. After the standardization calculations are completed, health scores are mapped according to the indicator weight system, that is, the standardized score of each indicator is multiplied by its corresponding weight, and then the weighted scores of all indicators are summed to obtain the preliminary health status score for each zone.For example, a certain zone's standardized score for a water quality indicator is 85 points, corresponding to a weight of 0.16, and the weighted score for this item is 13.6 points. The weighted scores of all indicators are calculated sequentially and summed to obtain the preliminary health status score of the zone, accurate to 0.1 points. The construction process of the river and lake health diagnostic indicator model involves first identifying three core evaluation dimensions—ecological health, flood control safety, and management efficiency—based on the core impact dimensions of river and lake health. Then, weights are assigned based on the degree of impact of each dimension on river and lake health. The ecological health dimension has a weight of 0.4, with subdivisions including water quality indicators (0.16%), aquatic biological indicators (0.12%), and shoreline ecological indicators (0.12%). The flood control safety dimension has a weight of 0.3, with subdivisions including dike compliance rate (0.1%), flood discharge capacity index (0.1%), and flood risk warning response (0.3%). Efficiency accounts for 0.1; management effectiveness is weighted at 0.3, with subdivided monitoring coverage, problem rectification completion rate, and public satisfaction each accounting for 0.1, forming a complete indicator weighting system; standardized calculation rules are established, using linear normalization for positive indicators such as dissolved oxygen content and reverse linear normalization for negative indicators such as ammonia nitrogen concentration, uniformly converting all actual indicator values ​​into standardized scores from 0 to 100 to ensure consistent evaluation direction; finally, health level classification rules are set, specifying a comprehensive score of 80 to 100 as excellent, 60 to 79 as good, 40 to 59 as average, and below 40 as poor, thus constructing a river and lake health diagnostic indicator model that combines systematic indicators, reasonable weights, standardized calculations, and clear levels.

[0098] Step 4.3: Based on the preliminary health status score, and combined with the spatial attributes and monitoring data integrity of each zone, spatial consistency correction and reliability weighting are applied to the score to obtain the corrected health status score for each zone. Specifically, this includes: First, collecting spatial attribute data for each zone, including zone type (river, lake, reservoir), zone area, and topographic features (plain, mountain, etc.). Simultaneously, calculating the monitoring data integrity for each zone, which is determined by the ratio of the number of valid monitoring data entries within the zone to the theoretically required number of data entries, accurate to 0.1%. Second, performing spatial consistency correction based on spatial attributes: For adjacent zones, calculating the difference in their preliminary health status scores. If the difference exceeds 10 points, and the two zones have similar geographical features and construction conditions (e.g., both are plain river zones with consistent shoreline management measures), then the zone with the higher score is lowered by 3 to 5 points, and the zone with the lower score is increased by 3 to 5 points, keeping the score difference between adjacent zones within 10 points. If a zone is an independent lake zone, and its geographical features differ from surrounding zones... If the difference is significant, the initial score remains unchanged. A credibility weighting is applied based on the completeness of the monitoring data. The credibility weight is set as follows: 1.0 for 100% data completeness; 0.95 for 90% to 99%; 0.9 for 80% to 89%; 0.85 for 70% to 79%; and 0.8 for below 70%. The initial health status score of each partition is multiplied by the corresponding credibility weight to obtain the weighted score. Finally, the corrected health status score for each partition is calculated by combining the spatial consistency correction and the credibility weighting results: if only spatial consistency correction was performed, the corrected score is the corrected score; if only credibility weighting was performed, the weighted score is the corrected score; if both are performed, spatial consistency correction is performed first, and then the corrected score is multiplied by the credibility weight to obtain the final corrected health status score, accurate to 0.1 points.

[0099] Step 4.4: Based on the corrected health status score, and following an evaluation strategy combining overall and regional assessments of rivers and lakes, determine the health status level and analyze spatial distribution characteristics to obtain structured river and lake health status assessment results. These results include the overall health level, regional health level distribution, and identification of major health problems. Specifically, this includes: First, conducting the assessment according to the combined overall and regional assessment strategy: For each region, based on the corrected health status score and preset health level classification rules, determine the health level of each region: 80-100 points is excellent, 60-79 points is good, 40-59 points is average, and below 40 points is poor. Simultaneously, record the specific score for each region's corresponding level, as well as the highest and lowest scores for the core indicators. For the overall river and lake, calculate the average of the corrected health status scores for all regions; this average is the overall river and lake health score. Then, determine the overall river and lake health level based on the overall health score, with the classification standards consistent with those for the regions. Subsequently, conduct spatial distribution characteristic analysis, using geographic information visualization technology to visualize the health status of each region. The health levels are marked with different colors on the spatial distribution map of the entire river and lake area, clearly showing the spatial distribution patterns of zones with excellent, good, average, and poor health levels, and identifying areas with concentrated health levels, such as areas in the downstream of a watershed where multiple zones have excellent and healthy levels scattered across the board. For each zone, indicators with standardized scores below 60 are extracted. If two or more indicators under a certain dimension have scores below 60, then that dimension is determined to be the main health problem for that zone. For example, if the standardized scores for ammonia nitrogen concentration and total phosphorus concentration in water quality indicators are both 55, then water pollution is determined to be the main health problem for that zone. If only a single indicator has a score below 60, then the specific problem corresponding to that indicator is determined to be a secondary health problem. All information is integrated to form a structured assessment result of the river and lake health status, specifically including the overall health level of the river and lake, the overall health score, the health level and corresponding score of each zone, the spatial distribution map of health levels, the list of main health problems for each zone, and a summary of main health problems for the entire area. If multiple zones in the entire area have water pollution problems, then they are listed as key health problems for the entire area.

