Intelligent river channel non-point source pollution load determination method based on GIS vector diagram conversion

Abstract

The invention relates to the technical field of source pollution load determination, in particular to an intelligent river channel non-point source pollution load determination method based on GIS (Geographic Information System) vector diagram conversion, which comprises the following steps of: obtaining water area shoreline data of rivers and lakes through GIS vector conversion; water environment treatment data, water pollution prevention and control data, water ecological restoration data, water administration law enforcement supervision data and video monitoring data are collected, and a basic data information base is constructed; the method comprises the following steps: dividing a pollution area into a plurality of subareas, and preliminarily positioning the subareas where pollution sources are located by using different data; reliability scores based on different data positioning modes are calculated, a pollution source positioning comprehensive score formula is constructed, and comprehensive reliability scores of different partitions are calculated; and the information push management module pushes the partition position with the highest comprehensive reliability score to related personnel, determines the final position of the pollution source, and calculates the total pollution load according to the type of the pollution source. According to the scheme, multiple modes are integrated to position the pollution source, the positioning accuracy is improved, and the source pollution load accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of source pollution load determination, and in particular to a method for determining river surface source pollution load based on GIS vector map conversion. Background Art

[0002] In river pollution control, accurately determining the source pollution load is the core of formulating effective control strategies. However, existing technologies have large deviations in determining the source pollution load due to inaccurate positioning of pollution sources.

[0003] In the early days, the location of pollution sources was determined based on human experience, which was highly subjective and arbitrary, with low accuracy. The pollution load determined on this basis lacked scientificity, resulting in waste of governance resources and poor governance effects.

[0004] Despite the advancements in technology, positioning methods based on single data sets have found applications, but they face significant challenges. During data collection, river and lake shoreline data are often not updated in a timely manner, and new land use changes cannot be promptly reflected. This impacts the identification of potential pollution sources, leading to biased calculations of source pollution loads and inappropriate resource allocation. Water quality monitoring data is also not ideal, with uneven distribution of stations and long monitoring intervals, making it difficult to capture sudden pollution outbreaks. Furthermore, delayed and missed location of pollution sources results in pollution load calculations that fail to reflect actual pollution levels.

[0005] At the analytical method level, the single data positioning model is simple, and the pollution source is judged only based on the water quality pollution index. It cannot comprehensively consider multiple factors and is difficult to accurately locate in complex pollution situations. As a result, the source pollution load cannot be determined by fully considering the contribution of each pollution source, and the governance strategy does not match the actual pollution.

[0006] Single technologies such as water ecological restoration, water administration law enforcement supervision, and video surveillance also have flaws. Biodiversity indicators are subject to interference from natural variations, making it difficult to accurately locate pollution sources and impacting source pollution load assessments. Water administration law enforcement supervision data lags behind, making it impossible to track changes in pollution sources, and the determination of source pollution loads lacks timeliness. Video surveillance is easily affected by environmental factors and its recognition capabilities are unstable, leading to inaccurate determination of source pollution loads. These issues lead to inaccurate determination of source pollution loads, a lack of targeted governance efforts, irrational resource allocation, and significant waste. Therefore, innovative integrated positioning technologies are urgently needed to address the shortcomings of traditional methods in locating pollution sources, improve the accuracy of source pollution load determination, and promote scientific and efficient river pollution control. Summary of the Invention

[0007] The present invention combines multiple positioning methods to improve the accuracy and efficiency of pollution source positioning, thereby improving the accuracy of source pollution load determination.

[0008] The technical solution proposed by the present invention is: a method for determining the non-point source pollution load of a smart river based on GIS vector map conversion, the method comprising: Obtain river and lake shoreline data through GIS vector conversion, and collect water environment management data, water pollution prevention and control data, water ecological restoration data, water administration law enforcement supervision data, and video surveillance data to build a basic data information database; Divide the polluted area into several zones, and use river and lake shoreline data, water environment management data, water pollution prevention and control data, water ecological restoration data, water administration law enforcement supervision data, and video surveillance data to preliminarily locate the zones where the pollution sources are located; Calculate the reliability scores based on different data positioning methods, determine the reliability weights of different positioning methods through the entropy weight method, construct the comprehensive score formula for pollution source positioning, and calculate the comprehensive reliability scores of different partitions; The information push management module pushes the location of the partition with the highest comprehensive reliability score to relevant personnel, who then conduct inspections in the partition to determine the final location and type of the pollution source and calculate the total pollution load based on the pollution source type. Verification monitoring points are set up in each partition, and the concentration error is calculated using model verification and optimization technology. When the error exceeds the threshold, parameter adjustment and weight optimization are performed.

[0009] Preferably, the river and lake shoreline data is obtained as follows: Store and process river and lake maps through scanners and computers; determine the proportional relationship between river and lake scans and GIS vector images, convert raster data into vector data, and store vector data; convert vector data into raster data.

[0010] Preferably, the basic data information database construction process is as follows: Arrange water quality monitoring stations to collect routine water quality indicators, as well as meteorological and surrounding pollution source information; collect water pollution prevention and control data according to the type of pollution source, and build a water pollution prevention and control database; monitor changes in water quality and water volume before and after the implementation of water ecological restoration projects, as well as the restoration of ecological functions at key ecological nodes; law enforcement personnel monitor the overall condition of the river in real time, and the public uploads photos, videos and related information of pollution problems found; install different types of high-definition cameras at key locations around rivers and lakes to collect video data; integrate the above data to build a basic data information database.

[0011] Preferably, the specific process of the preliminary positioning is as follows: Divide the polluted area into The buffer zones were constructed through GIS buffer analysis technology, the pollution-related attribute values ​​were determined using the spatial difference algorithm, the location of potential pollution sources was judged, and a scoring formula for river and lake shoreline factors was constructed to calculate the scores; the water quality pollution index method was used to calculate the comprehensive pollution index, and a scoring formula for water environment factors was set, and the scores were calculated based on the comparison results between the comprehensive pollution index and the set threshold value; the type and location of pollution sources were determined through material balance technology and actual removal amount, and the QUAL2K model was used to predict water quality change trends and pollution source development dynamics, and a scoring formula for water pollution prevention and control factors was constructed to calculate the scores.

[0012] Preferably, the specific process of the preliminary positioning further includes: The Shannon-Wiener Index is used to measure regional biodiversity, and the water ecological restoration factor scoring formula is constructed based on the vegetation coverage rate and the presence or absence of specific sensitive species. The pollution frequency index is calculated using data statistical analysis technology. Video image analysis technology is used to count the number of frames of suspected pollution sources and the number of frames of actual confirmed pollution sources, calculate the recognition accuracy, and perform weighted calculations based on equipment performance parameters and installation conditions to obtain the video surveillance credibility coefficient.

[0013] Preferably, the specific formula for the pollution source location comprehensive score formula is as follows: ; in: 、 、 、 、 、 、 are the weights corresponding to each factor, and their value range is [0,1]. Score the shoreline factors of rivers and lakes. Score the water environment governance factor. Water pollution prevention and control factor score, Score the water ecological restoration factor. is the pollution frequency index, For recognition accuracy, is the video surveillance credibility coefficient.

[0014] Preferably, the specific calculation process of the total pollution load is as follows: The daily emission load of the pollutant from the enterprise is calculated based on the pollutant concentration and wastewater discharge volume of the enterprise. The daily pollution load of the agricultural pollutant is calculated based on the crop varieties, area, fertilizer and pesticide usage and frequency collected from the farmland survey, combined with the water quality monitoring data of farmland irrigation water and drainage. The daily pollution load of the pollutant from domestic pollution sources is calculated based on the urban population, domestic sewage generation, sewage treatment plant treatment capacity and operating conditions. The total pollution load calculation formula is as follows: ; in: is the total pollution load, is the daily emission load of the pollutant of the enterprise; The daily pollution load of the pollutant in agriculture; is the daily pollution load of the pollutant from domestic pollution sources, For the Enterprises.

[0015] Preferably, the specific process of parameter adjustment and weight optimization is as follows: Multiple verification monitoring points are set up in each zone to collect actual pollutant concentrations regularly; the actual pollutant concentrations collected are compared with the calculated pollutant concentrations, and the concentration error rate is calculated; an error threshold is set. If the concentration error rate is greater than the error threshold, the parameters are adjusted. Using feedback data, the hierarchical analysis method is used to re-determine the weights of each factor. If special influencing factors are found in some areas that are not included in the model, the corresponding influencing factors and calculation formulas are added to improve the model.

[0016] Preferably, the push process of the information push management module is as follows: Information is classified and organized according to message type, and different push channels or multiple channels are used simultaneously according to the urgency and nature of different messages; relevant personnel set the message receiving preference priority according to needs, and the information push management module automatically pushes important information according to priority.

[0017] The present invention also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the method for determining the surface source pollution load of a smart river channel based on GIS vector map conversion.

[0018] Beneficial effects of the present invention: Pollution source location is determined by comprehensively utilizing information from various sources, including river and lake shorelines and water environment management. River and lake shorelines, combined with land use and human activity intensity, identify potential pollution areas. Water quality monitoring data clarifies the extent of pollution. Multi-source data complement each other, overcoming the limitations of single-source location and enabling precise location of pollution sources. This provides an accurate basis for determining source pollution loads and avoids load calculation errors caused by source location errors. Precise location allows accurate determination of the location and type of each pollution source, making subsequent pollution load calculations based on this data more accurate and aligning with actual conditions, thereby improving the accuracy of source pollution load determination.

[0019] Multiple algorithms and models are used for location calculations, such as spatial difference algorithms and water pollution index methods, to assess the likelihood of pollution sources from different dimensions. Standardization and the entropy weighting method are used to determine the weights of various factors and construct a comprehensive scoring formula. This multi-algorithm fusion and scientific weighting method enhances location reliability and provides a reliable basis for determining source pollution loads. Accurate pollution source location enables pollution load calculations to comprehensively consider the contributions of each pollution source, ensuring the reliability of source pollution load calculations and enabling more rational allocation of remediation resources.

[0020] The positioning system integrates real-time monitoring data to achieve dynamic positioning. As the environment changes, and the location and intensity of pollution sources shift, the system captures these changes in real time. When the comprehensive score is abnormal or an area enters a high-risk level, it automatically issues an alert and notifies relevant departments. This not only effectively curbs the spread of pollution but also allows for more timely determination of source pollution loads. As pollution sources dynamically change, the system can promptly adjust positioning results, allowing source pollution loads to be adjusted to reflect actual conditions. Relevant departments can then quickly adjust their control strategies, improve control efficiency, and minimize the impact of pollution on river ecosystems. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flow chart of a method for determining non-point source pollution load of a smart river channel based on GIS vector map conversion according to the present invention; Figure 2 This is a pollution source location flowchart of a method for determining river non-point source pollution load based on GIS vector map conversion in the present invention. DETAILED DESCRIPTION

[0022] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are for illustrative purposes only, and those skilled in the art will readily appreciate other obvious variations. The basic principles of the present invention defined in the following description may be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the present invention.

[0023] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the elements may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0024] like Figure 1 and Figure 2As shown, this solution builds a basic data database by collecting information on existing river and lake shorelines, water environment management, water pollution prevention and control, water ecological restoration, water administration law enforcement supervision, and video surveillance. A specific area near the detected pollutant is designated as a polluted zone (this can be determined based on the type of pollutant detected). The entire polluted area is then divided into several sub-zones. The pollution source is located using the information collected through these different methods, obtaining a precise location for each method. The reliability of each method is then calculated, and the sub-zone in which the pollutant is most likely located is determined based on these reliability scores. Finally, a manual investigation is conducted within the area to determine the specific type and location of the pollution source. Based on this specific type and location, the source pollution load for the entire polluted area is determined. This integrated location method reduces the influence of other factors on a single location method, effectively improving the accuracy of pollution source location and, consequently, the accuracy of source pollution load calculation.

[0025] When using river and lake shoreline information for positioning, obtaining shoreline data in some areas is difficult, especially in remote areas or those with complex terrain. It's difficult to fully and accurately obtain detailed information about the shoreline, such as land use types and human activities. This can lead to incomplete identification of potential pollution sources. The shoreline conditions of rivers and lakes change over time, due to factors such as riverbank erosion and siltation, and development and construction in surrounding areas. If data is not updated promptly, the impact of these changes on pollution sources will not be reflected in a timely manner, potentially leading to inaccurate identification of pollution sources. Relying solely on shoreline information for pollution source identification often only allows for preliminary assessments, lacking in-depth analysis of the pollution source's generation mechanisms, migration patterns, and transformation patterns, making it difficult to accurately assess the specific impact of pollution sources on water bodies.

[0026] When targeting pollution sources using water pollution prevention and control information, measures are typically formulated based on known pollution source types and characteristics. However, for some new pollution sources or complex pollution situations, it can be difficult to accurately determine their type and source. For example, emerging industrial production processes or the use of new pesticides and fertilizers may generate unknown pollutants, making it difficult to effectively identify them using existing prevention and control information. Even if the type of pollution source is known, pollutant emission patterns may vary from one enterprise to another, influenced by factors such as production processes, production scale, and environmental protection measures. Without an accurate understanding of these emission patterns, it is difficult to monitor and identify pollution sources at the appropriate time and location, potentially leading to missed or misidentified pollution sources. Over time, pollution source emissions may change, due to improvements in enterprise production processes or the strengthening or weakening of environmental protection measures. Without a dynamic update mechanism for water pollution prevention and control information, these changes cannot be reflected in a timely manner, thus affecting the accuracy of pollution source identification.

[0027] When using water restoration information for location analysis, the relationship between ecological changes and pollution sources is not a simple one-to-one correspondence, as aquatic ecosystems are complex entities. Ecological changes observed during water restoration may result from the combined effects of multiple factors and cannot necessarily be directly and accurately traced to specific pollution sources. For example, eutrophication of water bodies may be caused by a combination of factors, including agricultural non-point source pollution, domestic sewage discharge, and natural factors, making it difficult to accurately identify the primary pollution source. The evaluation of water restoration effectiveness is subject to uncertainty, and different assessment methods and indicators may yield different results. This makes it difficult to accurately determine whether pollution sources are being effectively controlled or treated, or whether other potential pollution sources exist, when using water restoration information to identify pollution sources. Water restoration is a long-term process that requires continuous monitoring data to evaluate its effectiveness and identify pollution sources. However, many regions currently lack sufficiently long-term monitoring data, making it difficult to accurately grasp long-term changes and trends in pollution sources, increasing the difficulty of identifying pollution sources.

[0028] When using water environment management information for location analysis, historical data may be incomplete or missing. This can hinder accurate analysis of water pollution status and trends, making it difficult to accurately identify pollution sources. For example, earlier water quality monitoring data in some areas may not be effectively preserved due to equipment failures, personnel changes, and other factors. The implementation of water environment management measures may have certain impacts on the water quality and ecological environment of water bodies, thereby interfering with the identification of pollution sources. For example, river dredging and ecological restoration projects may change the physical and chemical properties of water bodies, altering the original pollution characteristics and increasing the difficulty of identifying pollution sources. Water environment management involves multiple data and indicators, such as water quality indicators, water volume changes, and ecological indicators. These data are interconnected and complex, making it challenging to accurately interpret these data and transform them into effective information for identifying pollution sources. Different professionals may interpret them differently, leading to uncertainty in identification results.