[0100] In this embodiment of the invention, because it employs a technical approach that involves extracting multi-dimensional health diagnostic indicators from an optimized dataset, inputting them into a preset river and lake health diagnostic indicator model, and performing standardized calculations and score mapping based on a built-in indicator weighting system and health level classification rules, then combining the spatial attributes of each zone with the integrity of monitoring data to perform spatial consistency correction and credibility weighting on the preliminary scores, and finally conducting health level determination and spatial distribution characteristic analysis according to an evaluation strategy that combines the overall river and lake status with zone-based assessments, it effectively overcomes the technical problems in traditional river and lake health assessments, such as one-sided indicator selection, lack of scientific and standardized basis for score calculation, failure to consider zone differences and data integrity leading to large deviations in assessment results, low degree of structure, and difficulty in comprehensively and accurately reflecting the overall and zone-based health status and core issues of rivers and lakes. This results in a structured assessment result that includes overall health level, zone-based health level distribution, and identification information of major health problems, thus improving the comprehensiveness, accuracy, and practicality of river and lake health status assessment.

[0101] In a preferred embodiment of the present invention, step 5 above may include:

[0102] Step 5.1: Using the structured river and lake health status assessment results, extract health status indicators, historical trends, and spatial distribution anomaly information related to risk warning to obtain initial input data for risk warning. Specifically, this includes: First, retrieving the structured river and lake health status assessment results, which contain core information such as the overall health level of rivers and lakes, the health level and corresponding scores of each zone, the spatial distribution map of health levels, the list of major health problems in each zone, and a summary of key health problems across the entire region. From the assessment results, select health status indicators directly related to risk warning, prioritizing key water quality indicators such as ammonia nitrogen concentration, total phosphorus concentration, total nitrogen concentration, and dissolved oxygen content in the ecological health dimension; shoreline ecological indicators such as shoreline hardening rate and vegetation coverage; dike compliance rate and flood discharge capacity index in the flood control safety dimension; and problem rectification completion rate in the management efficiency dimension, ensuring that the indicators cover core risk-related items such as cyanobacterial blooms and shoreline restoration deviations mentioned in the background technology. Next, extract the historical trend data of each indicator, collect the standardized scores of health status indicators for the same period in the past three years, and calculate the annual... The rate of change of indicators during the same period is analyzed to determine whether the indicators are continuously deteriorating, fluctuating, or slowly improving. If the cumulative decrease in the rate of change of an indicator over three years exceeds 30%, it is judged as a continuous deterioration trend; if the annual fluctuation of the rate of change exceeds 20%, it is judged as a fluctuating trend; if the cumulative increase or decrease in the rate of change over three years does not exceed 10%, it is judged as a slow improvement or stable trend. At the same time, spatial distribution anomalies are identified: the differences between the health levels of each zone and the surrounding zones are compared. If the health levels of two adjacent zones differ by two levels or more, such as one being excellent and the other being poor, and the geographical environment and construction measures are similar, it is judged as a spatial distribution anomaly. If the standardized score of a certain type of indicator in a zone decreases by more than 20 points compared with the same period of the previous year, or is more than 30 points lower than the average score of the surrounding zones, it is also judged as a spatial distribution anomaly. The selected health status indicators, the analyzed historical change trend data, and the identified spatial distribution anomaly information are classified and organized by zone. Each piece of information is associated with the corresponding spatial coordinates, indicator name, change range, and anomaly type to form structured initial input data for risk warning.