[0029] When using water administration law enforcement and supervision information for location tracking, due to the limited resources and capacity of water administration law enforcement and supervision, it is difficult to conduct comprehensive, real-time oversight of all rivers, lakes, and pollution sources. Some remote areas, small businesses, or hidden pollution sources may not be inspected and discovered promptly, resulting in the unidentified sources of some pollution. Information sharing between water administration law enforcement and supervision departments and other relevant departments may be delayed or insufficient. For example, pollution problems discovered by environmental protection departments may not be promptly communicated to water administration law enforcement departments, resulting in delays in the identification and treatment of pollution sources. Water administration law enforcement standards may vary from region to region, which may lead to inconsistent results in the identification and treatment of pollution sources. Some regions may impose lighter penalties for certain polluting behaviors, which may encourage businesses or individuals to take chances and continue to discharge pollutants illegally, making the identification of pollution sources more difficult.

[0030] When using video surveillance information for location analysis, its effectiveness can be affected by environmental factors such as weather, lighting, and water turbidity. For example, in adverse weather conditions such as heavy rain or fog, camera image quality degrades, making it difficult to clearly identify pollution sources. Turbid water can also hinder the observation and identification of pollutants in the water. Video surveillance generates massive amounts of data, and effectively storing, managing, and analyzing this data presents a challenge. Current technologies may not be able to quickly and accurately extract useful information from massive amounts of video data and identify pollution sources, resulting in low information utilization. Most video surveillance systems rely primarily on manual observation to identify pollution sources and lack intelligent recognition algorithms and models. Manual recognition is not only inefficient but also prone to subjective errors, making it difficult to ensure the accuracy and consistency of identification results.

[0031] Therefore, by comprehensively considering the above methods for positioning, the impact of each defect can be effectively reduced, thereby improving the final positioning accuracy and the accuracy of the final calculation results when determining the source of pollution.

[0032] When constructing a buffer zone based on the shorelines of rivers and lakes using GIS buffer analysis technology, basic data such as the geographic coordinates of the shoreline are obtained through GIS vector graphics conversion. Scanners and computers are used to store and process river and lake maps and other information, and the scanned river and lake map information (raster data) is converted into vector data. Assuming that the river and lake management area is defined as a polygon consisting of N edges connected by multiple inflection points, this polygon can be further subdivided into N-2 triangles. Using the proportional relationship between the area and side length of similar triangles, the proportional relationship between the scanned river and lake map and the GIS vector graphics can be determined as: .in, Represents the ratio of the side lengths of two similar polygons; 、 Represents the area of ​​two similar polygons. In the actual process of determining the location of potential pollution sources, for example, when analyzing a certain area ( =1,2, , ), for the obtained land use type code and quantified values ​​of human activity intensity When analyzing and processing multi-faceted information such as remote sensing, cameras, sensors, and their networks, the direct application of vector data is complex. Therefore, vector data must be converted to raster data to facilitate computational processing such as intersection and overlay analysis. This conversion allows for more accurate information integration and assists in determining the location of potential pollution sources. When determining pollution-related attribute values ​​using spatial interpolation algorithms, the converted vector data can more accurately determine the location of sample points and the distance between the estimated point and the sample point.

[0033] Water quality monitoring stations are strategically located across rivers, lakes, and reservoirs, taking into account flow characteristics, pollution source distribution, and water function. These stations cover key locations, including the upper, middle, and lower reaches of rivers, the various functional zones of lakes, and water inlets and outlets. Advanced equipment, including multi-parameter water quality monitors and automatic samplers, monitors frequently for common indicators such as water temperature, pH, dissolved oxygen, chemical oxygen demand (COD), ammonia nitrogen, total phosphorus, and total nitrogen, as well as specific indicators such as heavy metals and organic pollutants. Some stations implement real-time online monitoring to ensure timely monitoring of water quality changes. In addition to water quality indicators, meteorological data, including temperature, precipitation, wind speed and direction, is also collected simultaneously, along with information on surrounding pollution sources, such as the location, volume, and types of pollutants emitted by industrial discharge outlets. Wireless transmission technology transmits this data in real time to a data center, where it is visualized and analyzed using a geographic information system (GIS). This allows for the timely detection of water quality anomalies and provides a scientific basis for decision-making in water environmental management.

[0034] A multi-dimensional data collection approach is employed for water pollution prevention and control. For industrial pollution sources, in-depth investigations are conducted within enterprises to collect detailed information on production processes, raw material usage, and equipment operation. Automatic monitoring equipment installed at discharge outlets provides real-time data on wastewater discharge volume and major pollutant concentrations. This data is then connected to the environmental protection department's monitoring system to ensure data accuracy and timeliness. For agricultural pollution sources, extensive farmland surveys are conducted to collect information on crop varieties, planted area, fertilizer and pesticide usage, and frequency of use. The quality of irrigation and drainage water is also monitored. For domestic pollution sources, collaboration is conducted with municipal authorities and sewage treatment plants to obtain data on urban population, domestic sewage generation, and sewage treatment plant treatment capacity and operational status. Furthermore, drones equipped with high-resolution imaging equipment and spectrometers are used to rapidly inspect large areas of water, identifying the location and extent of suspected pollution sources. By integrating data from multiple sources, a comprehensive water pollution prevention and control database is constructed, providing strong support for analyzing pollution sources and evaluating prevention and control effectiveness.

[0035] To comprehensively evaluate the effectiveness of water ecological restoration, a comprehensive monitoring approach is used for data collection. Regarding biodiversity, a combination of sampling, line transecting, and drone monitoring is used to regularly survey the species, abundance, and distribution of plants and animals in different ecological zones. DNA barcoding technology and a biodiversity monitoring system are used to accurately identify species and establish a database on species dynamics. For aquatic organisms, water samples are collected for analysis of plankton and benthic organisms to assess the health of the aquatic ecosystem. Regarding ecosystem structure and function, remote sensing technology and geographic information systems (GIS) are used to obtain information on vegetation cover and wetland area. Combined with field measurements of soil texture and nutrient content, the ecosystem's material cycles and energy flows are analyzed. Furthermore, changes in water quality and quantity before and after the implementation of water ecological restoration projects are monitored, as well as the restoration of ecological functions at key ecological nodes, such as the connectivity of river ecological corridors and the purification capacity of wetlands. This provides data support for optimizing water ecological restoration plans.

[0036] Law enforcement officers conduct aerial inspections of rivers using drones equipped with advanced equipment such as high-definition cameras, infrared sensors, and spectrometers, providing real-time monitoring of overall river conditions. All data collected by law enforcement officers, including inspection records and reported incidents, is first aggregated into a dedicated data management system. Within this system, data cleaning algorithms are used to deduplicate and correct errors to ensure data accuracy and completeness. Data analysis tools are used to deeply mine water administration law enforcement and supervision data. For example, by analyzing the frequency and distribution of pollution incidents in different regions, pollution hotspot maps are created to visually visualize high-incidence areas. Time series data is analyzed to identify patterns in pollution incidents, such as seasonal trends. These analytical results will provide a scientific basis for developing targeted law enforcement strategies. A public participation mechanism has been established to encourage public participation in the collection of water administration law enforcement and supervision data through mobile applications, online platforms, and other channels. The public can upload photos, videos, and related information about pollution issues they discover, which will be reviewed and included in the water administration law enforcement and supervision database. Furthermore, timely feedback on law enforcement results is provided to the public to enhance public trust and support for water administration law enforcement and foster a positive atmosphere for shared participation in river management.

[0037] Based on the geographical environment, flow characteristics, and distribution of key regulatory areas, different types of high-definition cameras, including fixed cameras, pan-tilt cameras, and panoramic cameras, are strategically installed at key locations around rivers and lakes, such as major sewage outlets, areas prone to pollution, and near water conservancy facilities. Each camera is configured with an appropriate resolution, frame rate, and shooting angle based on monitoring requirements to ensure comprehensive coverage and clear images. Geographic Information System (GIS) technology is used to accurately locate and annotate cameras for rapid subsequent query and management. Cameras continuously collect video data at set intervals or event triggers. This collected video data is transmitted in real time to a data center via a wired network (such as fiber optic) or a wireless network (such as 4G / 5G). During transmission, efficient video encoding technologies (such as H.265) are used to compress data, reducing data volume and improving transmission efficiency, ensuring the real-time and smooth delivery of video data. Furthermore, a data backup mechanism is established to offsitely back up important video data to prevent data loss. In the data center, large-capacity storage devices (such as disk arrays) are used for long-term storage of video data. Distributed storage technology is employed to improve the reliability and scalability of data storage. A comprehensive video data management system has been established to categorize and store video data, indexing it by time, location, and surveillance area, enabling users to quickly query and retrieve historical video footage. Strict access rights are set to ensure data security and confidentiality. Advanced video intelligent analysis algorithms are used to analyze collected video data in real time. Object detection algorithms identify floating objects, vessels, and people in the water, and track and analyze their behavior. Image recognition technology is used to determine whether pollution incidents, such as sewage discharge and garbage dumping, are occurring, and timely alerts are issued. Through deep learning of video data, intelligent analysis models are continuously optimized to improve the accuracy and timeliness of event detection. Video surveillance data is integrated with other monitoring data (such as water quality and water level data) for analysis, providing a more comprehensive basis for decision-making in river management. For example, when video surveillance detects an anomaly in a specific area, it is combined with water quality monitoring data to determine whether it has impacted the water environment. Furthermore, video surveillance data is applied to business scenarios such as law enforcement supervision and emergency management. Through video playback and evidence extraction, it provides strong support for water administration law enforcement, improving emergency response speed and efficiency.

[0038] In order to accurately locate the pollution source, the entire area is first divided into regions. A small area, denoted as The following is a detailed process of locating pollution sources based on multiple factors: Preliminary location of pollution sources based on river and lake shoreline data: With the help of GIS buffer analysis technology, a buffer zone is constructed based on the river and lake shoreline to determine the potentially affected areas. At the same time, its powerful spatial analysis function is used to integrate geographic data such as land use type codes and quantitative values ​​of human activity intensity to assist in determining the location of potential pollution sources. For example, when determining the buffer zone range, an appropriate buffer distance is set based on the geographic coordinates of the shoreline, and the land use type and human activity intensity within the range are analyzed to identify potential pollution areas. For each sub-area ( =1,2, , ), get the land use type code (such as arable land , industrial land etc.) and quantitative values ​​of human activity intensity (Value range [0,10]). Determine the pollution-related attribute values ​​through a spatial difference algorithm (such as the inverse distance weighted interpolation method), and use this algorithm to calculate the pollution-related attribute values ​​in the region. According to the attribute values ​​of the known sample points and the distance between the estimated point and the sample point, the pollution attribute value of the estimated point is calculated through the formula, thereby determining the pollution distribution in the region and providing data support for the location of the pollution source. For example, in the calculation process, based on the pollution data and distance information of different sample points, the pollution concentration and other attribute values ​​of the unknown point can be accurately calculated. Suppose the estimated point In the area The calculation formula of its pollution attribute value is: ; in: It is a region Estimated points Pollution attribute values ​​(such as pollution concentration and other data used to determine pollution sources); It is a region Known sample points Attribute value of Is the point to be estimated to the area Known sample points distance; It is a region The number of known sample points in the is the weight coefficient, usually set to 2 (the value range is generally between 1-3). Based on this, the scoring formula for the river and lake shoreline factor is set as: ; in: The number of pollution assessment indicators related to river and lake shorelines (e.g., indicators related to land use types, human activity intensity, etc.); For the region Middle The weight of each indicator is determined according to the importance of the indicator to the pollution source judgment, and the value range is between [0,1]. ; The area after normalization Middle The value range is [0,1]. The larger the value, the higher the potential pollution possibility reflected by the indicator.

[0039] Preliminary location of pollution sources based on water environment management data: Based on water quality testing technology, a variety of water quality monitoring methods are used to obtain the measured concentration data of pollutants at different locations in the region. These data are the basis for subsequent analysis. By monitoring various pollutant indicators in the water body, the water environment quality status can be intuitively reflected. For example, professional water quality monitoring instruments are used to regularly collect water samples for analysis to obtain pollutant concentration data such as chemical oxygen demand and ammonia nitrogen. In each area The water pollution index method is used to determine the pollution situation. Based on the water quality monitoring data, the water pollution index method is used to calculate the comprehensive pollution index. By comparing the measured concentration with the evaluation standard, it is determined whether the area is polluted, and the degree of pollution is judged based on the size of the pollution index, thereby providing a basis for locating the pollution source. In the calculation process, the measured concentration of various pollutants is substituted into the formula to obtain the comprehensive pollution index, which is used to evaluate the regional pollution situation. The calculation formula for the comprehensive pollution index is: ; in: For the region Comprehensive pollution index; is the number of evaluation indicators; For the region Neidi Measured concentrations of pollutants; For the region Neidi The evaluation criteria for pollutants. The value exceeds a certain threshold (set as ,like =1, which can be adjusted according to local water quality standards and actual conditions), it indicates that the area is polluted. The scoring formula for water environment governance factors is set as: ; Based on water pollution prevention and control data, the pollution source is initially located: Taking the biological treatment method for organic pollution as an example, the theoretical removal amount is calculated based on the principle and design parameters of the biological treatment method through material balance technology, and compared with the actual removal amount obtained by actual monitoring to determine the type and location of the pollution source. In actual application, the input and output of pollutants in the biological treatment process are calculated in detail, the difference in removal amount is analyzed, and the pollution source is determined. Within, taking the biological treatment method for organic pollution as an example (other pollution types are analyzed similarly), determine the type and location of the pollution source.

[0040] ; in: For the region The actual removal amount within the system, and the reduction amount of pollutants obtained through monitoring; For the region The theoretical removal capacity is the removal capacity of specific organic pollutants calculated based on the biological treatment principle and design parameters; It is the judgment threshold, and the value range is generally between 0.7-0.9.

[0041] Forecasting region using QUAL2K model (simplified form) Water quality trends and pollution source development dynamics. This model is used to predict regional water quality trends and pollution source development dynamics. By simulating the changes in indicators such as biochemical oxygen demand (BOD) and dissolved oxygen (DO) over time, the transformation and migration patterns of pollutants in water bodies are analyzed, providing dynamic data support for pollution source location. For example, by inputting water flow, meteorological conditions, and other conditions within the region, water quality changes at different time points are simulated to predict the diffusion path and impact range of pollution sources. The specific calculation formula is: ; ; in: For the region Biochemical oxygen demand (BOD, mg / L); For the region Dissolved oxygen (DO, mg / L); For time ( ); For the region Internal BOD attenuation coefficient ( ), the value is generally between 0.1-0.5 between; For the region Internal reoxygenation coefficient ( ), the value is usually between 0.5-3 between; For the region Sources and sinks of internal BOD (mg / L / d); For the region Sources and sinks of internal DO (mg / L / d).

[0042] Based on the above analysis, the scoring formula for water pollution prevention and control factors is set as follows: ; in: The number of indicators used to evaluate the effectiveness of water pollution prevention and control and locate pollution sources; For the The weight of each indicator ranges from [0,1], and =1; The area predicted by the model Neidi The value of an indicator; For the region Neidi The actual monitoring value of an indicator.

[0043] Preliminary location of pollution sources based on water ecological restoration data: The Shannon-Wiener Index is used to measure biodiversity within a region and assess the health of the ecosystem. Changes in the biodiversity index can reflect whether the ecosystem is being disturbed, and thus infer the presence and potential location of pollution sources. For example, during the calculation process, the number of species and the proportion of individuals of each species within the region are counted, and then substituted into the formula to calculate the biodiversity index, which can determine the extent of the pollution impact on the ecosystem: ; in: For the region inner Shannon-Wiener index; For the region Number of species within; For the region Neidi The proportion of the number of individuals of a species to the total number of individuals. The value is lower than the threshold value under normal ecological conditions in the area When the ecosystem is disturbed.

[0044] Assumed vegetation coverage The normal range is [ , ], normalized to : ; When certain sensitive species are present , when it does not exist .