[0103] Step 5.2: Input the initial risk warning data into the preset river and lake health risk warning model. Based on the risk evolution law and multi-threshold judgment rules embedded in the model, calculate the risk probability and preliminarily classify the risk level of each zone's health status. Specifically, this includes: First, clarifying the core components of the preset river and lake health risk warning model. The model embeds the risk evolution law of different health problems, such as: when the total phosphorus concentration continues to rise, the risk of cyanobacterial blooms will increase exponentially with the increase in concentration; when the shoreline hardening rate exceeds 60% and the vegetation coverage is less than 40%, the risk of soil erosion will increase; when the dike compliance rate is less than 70%, the probability of flood overflow increases synchronously with the rise in water level; the model has built-in multi-threshold judgment... The rules, based on risk probability as the core criterion, classify risk probabilities as follows: 0% to 30% is low risk, 31% to 60% is medium risk, 61% to 80% is high risk, and 81% to 100% is extremely high risk. Initial risk warning data is input into the model, and the risk probability is calculated for each zone's health status indicators, combined with historical trends. For continuously deteriorating indicators, the rate of deterioration is multiplied by a base risk coefficient; the base risk coefficient for water quality indicators is 0.8, for flood control indicators it is 0.7, and for shoreline ecological indicators it is 0.75. For fluctuating indicators, the highest historical risk value is multiplied by a fluctuation coefficient; the larger the fluctuation, the higher the coefficient, with a maximum fluctuation coefficient of 1.2. For indicators with abnormal spatial distribution, a 15% risk premium is added to the normal calculation result. After completing the risk probability calculation, the risk level of each zone is initially determined according to the multi-threshold judgment rule. If there are multiple risk-related indicators in a certain zone, the level corresponding to the indicator with the highest risk probability is taken as the preliminary risk level of the zone. If the risk probabilities of multiple indicators are in different ranges, and the difference between the highest risk probability and the second highest risk probability does not exceed 10%, the preliminary risk level is determined by raising the higher level by one level to ensure that no potential compound risks are missed. The construction process of the river and lake health risk early warning model is to first base it on the correlation between common health problems and risks in rivers and lakes, and then embed targeted risk evolution rules. The study clarifies the core correlations: the risk of cyanobacterial blooms increases exponentially with continuously rising total phosphorus concentration; the risk of soil erosion increases when shoreline hardening exceeds 60% and vegetation coverage is below 40%; and the risk of flooding increases synchronously with rising water levels when dike compliance is below 70%. It then establishes a multi-threshold judgment rule based on risk probability, dividing the risk into four levels: 0% to 30% (low risk), 31% to 60% (medium risk), 61% to 80% (high risk), and 81% to 100% (extremely high risk). Subsequently, it formulates differentiated risk probability calculation rules, multiplying the rate of deterioration of continuously worsening indicators by the corresponding basic risk coefficient: 0.8 for water quality indicators, 0.7 for flood control indicators, and 0 for shoreline ecological indicators.The calculation method (75) involves multiplying the historical highest risk value by a volatility coefficient for indicators with fluctuating changes, and adding a 15% risk premium to the normal calculation result for indicators with abnormal spatial distribution. Finally, a preliminary risk level classification rule is established: when multiple risk-related indicators are used, the level corresponding to the highest risk probability is taken; if the difference between the highest and second-highest risk probabilities does not exceed 10%, the higher level is used, increasing the risk level by one level. This constructs a river and lake health risk early warning model that combines pattern targeting, standardized calculation, and rigorous level determination.

[0104] Step 5.3, based on risk probability and preliminary risk level, combined with external environmental forecast information and human activity impact data, conduct risk spatiotemporal evolution simulation and multi-scenario prediction analysis to obtain dynamic risk evolution maps of each region over a future period. Specifically, this includes: First, collecting external environmental forecast information and human activity impact data: External environmental forecast information includes meteorological forecast data for the next 30 days, daily average temperature, daily precipitation, wind speed, sunshine duration, hydrological forecast data, daily average river flow, lake water level changes, and flood season early warnings. The data comes from official forecasts issued by meteorological departments and hydrological monitoring agencies; Human activity impact data... Impact data for the activity includes pollution discharge plans of industrial enterprises along rivers and lakes, implementation of agricultural non-point source pollution control measures, construction schedules for water conservancy projects such as river dredging, estimated visitor numbers at tourist attractions, and peak periods for domestic sewage discharge by residents along the riverbanks. This data was obtained by integrating filings from relevant authorities, enterprise declarations, and on-site surveys. Based on the risk probability and preliminary risk level of each zone, external environmental forecasts, human activity impact data, and risk evolution patterns were combined to conduct a spatiotemporal risk evolution simulation. The time dimension was divided into three phases: 7 days, 15 days, and 30 days. The spatial dimension radiated outwards from each zone as the core. If the preliminary risk level of the associated area within a 5-kilometer radius is high or very high, and the forecast for the average daily temperature over the next 7 days exceeds 30°C and the sunshine duration exceeds 8 hours, simulate the rate and extent of the spatial spread of cyanobacterial bloom risk to surrounding waters; if the preliminary risk level is medium or higher, and the forecast for the cumulative precipitation over the next 15 days exceeds 200 mm, simulate the propagation path and impact zones of flood overflow risk along the upstream and downstream of the river channel; if there is large-scale engineering construction during human activities, simulate the impact range of soil erosion risk on the surrounding shoreline ecology during construction; set up three scenarios to conduct multi-scenario predictive analysis: Baseline scenario: external ring The environment is within the normal fluctuation range, and human activities are carried out according to the established routine plan; adverse scenario: encountering extreme weather conditions, while the intensity of human activities increases by 30% compared to the normal level; optimized scenario: fully implementing proactive intervention measures such as strengthening pollution prevention and control, refined management and control of water conservancy projects, and staggered scheduling of human activities; for each scenario, the risk probability changes, risk level rises and falls, and spatial diffusion of each zone at each stage are simulated, and the simulation results are presented in the form of a spatiotemporal matrix to generate a dynamic risk evolution map of each zone in the next 30 days. The map clearly marks the risk level, risk diffusion direction, and diffusion rate of each zone at different time points.