[0045] The comprehensive impact score formula of water ecological restoration factors is set as: ; in: 、 、 are the weights of the three indicators, Shannon-Wiener index, vegetation coverage, and the presence or absence of specific sensitive species, with a value range of [0,1], and .

[0046] Comparison of areas before and after ecological restoration Changes in biodiversity index, ecosystem structure and function. Assuming that the biodiversity index before ecological restoration is , after repair , the expected recovery index is , the quantitative indicators of ecosystem structure and function before restoration were , after repair , the expected value is . Set the ecological restoration effect evaluation coefficient : ; in: and are the weights of biodiversity index changes and ecosystem structure and function changes in the evaluation coefficient, respectively, and their values ​​range from [0,1], and .when ( For the effect evaluation threshold, such as 0.6), Make corrections: ; in: is the correction coefficient, and its value range is [0,1].

[0047] Standardize data such as vegetation coverage to make them comparable. Combined with information on the presence or absence of specific sensitive species, comprehensively assess the impact of water ecological restoration factors on pollution source location. For example, standardizing vegetation coverage data to its normal range, keeping it within the [0,1] interval, facilitates comprehensive analysis with other indicators.

[0048] Preliminary location of pollution sources based on water administration law enforcement supervision data: Use data statistical analysis technology to count the number of pollution incidents and the total number of inspections in the region, and calculate the pollution frequency index. Through statistical analysis of law enforcement supervision data, the pollution frequency area is determined, providing clues for locating pollution sources. For example, within a certain period of time, the number of pollution incidents and the number of inspections in different areas are counted, the pollution frequency index of each area is calculated, and the high-pollution areas are found. During the process of water administration law enforcement supervision, the number of pollution incidents is counted. and total number of inspections , calculate the pollution frequency index : ; Preliminary location of pollution sources based on video surveillance data: Using video image analysis technology, count the number of frames where suspected pollution sources appear and the number of frames where actual pollution sources are confirmed, calculate the recognition accuracy, and judge the ability of video surveillance to identify pollution sources. By analyzing video images, relevant information about pollution sources is extracted to provide an intuitive basis for positioning. For example, using image recognition algorithms, analyze the water bodies and surrounding environment in the video, identify possible pollution sources and count the frames. In the video surveillance system analysis, statistical areas Number of frames in which suspected pollution sources appear and the actual number of confirmed pollution source frames , calculate the recognition accuracy : ; A weighted calculation method is used to determine the video surveillance credibility coefficient based on performance parameters and installation conditions, such as device resolution, frame rate, coverage angle, and device distance. Taking these factors into consideration, the reliability of video surveillance data is evaluated to improve the accuracy of pollution source location. During the calculation process, the credibility coefficient is calculated by setting weights for each parameter based on the requirements of different scenarios, providing a quantitative indicator of the reliability of video surveillance data. The video surveillance credibility coefficient is obtained through weighted calculation based on the device's performance parameters and installation conditions: ; in: 、 、 、 They are resolution weight, frame rate weight, coverage angle weight, and device distance weight, and These weights can be set according to actual needs, for example, in scenes with high requirements on details, Can be set to 0.4; in scenes where dynamic images need to be captured quickly, Can be appropriately increased. For the region The resolution of the internal video surveillance equipment, The highest resolution on all devices; is the device frame rate, is the highest frame rate; is the device coverage angle, Ideal full coverage angle (e.g. 360°); is the distance from the device to the key monitoring area, The maximum effective monitoring distance allowed.

[0049] The data table conversion and entropy weight method are used to standardize the scores of each factor in each region, eliminate dimensional differences, and make different factors comparable. Then the entropy weight method is used to determine the weight of each factor. According to the size of the information entropy of each factor, its importance in locating the pollution source is objectively reflected, and then a comprehensive score formula is constructed to achieve accurate positioning. For example, after standardizing the scores of each factor, the information entropy is calculated, and the weight is determined based on the information entropy. The comprehensive score of each region is calculated by substituting it into the comprehensive score formula to determine the area where the pollution source is most likely to exist. For each region The factors Score, perform standardization, and obtain the original data matrix .in Indicates the number of regions, corresponding to the division of the study area into this sub-regions; It indicates the number of factors that affect the location of pollution sources, namely river and lake shorelines, water environment management, water pollution prevention and control, water ecological restoration, water administration law enforcement supervision, video surveillance and other factors. Indicates the Regions ( =1,2, , ) factors ( =1,2, , ) score, for example Representable area The shoreline factor score of rivers and lakes , Indicates area Water environment governance factor score wait, Indicates area Water pollution prevention factor score , Indicates area Water ecological restoration factor score wait, Indicates area Water administration law enforcement supervision pollution frequency index wait, Indicates area The video surveillance recognition accuracy rate is Indicates area The credibility coefficient of video surveillance.

[0050] Standardized data It is the original data The result after standardization is: .in It is The minimum value of the factor in all regions. It is The purpose of standardization is to eliminate the dimensional differences between the scores of different factors and make the factors comparable. Each column (i.e. each factor) in Perform standardization to obtain the standardized data matrix For example, for the river and lake shoreline factor (column 1), the standardized score for each region is calculated. , so that the scores of all factors are in the interval [0,1].

[0051] Reflects the The distribution of scores of each factor in each region is calculated as follows: , express In the region The weight of the factors.

[0052] For the factors, its information entropy Information entropy is used to measure the The smaller the information entropy, the greater the difference between the factors in different regions, the more information is provided, and the greater the impact on the location of pollution sources.

[0053] No. The weight of the factors is: The weight reflects the relative importance of the factor in the comprehensive assessment of pollution source location.

[0054] Taking all factors into consideration, the region The comprehensive scoring formula for pollution source location is: ; in: 、 、 、 、 、 、 are the weights corresponding to each factor, according to the formula Get, the value range is between [0,1], and By comparing the regions size, The higher the value, the greater the possibility of the existence of pollution sources, thus achieving accurate positioning of pollution sources.

[0055] In order to ensure the accuracy of the positioning results, the comprehensive score of each area needs to be calculated. Verification is carried out. Multiple verification monitoring points are set up in each area to regularly collect water and soil samples and record meteorological data. The actual pollutant concentrations obtained by monitoring The pollutant concentrations predicted by the model Compare and calculate the concentration error rate : ; like Exceeding the set error threshold (such as 15%, which can be adjusted according to the actual monitoring accuracy requirements), it indicates that the positioning results in this area may be biased and the model needs to be optimized.

[0056] Using model verification and optimization technology, by setting up verification monitoring points in each area, collecting actual data and comparing it with the model prediction data, and calculating the concentration error rate. If the error exceeds the threshold, the model parameters are adjusted, the weights are optimized, and the model is improved to continuously improve the positioning accuracy. For example, actual data such as water samples and soil samples are collected regularly, and compared with the pollutant concentrations predicted by the model. According to the error situation, the model parameters are adjusted and the model structure is optimized. The optimization process includes parameter adjustment, weight optimization, and model improvement. Re-evaluate the parameters in the scoring formula of each factor. For example, for the evaluation criteria in the water pollution index method , which can be updated according to the latest environmental quality standards or the special environmental needs of the area; in the calculation of the biodiversity index, if omissions or errors are found in the species statistics, the species numbers will be corrected in a timely manner. and species individual ratio Parameters such as . Using feedback data, the analytic hierarchy process (AHP) or machine learning algorithm is used to re-determine the weight of each factor. Taking machine learning as an example, historical verification data and the corresponding comprehensive score are combined. As training samples, the algorithm learns the actual contribution of different factors to the accuracy of pollution source positioning, thereby adjusting the weights 、 To make the model more realistic, we need to add factors and calculation formulas to the model. If specific factors are found in certain areas that are not included in the model, such as sudden geological activity leading to groundwater contamination, we can add these factors and calculation formulas to the model. For areas with complex terrain, we can introduce more sophisticated landform models to optimize pollutant dispersion calculations.