[0105] Step 5.4: Based on the dynamic risk evolution map, identify high-risk areas, risk diffusion paths, and key risk triggering factors, and generate river and lake health risk early warning information according to the preset early warning level standards. Specifically, this includes: First, analyzing the dynamic risk evolution map to identify high-risk areas. Zones where the risk level reaches extremely high risk at any stage within the next 30 days, or zones that maintain a high risk level for 15 consecutive days, are designated as high-risk areas. The specific spatial range, risk type, and duration of the risk in high-risk areas are clarified. Second, tracking the risk diffusion path. Based on the trajectory of the risk level spreading from high-risk areas to surrounding areas in the map, determine the main direction of diffusion, such as diffusion from the shallows in the center of the lake to the east and west banks, or diffusion from the upper reaches of the river to the lower reaches. Mark the zones and key nodes along the diffusion path, such as bridges, tributary confluences, and the time required for diffusion. If the risk level decreases or increases during diffusion, record the decrease magnitude and triggering factors simultaneously. Third, identifying key risk triggering factors. For high-risk areas and areas covered by diffusion paths, associate them with corresponding health status indicators and external environmental factors. If changes in a certain factor are directly correlated with an increase in risk level, such as a 20% increase in total phosphorus concentration raising the risk level from high to extremely high, or a doubling of the spread rate of cyanobacterial blooms after five consecutive days of high temperatures, then the factor is identified as a key risk triggering factor. The factor type is then clearly defined: water quality exceeding standards, meteorological, or human activity-related, along with specific values ​​or characteristics. River and lake health risk warning information is generated according to preset warning level standards. Preset warning levels correspond to risk levels: extremely high risk corresponds to Level 1, high risk to Level 2, medium risk to Level 3, and low risk to Level 4. The warning information includes core elements such as the specific name and spatial location of high-risk areas, risk type and warning level, risk duration, risk spread path description, a list of key risk triggering factors, and targeted response suggestions. For example, a Level 1 warning requires immediate activation of the cyanobacterial bloom emergency response plan and enhanced water quality monitoring; a Level 2 warning requires strengthened control of sewage discharge along the banks and advance clearing of flood channels. Ultimately, this results in structured and actionable river and lake health risk warning information.

[0106] In this embodiment of the invention, because it employs the technical means of extracting health status indicators, historical trends, and spatial distribution anomaly information from structured river and lake health status assessment results as initial input data for risk warning, inputting this data into a preset river and lake health risk warning model, calculating risk probability and initially delineating risk levels based on embedded risk evolution laws and multi-threshold judgment rules, and then combining external environmental forecast information and human activity impact data to conduct risk spatiotemporal evolution simulation and multi-scenario prediction analysis, and finally identifying high-risk areas, risk diffusion paths, and key risk triggering factors based on dynamic risk evolution maps and generating warning information according to preset standards, it effectively overcomes the technical problems of traditional river and lake health risk warning, such as single data support, lack of integration with historical trends and external influencing factors, lack of dynamic and multi-scenario considerations in prediction, and difficulty in accurately identifying key risk information. This results in the generation of accurate and dynamic river and lake health risk warning information, clearly presenting the risk evolution trend and core risk elements of each zone.

[0107] In a preferred embodiment of the present invention, step 6 above may include:

[0108] Step 6.1: Based on the river and lake health status assessment results and river and lake health risk early warning information, perform spatiotemporal alignment and information fusion to construct a comprehensive analysis dataset. Specifically, this includes: First, retrieving structured river and lake health status assessment results and river and lake health risk early warning information: The health status assessment results include the overall health level of the river and lake and each zone, corresponding scores, a list of major health problems, and a spatial distribution map of health levels; the risk early warning information includes the early warning level of each zone, the scope of high-risk areas, risk diffusion paths, key risk triggering factors, and a dynamic risk evolution map; the time dimension uses a unified time format as a benchmark, arranging the collection time of the health status assessment data and the prediction period of the risk early warning information into 7-day intervals. A unified conversion is performed in 15-day and 30-day segments to ensure accurate correspondence between health data and risk information within the same zone and time period. Spatial dimensions are based on the nationally unified geodetic coordinate system, converting all zone spatial coordinates in health assessments, boundary coordinates of high-risk areas in risk warnings, and spatial trajectory data of risk diffusion paths to this coordinate system. This eliminates inconsistencies in spatial reference standards and ensures precise spatial location matching. The aligned health status data and risk warning information are then linked and bound by zone. Each data entry includes core fields such as zone identifier, spatial coordinates, time node, health level, health score, main health problems, warning level, risk probability, risk type, and key triggering factors. Duplicate or closely related information is integrated; for example, the main health problems of water pollution in a certain zone are linked and merged with warning information on high-risk cyanobacterial blooms to supplement the risk evolution trend corresponding to that health problem. Conflicting information is prioritized, using health status indicators supported by real-time monitoring data and risk warning information supported by the latest environmental forecasts as the basis, eliminating outdated or contradictory data, and ultimately constructing a structured comprehensive analysis dataset.

[0109] Step 6.2: Based on the comprehensive analysis dataset, select preset evaluation indicators and weights from four dimensions: health level, risk status, construction progress, and sustainability. Calculate the multi-dimensional effectiveness score for the entire river and lake system and its various zones. Specifically, this includes: First, based on the comprehensive analysis dataset, clarify the specific indicators and weights for the four core evaluation dimensions: health level (0.35 weight), risk status (0.25 weight), construction progress (0.2 weight), and sustainability (0.2 weight), with a total weight of 1, ensuring the evaluation focuses on key aspects while providing comprehensive coverage. The evaluation also includes the corresponding scores for each zone's health level, the average values ​​of core health indicators (water quality, shoreline ecology, flood control safety standardization), and the percentage of completed health problem rectification. The indicators selected for the risk status dimension include the corresponding scores for warning levels, the percentage of high-risk areas, the estimated duration of risk, and the risk diffusion rate. The indicators selected for the construction progress dimension include the comparison with the same period of the previous year. The indicators for the health score improvement, the reduction in the number of health problems, the decrease in risk warning levels, and the completion rate of construction measures are considered. The sustainability dimension includes indicators such as the duration of stable health status, the long-term effectiveness score of ecological restoration measures, the completeness of the risk prevention and control system, and the percentage of continuously improving public satisfaction. Standardized calculations are performed for each dimension's indicators, mapping all indicator values ​​to a 0-100 score range: positive indicators, such as the improvement in health score and the completion rate of rectification, are linearly normalized, with higher values ​​resulting in higher scores; negative indicators, such as the proportion of high-risk areas and the rate of risk spread, are inversely linearly normalized, with lower values ​​resulting in higher scores. Subsequently, the standardized indicator scores are weighted and summed according to the weights of each dimension to obtain a multi-dimensional effectiveness score for each zone and the entire river and lake system. The health level score is calculated as ∑(standardized score of each indicator in this dimension × internal weight allocation of the indicator) × 0.35, with the final score accurate to 0.1 points.

[0110] Step 6.3: Based on the multi-dimensional performance scores, combined with the comparison of management objectives and historical performance, and after weighted integration and grade determination, the overall construction performance grade and comprehensive score of the river and lake as a whole and each sub-district are formed. Specifically, this includes: First, clarifying the preset management objectives and historical performance comparison standards. Management objectives include specific indicators such as water quality compliance rate, shoreline ecological restoration compliance rate, flood control safety compliance rate, and risk warning response timeliness rate ≥95%. Historical performance comparison selects multi-dimensional performance score data from the same period of the past three years to form a historical comparison baseline. The multi-dimensional performance scores of each sub-district and the river and lake as a whole are compared bidirectionally with the management objectives and historical baseline: If the score of a certain dimension reaches the score corresponding to the management objective, such as 85 points for water quality compliance rate, and is more than 10 points higher than the highest score in the same period in history, it is judged as excellent performance in that dimension; if the management objective is achieved but the score is lower, the performance is considered excellent. A score less than 5 points is considered good; a score more than 15 points higher than the same period in previous years but below the management target is considered progress; a score lower than the same period in previous years but below the management target is considered a weakness. The performance scores of the four dimensions of health level, risk situation, construction progress, and sustainability are weighted and summed again to obtain the comprehensive score: Comprehensive Score = Health Level Score × 0.35 + Risk Situation Score × 0.25 + Construction Progress Score × 0.2 + Sustainability Score × 0.2. A grade classification threshold is set: a comprehensive score of 80 to 100 is excellent, 60 to 79 is good, 40 to 59 is average, and below 40 is poor. The overall construction effectiveness level of the river and lake and each zone is determined based on the comprehensive score, and the contribution of each dimension score to the comprehensive score is recorded to identify the core dimensions affecting the effectiveness level.