[0057] As time goes by and the environment changes, the location and intensity of pollution sources may change. The positioning system based on GIS vector map can access real-time monitoring data to achieve dynamic positioning. Significant changes occur within a short period of time (such as changes exceeding the set threshold ), or when new monitoring data calculates a score that places the area at a higher risk level, the system automatically triggers a real-time warning. Relevant departments are notified via text messages and app push notifications so that they can take timely countermeasures and effectively curb the spread of pollution.

[0058] In addition to locating pollution sources in a single area, the system can also conduct collaborative analysis of the positioning results of multiple areas. For example, by analyzing the comprehensive scores of pollution sources and pollutant types in adjacent areas, it can be determined whether there is cross-regional diffusion of pollution sources; combined with factors such as the connectivity of water systems and wind direction between regions, the propagation path of pollution can be predicted. It provides decision-making support for joint governance between regions, formulates unified pollution prevention and control and governance plans, improves overall governance efficiency, and realizes coordinated protection and restoration of the ecological environment within the basin. When relevant personnel receive information on the partition with the greatest possibility of pollution sources, they can first check the locations of pollution sources located in the partition using different positioning methods, and then check other locations, thereby improving the efficiency of determining the location of pollution sources.

[0059] After the final location of the pollution source is determined, the source pollution load is calculated. Errors in the location of the pollution source will directly affect the accuracy of the pollution load calculation. When locating pollution sources based on river and lake shoreline data, if a certain area is mistakenly identified as a pollution source due to data errors or inaccurate analysis methods, while the pollution source is actually located elsewhere, the non-existent pollution load will be included in the calculation of the pollution load for that area, resulting in an inflated result. Conversely, if the actual pollution source area is omitted, the pollution load calculation result will be underestimated. When dividing small areas to locate pollution sources, inaccurate boundary demarcation may result in some pollution sources being assigned to the wrong area, affecting the accuracy of the pollution load calculation for each area. Misjudgment of the pollution source type can also affect the accuracy of the pollution load determination. When using water pollution control data to determine the pollution source type, if organic pollution is mistakenly identified as other types of pollution, the calculation method and parameters used for the pollution load calculation will be incorrect. When biological treatment is used for organic pollution, the calculation methods for the theoretical and actual removal amounts of different types of pollution are different. Misjudging the type will lead to errors in the calculation of pollution loads, which cannot truly reflect the actual pollution situation. Insufficient precision in the identification of pollution sources leads to inaccurate determination of source pollution loads, which in turn affects the formulation and implementation of pollution control decisions. If the pollution load is underestimated, it may lead to insufficient control measures and the inability to effectively improve environmental quality; overestimating the pollution load may result in a waste of control resources. When formulating the treatment scale and process of a sewage treatment plant, if the source pollution load is not accurately determined, it may lead to the treatment facilities being unable to meet actual needs or being overbuilt, affecting the scientific and economic nature of the control work.

[0060] Based on the law of conservation of mass, by integrating data from river and lake shorelines, water environment management, water pollution prevention and control, water ecological restoration, water administration law enforcement supervision, video surveillance, and other aspects, the input and output of pollution sources and their migration and transformation processes in the environment are comprehensively considered to determine the source pollution load. For industrial pollution sources, the pollution load is calculated based on the mass balance principle using information collected within the enterprise on production processes, raw material usage, and the operating status of production equipment, combined with data on wastewater discharge volume and major pollutant concentrations obtained by automatic monitoring equipment at the discharge port. When determining the pollution load of a chemical enterprise, the pollution load of the enterprise can be obtained by subtracting the amount of pollutants contained in the products from the amount of pollutants contained in the raw materials used in its production process and adding the amount of pollutants generated and discharged into the environment during the production process.

[0061] The specific calculation process is as follows: First, we collect the relevant data of various pollution sources in the area. For industrial pollution sources, we assume that the enterprise The concentration of a certain pollutant emitted is (mg / L), the wastewater discharge is ( ), then the daily emission load of the pollutant of the enterprise is For agricultural pollution sources, the agricultural non-point source pollution load is calculated based on the information on crop varieties, area, fertilizer and pesticide usage and frequency collected from farmland surveys, combined with the water quality monitoring data of farmland irrigation water and drainage. Assume that a certain fertilizer is used on a farmland, and the proportion of a certain pollutant in its active ingredients is , the usage is M (kg), and the concentration of the pollutant in farmland drainage is (mg / L), drainage flow rate is ( ), then the daily pollution load of the pollutant from agricultural non-point sources is For domestic pollution sources, the calculation is based on data such as the city’s population, domestic sewage generation, sewage treatment plant capacity and operating conditions. Assuming the city’s population is , the per capita domestic sewage generation is ( ), the removal rate of a pollutant by a sewage treatment plant is The concentration of this pollutant in domestic sewage is (mg / L), then the daily pollution load of the pollutant from domestic pollution sources The pollution load of all industrial, agricultural, and domestic pollution sources in the region is added together to obtain the regional The total pollution load of the pollutant .

[0062] Build an application support platform to manage data and information. Information resources, serving as the data support layer, form the information source and foundation of the regulatory platform. To avoid duplication and ensure effective sharing of data resources, the project leverages the existing basic information databases of relevant departments and bureaus. By collecting, integrating, and improving information on existing river and lake shorelines, water environment management, water pollution prevention and control, water ecological restoration, water administration law enforcement supervision, and video surveillance, a practical, reliable, and advanced comprehensive database was constructed to meet the information service requirements of the information management system. Based on the needs of the regulatory platform and the actual conditions and characteristics of rivers and lakes, this project constructed basic, operational, monitoring, spatial, and unstructured databases. Given the large volume of data and the need for data exchange with various entities, this research utilized MySQL database software, established an efficient data update mechanism, integrated information resources, and ensured data integrity and consistency. The project encompassed data resource planning, collection, compilation, and data entry, maintenance and management, and database construction.

[0063] Establish a unified application support platform, providing a business development and operational support environment based on a unified technical architecture. This platform provides a foundational framework and underlying general services for upper-level application development, and provides an operational platform for data access and integration, enabling information sharing. Specifically, a river map service was customized and developed based on the basemap of the relevant unit's GIS platform. A workflow engine was used to customize and execute business processes, such as business management. Through this engine, processes for related businesses can be quickly and easily developed. This helps users adapt to the changing needs of processes and maintains ease of maintenance and cost-effectiveness when changes occur.

[0064] The middleware provides efficient and flexible message synchronization, as well as asynchronous transmission processing, store-and-forward, and reliable transmission capabilities, ensuring secure, reliable, and efficient message delivery in complex network and application environments. During data exchange, data in various formats is sent or uploaded to the target system via WebService and REST interface calls, enabling data exchange between heterogeneous systems across regions, platforms, and security authentication methods. Building a data exchange architecture from two core perspectives, technical and business, enables service-oriented IT capabilities and lays a solid foundation for the establishment of a SOA architecture.

[0065] The application support platform is built on the web, with mobile apps and WeChat official accounts to provide corresponding services for inspections. The web platform is based on the backend database, achieving a single source of data and ensuring efficient interoperability of information and data.

[0066] The main functions of the system are as follows: Basic Parameter Files: The Basic Parameter Files module is used to enter and manage basic project data. Users can use this module to enter basic project information, including project overview, location, and responsible personnel. This information provides essential data support for daily business management. Data entry supports multiple formats and batch import, ensuring accurate and efficient data entry.

[0067] Attendance Management: The attendance management module uses electronic attendance technology to record the attendance of cleaning vessels. Utilizing GPS positioning and clock-in / clock-out functionality, the module records in detail the time and location of vessels entering and exiting each river section. This ensures the accuracy of attendance data and provides reliable data support for management. The system automatically calculates the working hours of cleaning vessels and exports this data in the required format based on the purchaser's needs. This detailed record of attendance data allows management to track and analyze the operation of cleaning vessels and promptly identify and resolve attendance issues. The system also supports attendance exception handling, helping management resolve anomalies and ensuring the accuracy and completeness of attendance work.

[0068] Inspection Management: The inspection management module is used to record and save inspectors' inspection tracks and status. Through GPS positioning and mobile device upload capabilities, the system can update inspection records in real time, ensuring the accuracy and completeness of inspection data. This module supports live broadcasts of inspections by drones, further improving the coverage and efficiency of inspections. Drones can transmit inspection footage in real time, helping managers better understand on-site conditions. Problems discovered during inspections can be immediately reported through the system, forming a closed-loop management chain. This function ensures that problems are discovered and resolved in a timely manner, improving the effectiveness and responsiveness of inspection management. The system also supports historical inspection record queries, helping managers analyze inspection data and optimize inspection strategies and workflows.

[0069] Cleaning Turnover Management: The Cleaning Turnover Management module is used to optimize the assignment of cleaning tasks and vessel scheduling. Through this module, managers can view the progress of cleaning tasks in real time and deploy personnel and resources as needed.

[0070] Track Query Management: The Track Query Management module records and queries the operation tracks of cleaning vessels. Through this module, users can view the historical operation tracks of cleaning vessels at any time to understand their work status and routes. The system provides detailed track recording and query functions, allowing users to generate various reports and statistical data as needed. By analyzing track data, managers can identify potential problems in cleaning work, optimize operation routes and workflows, and improve work efficiency and effectiveness.

[0071] Assessment Indicator Management: The assessment indicator management module is used to assess and evaluate daily work. The system digitizes assessment indicators and evaluates them based on actual work performance. This module automatically generates assessment reports and performance evaluation results based on different assessment standards and requirements, ensuring fairness and transparency in the assessment process. The system provides flexible assessment standard settings, allowing managers to define assessment indicators based on actual needs. Assessment results can be generated into detailed reports and charts. The module supports historical recording and query of assessment results, facilitating long-term performance tracking and analysis.

[0072] Carbon Reduction Management: The Carbon Reduction Management module calculates the carbon conversion of salvaged waste and displays the results in graphical form. This module processes the weighing data of salvaged waste to calculate the corresponding carbon conversion, thereby evaluating the environmental benefits of cleaning operations. The system provides detailed carbon conversion calculation and display capabilities. By analyzing carbon conversion, managers can assess the environmental impact of cleaning operations, formulate appropriate environmental strategies, and further improve the environmental benefits of their work.

[0073] Salvaged Object Weighing Management: The salvaged object weighing management module uses onboard weighing equipment to record the weight of salvaged waste in real time and upload the data to the system. The system supports real-time monitoring and recording of weighing data, allowing managers to keep abreast of the salvage progress. By analyzing weighing data, the system generates detailed reports and statistics to assist managers in waste disposal and resource management.

[0074] Information Push Management: The Information Push Management module is used to promptly push important messages and alerts from the system to users. This includes work notifications, early warning messages, and more, ensuring that all relevant personnel receive system messages promptly. The system offers a variety of push methods, including SMS, email, and mobile notifications, to ensure timely delivery of information to all relevant personnel. Users can set their message preferences based on their needs, and the system will automatically push important messages based on priority.

[0075] Real-time sensor monitoring: The real-time sensor monitoring module uses cameras installed at key monitoring points to monitor garbage accumulation in real time. This module supports both the integration of new cameras and the integration of existing cameras, ensuring comprehensive monitoring system coverage. The system transmits monitoring footage in real time, allowing users to monitor garbage accumulation at any time. By analyzing video data, managers can promptly identify garbage accumulation issues and take necessary measures to address them.

[0076] Data Analysis and Statistics: The Data Analysis and Statistics module aggregates and analyzes entered cleaning data. This module supports daily, monthly, quarterly, annual, or custom date analysis, and exports reports and charts in custom formats. By collating and analyzing historical data, the system generates various statistical reports and charts, providing strong support for management decision-making. Through data analysis, users can understand cleaning trends and performance, identify potential issues, and make adjustments.

[0077] Attendance supervision and early warning: The non-attendance early warning function in the attendance supervision and early warning module is committed to ensuring that the attendance records of cleaning vessels are accurate and correct. When the system detects that a cleaning vessel has not punched in at the specified time, it will automatically trigger the early warning mechanism and immediately send a notification to the relevant management personnel. Through automatic early warning, the system can promptly remind relevant personnel to perform supplementary punch-in operations to avoid omissions and incomplete attendance records. At the same time, the non-attendance early warning function also has detailed record and report generation capabilities, so managers can easily query attendance history data and conduct comprehensive attendance statistical analysis. Garbage volume statistics management: The garbage volume statistics management module generates detailed daily, monthly, and annual statistical reports by accurately recording and counting the amount of garbage salvaged by cleaning vessels. The garbage salvage volume statistics function uses advanced data collection and processing technologies to ensure that the garbage volume records of each ship are accurate. By summarizing and analyzing these data, the system can intuitively display the trends and changes in garbage salvage, providing an important reference for management decisions. In actual applications, the garbage salvage volume statistics module also supports multi-dimensional data display and comparative analysis. Users can conveniently view the amount of garbage salvaged in different time periods and different areas through the system interface, identify high-incidence areas and peak periods of garbage, and thus adjust cleaning strategies and resource investment in a targeted manner. In addition, the statistical reports generated by the system can also be exported in multiple formats to facilitate data sharing and communication among management personnel.

[0078] Overload Warning Statistics: The Overload Warning Statistics module monitors waste collection volumes in real time. When collection volumes exceed preset thresholds, the system immediately issues warning notifications. This feature helps managers promptly understand excessive waste levels and promptly take necessary measures to address them, ensuring smooth waste disposal. By setting appropriate thresholds, the Overload Warning Statistics module effectively prevents waste accumulation and processing delays, ensuring the continuity and efficiency of cleaning operations. The Overload Warning feature also supports detailed statistics and analysis of warning records. Managers can review historical overload warning data, analyze fluctuations and trends in waste collection volumes, and optimize warning thresholds and response strategies. The system also generates overload warning reports, providing intuitive data presentation and multi-dimensional comparative analysis to help managers better understand and address waste disposal challenges. The Overload Warning Statistics module enables users to accurately monitor and efficiently manage waste collection volumes, improving the overall quality and efficiency of cleaning operations.

[0079] Off-Track Warning: The Off-Track Warning module monitors the trajectory of cleaning vessels in real time to ensure they adhere to prescribed routes and schedules. When the system detects that a cleaning vessel has docked at a location for longer than a set threshold or has deviated from its established trajectory, it automatically issues an alert and generates a corresponding report. The Off-Track Warning module also features detailed trajectory recording and analysis. Managers can view each vessel's actual trajectory through the system, identifying potential deviations and abnormal docking situations. The system-generated trajectory report provides detailed data and charts, helping users gain a comprehensive understanding of a vessel's movement and operational efficiency.

[0080] Waste Disposal Monitoring: The waste disposal monitoring module uses cameras installed at waste disposal sites to provide real-time monitoring of the entire waste disposal process. Users can view on-site waste disposal conditions through the system interface, ensuring compliance with environmental standards and promptly identifying and resolving any issues. This function utilizes efficient video surveillance technology to provide comprehensive oversight of the waste disposal process, ensuring transparency and standardization of waste disposal operations. The waste disposal monitoring module also supports video playback and event marking. Managers can easily review historical recordings to analyze process issues and areas for improvement. The system also provides event marking and alarm functions. When abnormal processing behavior or equipment failure is detected, early warning notifications are automatically issued, helping users take timely measures to prevent environmental pollution and resource waste. This is achieved through the waste disposal monitoring module.