[0111] Step 6.4: Based on the construction effectiveness level and comprehensive score, identify areas with outstanding achievements, weak links, and directions for improvement. Integrate key evaluation findings, major risk warnings, and targeted suggestions to obtain a river and lake construction effectiveness evaluation report. Specifically, this includes: First, identifying areas with outstanding achievements and weak links: Areas with outstanding achievements are those with a comprehensive score of excellent and at least two dimensions scoring ≥85 points. The report focuses on summarizing typical experiences in improving health status, risk prevention and control, and implementation of construction measures. For example, a certain area achieved a significant improvement in shoreline ecological indicators through the construction of ecological buffer zones, or reduced water pollution risks through precise sewage discharge control. Weak links are areas with a comprehensive score below 60 points, or a score below 40 points in a certain dimension. The report analyzes the reasons in depth using the comprehensive analysis dataset. For example, a certain area may have a low health level score due to persistently excessive total phosphorus concentration, or significant shortcomings in flood control safety due to untimely dike maintenance. Simultaneously, it links risk warning information to identify the high-risk types corresponding to the weak links, such as cyanobacterial blooms and flooding. The report outlines several key areas of improvement. Specifically, it addresses weaknesses in water quality control, proposing optimization of sewage discharge management plans, increased water quality monitoring frequency, and implementation of water purification projects. For deviations in shoreline ecological restoration, it proposes adjusting restoration plant species, expanding ecological buffer zones, and reducing the proportion of shoreline hardening. Regarding flood control shortcomings, it suggests reinforcing dikes, dredging flood channels, and optimizing flood warning response procedures. For insufficient risk prevention, it proposes improving the risk monitoring network, strengthening early warning information dissemination, and developing multi-scenario emergency response plans, ensuring the improvement directions are targeted and feasible. Key assessment findings include the overall effectiveness level of river and lake construction, the distribution patterns of effectiveness across different zones, the performance of core evaluation dimensions, and the gap between these dimensions and management objectives and historical achievements. Major risk warnings include a summary of high-risk areas across the entire region, a list of key risk triggering factors, and predictions of risk evolution trends. Targeted recommendations, combining successful experiences with the causes of weaknesses, propose specific measures by zone and dimension, clarifying responsible entities, implementation steps, and expected goals. The final result is a structured evaluation report on the effectiveness of river and lake construction. The report covers the overall effectiveness summary, details of regional effectiveness, case studies of outstanding areas, a list of weak links, directions for improvement and specific suggestions, and key tasks for risk prevention and control. It provides comprehensive and practical technical support for precise policy implementation, dynamic optimization and closed-loop management of river and lake construction.

[0112] In this embodiment of the invention, a comprehensive analysis dataset is constructed by spatiotemporally aligning and fusing the health status assessment results of rivers and lakes with risk warning information. Based on this dataset, preset evaluation indicators and weights are selected from four dimensions—health level, risk situation, construction progress, and sustainability—to calculate multi-dimensional effectiveness scores. Weighted integration and level determination are then performed by combining management objectives with historical performance comparisons. Finally, based on the construction effectiveness level and comprehensive score, outstanding areas, weak links, and improvement directions are identified, and key information is integrated to generate an evaluation report. Therefore, this approach effectively overcomes the technical problems of traditional river and lake construction effectiveness evaluations, such as lack of multi-dimensional systematic consideration, failure to achieve deep integration of assessment and warning information, neglect of management objectives and historical performance comparisons, and weak targeting of evaluation results that are difficult to support precise improvement decisions. This results in a comprehensive, objective, and structured river and lake construction effectiveness evaluation report, clearly defining the overall construction effectiveness level, core advantages, and improvement directions of rivers and lakes and their respective zones. This provides a scientific and practical decision-making basis for the dynamic optimization, precise policy implementation, and closed-loop management of river and lake construction.

[0113] like Figure 2 As shown, embodiments of the present invention also provide a river and lake construction effectiveness evaluation system, comprising:

[0114] The acquisition module is used to acquire monitoring data of rivers and lakes, including satellite remote sensing data, drone monitoring data, video surveillance data, and social network data.

[0115] The fitting module is used to construct a spatial coverage area in rivers and lakes by selecting hydrological monitoring stations, automatic water quality monitoring stations and shoreline fixed markers based on the spatial distribution characteristics of the detection data. The spatial coverage area is then spatially partitioned. By performing circular geometric fitting on key monitoring points in each partition, the spatial geometric reference benchmark of the partition is optimized. Based on the spatial distribution characteristics of each partition after optimization, a spatial correction factor is generated.

[0116] The correction module is used to fuse the detection data based on the detection data and the spatial correction factor, and to perform spatial correction on the fused data through the spatial correction factor to obtain an optimized dataset.

[0117] The assessment module is used to assess the health status of rivers and lakes based on the optimized dataset and the river and lake health diagnostic index model, and obtain the assessment results of the river and lake health status.

[0118] The early warning module is used to predict and analyze the health risks of rivers and lakes based on the assessment results of the health status of rivers and lakes, and obtain early warning information on the health risks of rivers and lakes.

[0119] The processing module is used to comprehensively evaluate the effectiveness of river and lake construction based on the assessment results of river and lake health status and the early warning information of river and lake health risks, and to obtain a river and lake construction effectiveness evaluation report.

[0120] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for evaluating the effectiveness of river and lake construction, characterized by, The method includes: Step 1: Obtain monitoring data for rivers and lakes. The monitoring data includes satellite remote sensing data, drone monitoring data, video surveillance data, and social network data. Step 2: Based on the spatial distribution characteristics of the detection data, select hydrological monitoring stations, automatic water quality monitoring stations, and fixed shoreline markers in rivers and lakes to construct spatial coverage areas. These areas are then spatially partitioned. By performing circular geometric fitting on key monitoring points within each partition, the spatial geometric reference benchmark for each partition is optimized. Based on the optimized spatial distribution characteristics of each partition, spatial correction factors are generated, including: Receive detection data and perform spatial coverage analysis based on the spatial distribution characteristics of the detection data to identify the density distribution characteristics of monitoring data and the distribution of spatial coverage blind spots within the river and lake area; Based on the density distribution characteristics of monitoring data and the distribution of spatial coverage blind spots, hydrological monitoring stations, automatic water quality monitoring stations, and fixed shoreline markers were selected as key reference points in the river and lake area to construct an initial spatial coverage area to cover the spatial coverage blind spots. Based on the initial spatial coverage area, combined with the geographical characteristics of rivers and lakes and monitoring needs, the initial spatial coverage area is spatially partitioned, dividing the river and lake area into multiple logical partitions with continuous spatial coverage characteristics. Based on each logical partition, circular geometric fitting is performed on the key monitoring points distributed within each partition to calculate the final geometric center position and coverage radius parameters of each partition. Based on the final geometric center location and coverage radius parameters of each partition, optimize the spatial geometric reference benchmark of each partition, and determine the precise spatial positioning parameters and spatial coverage of each partition; Based on the precise spatial positioning parameters and spatial coverage of each zone, the spatial distribution characteristics of each zone after optimization are analyzed, including zone area parameters, shape coefficient parameters and monitoring point density parameters, and the corresponding spatial correction factors are obtained. Step 3: Based on the detection data and the spatial correction factor, the detection data is fused, and the fused data is spatially corrected using the spatial correction factor to obtain an optimized dataset; Step 4: Based on the optimized dataset, assess the health status of rivers and lakes using the river and lake health diagnostic index model to obtain the assessment results of river and lake health status. Step 5: Based on the assessment results of river and lake health status, predict and analyze the health risks of rivers and lakes through a risk warning model to obtain river and lake health risk warning information; Step 6: Based on the assessment results of river and lake health status and the early warning information of river and lake health risks, conduct a comprehensive evaluation of the effectiveness of river and lake construction and obtain a river and lake construction effectiveness evaluation report.

2. The method according to claim 1, characterized in that, Based on each logical partition, circular geometric fitting is performed on the key monitoring points distributed within each partition to calculate the final geometric center position and coverage radius parameters of each partition, including: Based on the precise spatial coordinate data of the key monitoring points distributed within each logical partition, the set of spatial coordinates of the key monitoring points in each partition is obtained; based on the set of spatial coordinates of the key monitoring points, the spatial distance relationship matrix between all key monitoring points in each partition is calculated, and the spatial distribution density characteristics of each monitoring point are identified. By using the spatial distance relationship matrix and spatial distribution density characteristics, initial circular geometry fitting is performed on the key monitoring points in each partition to determine the candidate positions of the initial geometric center of each partition; using the candidate positions of the initial geometric center, the radial distance from all key monitoring points in each partition to the initial geometric center is calculated, and the statistical distribution characteristics of the radial distance are analyzed. Based on the statistical distribution characteristics of radial distance, the optimized geometric center position is obtained by iteratively correcting the initial candidate geometric center position. Based on the optimized geometric center position, the distance from each key monitoring point to the optimized geometric center is recalculated, and the maximum distance value is determined as the initial coverage radius parameter. Based on the initial coverage radius parameter, the coverage integrity of the circular geometric fit for key monitoring points in each partition is evaluated. When the coverage integrity does not meet the preset threshold, the optimized geometric center position and coverage radius parameter are adjusted to obtain the final geometric center position and coverage radius parameter.

3. The method according to claim 2, wherein Based on the detection data and spatial correction factor, the detection data is fused, and the fused data is spatially corrected using the spatial correction factor to obtain an optimized dataset, including: Based on the detection data and spatial correction factor, the detection data of each partition is spatially normalized to obtain the preliminary fused dataset of each partition; based on the preliminary fused dataset, combined with the partition area parameter, shape coefficient parameter and monitoring point density parameter in the spatial correction factor, the data of each partition is spatially weighted and fused to obtain an aligned dataset with a unified spatial benchmark. By combining the aligned dataset with the precise spatial positioning parameters and coverage of each partition, spatial interpolation and smoothing are performed to obtain a smooth dataset that eliminates the discontinuity of partition boundaries. By applying a spatial correction factor to the smooth dataset and performing spatial coordinate transformation and correction, sub-datasets of river and lake health monitoring for each partition with a consistent spatial reference system are obtained. The sub-datasets of river and lake health monitoring in each region were integrated to form an optimized dataset.

4. The method according to claim 3, characterized in that, Based on the optimized dataset, the health status of rivers and lakes is assessed using a river and lake health diagnostic index model, yielding the following assessment results: Based on the optimized dataset, multi-dimensional monitoring indicator data related to river and lake health diagnosis are extracted to form a health diagnosis input data set; The health diagnosis input data set is input into the preset river and lake health diagnosis index model. According to the built-in index weight system and health level classification rules of the model, the indicators are standardized and mapped to health scores to generate preliminary health status scores for each zone. Based on the preliminary health status score, and combined with the spatial attributes of each zone and the completeness of the monitoring data, the score is corrected for spatial consistency and weighted for reliability to obtain the corrected health status score for each zone. Based on the corrected health status score, and following an evaluation strategy that combines overall and regional assessments of rivers and lakes, the health status level is determined and the spatial distribution characteristics are analyzed to obtain structured river and lake health status assessment results, including overall health level, regional health level distribution, and identification information of major health problems.

5. The method according to claim 4, wherein Based on the assessment results of river and lake health status, a risk early warning model is used to predict and analyze river and lake health risks, resulting in early warning information on river and lake health risks, including: By extracting health status indicators, historical trends and spatial distribution anomalies related to risk warning from the structured river and lake health status assessment results, the initial input data for risk warning is obtained. The initial input data for risk warning is input into the preset river and lake health risk warning model. Based on the risk evolution law and multi-threshold judgment rules embedded in the model, the risk probability of each zone is calculated and the risk level is initially determined. Based on risk probability and preliminary risk level, combined with external environmental forecast information and human activity impact data, risk spatiotemporal evolution simulation and multi-scenario prediction analysis are carried out to obtain dynamic risk evolution maps of each region in the future. Based on the dynamic risk evolution map, high-risk areas, risk diffusion paths and key risk triggering factors are identified, and river and lake health risk warning information is generated according to the preset warning level standards.

6. The method according to claim 5, wherein Based on the assessment results of river and lake health status and the early warning information of river and lake health risks, a comprehensive evaluation of the effectiveness of river and lake construction is conducted, resulting in a river and lake construction effectiveness evaluation report, including: Based on the results of the river and lake health status assessment and the river and lake health risk early warning information, a comprehensive analysis dataset is constructed by spatiotemporal alignment and information fusion. Based on the comprehensive analysis dataset, from four dimensions—health level, risk status, construction progress, and sustainability—pre-set evaluation indicators and weights are selected to calculate the multi-dimensional effectiveness scores of the river and lake as a whole and its various sub-districts, resulting in multi-dimensional effectiveness scores. Based on multi-dimensional performance scoring, combined with management objectives and historical performance comparison, and weighted integration and rating determination, the overall construction performance rating and comprehensive score of the river and lake as a whole and each zone are formed. Based on the construction effectiveness level and comprehensive score, areas with outstanding achievements, weak links and directions for improvement are identified, and key evaluation findings, major risk warnings and targeted suggestions are integrated to obtain a river and lake construction effectiveness evaluation report.

7. A river and lake construction effectiveness evaluation system, wherein the system implements the method as described in any one of claims 1 to 6, characterized in that, include: The acquisition module is used to acquire monitoring data of rivers and lakes, including satellite remote sensing data, drone monitoring data, video surveillance data, and social network data. The fitting module is used to construct a spatial coverage area in rivers and lakes by selecting hydrological monitoring stations, automatic water quality monitoring stations and shoreline fixed markers based on the spatial distribution characteristics of the detection data. The spatial coverage area is then spatially partitioned. By performing circular geometric fitting on key monitoring points in each partition, the spatial geometric reference benchmark of the partition is optimized. Based on the spatial distribution characteristics of each partition after optimization, a spatial correction factor is generated. The correction module is used to fuse the detection data based on the detection data and the spatial correction factor, and to perform spatial correction on the fused data through the spatial correction factor to obtain an optimized dataset. The assessment module is used to assess the health status of rivers and lakes based on the optimized dataset and the river and lake health diagnostic index model, and obtain the assessment results of the river and lake health status. The early warning module is used to predict and analyze the health risks of rivers and lakes based on the assessment results of the health status of rivers and lakes, and obtain early warning information on the health risks of rivers and lakes. The processing module is used to comprehensively evaluate the effectiveness of river and lake construction based on the assessment results of river and lake health status and the early warning information of river and lake health risks, and to obtain an evaluation report on the effectiveness of river and lake construction.

8. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method as described in any one of claims 1 to 6.

Images