[0081] Closed-Loop Situation Warning: The closed-loop situation warning module monitors every step of the cleaning process to ensure that each step is completed smoothly. When the system detects a problem or non-compliance in a certain step, it automatically issues an early warning notification, helping users to promptly identify and resolve process issues. The closed-loop situation warning module also supports detailed process logging and analysis. Users can view the completion status and problem records of each process step through the system interface, identifying potential bottlenecks and areas for improvement. The system-generated closed-loop warning report provides detailed data and charts to help users fully understand the execution and efficiency of the process.

[0082] Message push warning: The message push warning module is used to push warning messages in the system to relevant personnel in a timely manner, including warning information such as abnormal attendance, excessive garbage volume, and deviation from track. Through real-time message push, it ensures that all important information can be quickly conveyed, improves response speed and processing efficiency, and avoids management problems caused by information delays. This function ensures that users can obtain warning information in a timely manner through multi-channel information push methods such as SMS, email, system notifications, etc. The message push warning module also supports message recording and analysis functions. Users can view historical warning messages through the system interface, analyze the frequency and causes of warnings, and optimize warning strategies and response measures. The warning message report generated by the system provides detailed data and chart displays to help users fully understand the implementation and effectiveness of the warning.

[0083] For example, based on the basin's geographical characteristics, water flow direction, and functional area distribution, the entire basin is divided into 100 small areas, marked as , ,..., , laying the foundation for subsequent precise positioning.

[0084] Using GIS buffer analysis technology, a buffer zone is constructed based on the coastline. , its land use types include large industrial parks and dense residential areas. The potential pollution possibility corresponding to the industrial land code is high, and the quantitative value of human activity intensity in this area is 8 (value range [0,10]). Assume that there are 3 known sample points in this area for spatial difference algorithm to calculate pollution attribute values. The pollution attribute values ​​of the known sample points are They are =50, =60, =70, the distance from the point to be estimated to each sample point They are =2, =3, =4, weight coefficient =2. According to the spatial difference algorithm formula, calculate the pollution attribute value of the point to be estimated : ; Assume that the pollution judgment indicators related to river and lake shorelines include land use type and human activity intensity ( =2), land use type indicator weight =0.6, human activity intensity index weight =0.4, the land use type index value after standardization =0.8, human activity intensity index value =0.9. According to the scoring formula of river and lake shoreline factors, we can get Regional river and lake shoreline factor score for: ; exist In a certain monitoring area, the actual concentration of chemical oxygen demand was obtained =50 , measured concentration of ammonia nitrogen , COD evaluation standard for this area , Assume the number of evaluation indicators = 2. Calculate the comprehensive pollution index according to the water pollution index method : ; Setting thresholds ,because , according to the scoring formula of water environment governance factors: ; Available .

[0085] In the treatment of organic pollution by biological treatment The actual removal amount of the area is obtained through monitoring , calculate the theoretical removal capacity based on the biological treatment principle and design parameters , judgment threshold .because , and it meets the characteristics of organic pollution, so the pollutant type in this area is organic pollution. It is assumed that the indicators used to evaluate the effectiveness of water pollution prevention and control and the location of pollution sources are the ratio of actual removal to theoretical removal and the BOD change predicted by the QUAL2K model. , the ratio of actual removal amount to theoretical removal amount , BOD change index weight predicted by QUAL2K model The BOD change in the region was predicted by the QUAL2K model. , actual monitoring BOD change According to the water pollution prevention and control factor scoring formula, we can get: ; In the area The number of species was obtained by sampling, line transect and drone monitoring. , and calculate the proportion of individuals of each species , and then calculate the Shannon-Wiener index : ; At the same time, obtain vegetation coverage , and normalize it to , an indicator to determine the presence or absence of specific sensitive species (Sensitive species exist). According to the comprehensive impact score formula of water ecological restoration factors, we can get: ; If the area has undergone water ecological restoration projects, the changes in biodiversity index, ecosystem structure and function before and after restoration will be compared to calculate the ecological restoration effect evaluation coefficient. (greater than the set threshold ), then there is no need to Make corrections.

[0086] Over a period of time, the statistical area Number of pollution incidents times, total number of inspections times, calculate the pollution frequency index according to the formula The higher the index, the more likely the area is to be polluted frequently. According to the scoring formula for water administration law enforcement supervision factors, we can get: ; In the area In the video surveillance, count the number of frames where suspected pollution sources appear Frames, the actual number of confirmed pollution source frames Frame, calculate recognition accuracy At the same time, the comprehensive score of the camera parameters installed in the area Points (full score is 100 points), according to the video surveillance credibility coefficient formula, we can get: ; According to the video surveillance factor scoring formula (assuming the total number of frames ), we can get: ; The data table transformation and entropy weight method are used to standardize the scores of each factor in each region. Assuming that the standardization has been completed, the standardized scores of each factor in each region are obtained. 、 、 、 、 、 For example, assume that the standardized scores are: , , , , , ; , , , , , ; , , , , , ; , , , , , ; , , , , , ; , , , , , ; , , , , , ; Calculate the comprehensive score for each region: ; ; ; ; ; ; By comparing the comprehensive scores of each region, The highest overall score (0.725) was determined to be the most likely source of pollution. Further investigation revealed a chemical plant in the area illegally discharging industrial wastewater, and a plot of agricultural land with excessive pesticide pollution, consistent with the calculated results.

[0087] The process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication portion, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the above-mentioned functions defined in the method of the present application are performed. It should be noted that the computer-readable medium mentioned above in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared segment or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Furthermore, in this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, electrical, optical, RF, or any suitable combination thereof.

[0088] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or portion of code that contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or operations, or can be implemented using a combination of dedicated hardware and computer instructions.

[0089] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be subject to any deformation or modification.

Claims

1. A method for determining river non-point source pollution load based on GIS vector map conversion, characterized in that: The method comprises: Obtain river and lake shoreline data through GIS vector conversion, and collect water environment management data, water pollution prevention and control data, water ecological restoration data, water administration law enforcement supervision data, and video surveillance data to build a basic data information database; Divide the polluted area into several zones, and use river and lake shoreline data, water environment management data, water pollution prevention and control data, water ecological restoration data, water administration law enforcement supervision data, and video surveillance data to preliminarily locate the zones where the pollution sources are located; Calculate the reliability scores based on different data positioning methods, determine the reliability weights of different positioning methods through the entropy weight method, construct the comprehensive score formula for pollution source positioning, and calculate the comprehensive reliability scores of different partitions; The information push management module pushes the location of the partition with the highest comprehensive reliability score to relevant personnel, who then conduct inspections in the partition to determine the final location and type of the pollution source and calculate the total pollution load based on the pollution source type. Verification monitoring points are set up in each partition, and the concentration error is calculated using model verification and optimization technology. When the error exceeds the threshold, parameter adjustment and weight optimization are performed.

2. The method for determining the non-point source pollution load of a smart river based on GIS vector map conversion according to claim 1 is characterized in that: The method for obtaining the shoreline data of river and lake waters is as follows: Store and process river and lake maps through scanners and computers; determine the proportional relationship between river and lake scans and GIS vector images, convert raster data into vector data, and store vector data; convert vector data into raster data.

3. The method for determining the non-point source pollution load of a smart river based on GIS vector map conversion according to claim 2 is characterized in that: The basic data information database construction process is as follows: Set up water quality monitoring stations to collect routine water quality indicators, as well as meteorological and surrounding pollution source information; collect water pollution prevention and control data based on the type of pollution source and build a water pollution prevention and control database; Monitor changes in water quality and quantity before and after the implementation of water ecological restoration projects, as well as the restoration of ecological functions at key ecological nodes; law enforcement personnel monitor the overall condition of the river in real time, and the public uploads photos, videos, and related information of pollution problems they discover; Install different types of high-definition cameras at key locations around rivers and lakes to collect video data; integrate the above data to build a basic data information database.

4. The method for determining the non-point source pollution load of a smart river based on GIS vector map conversion according to claim 3 is characterized in that: The specific process of the preliminary positioning is as follows: Divide the polluted area into The buffer zones were constructed through GIS buffer analysis technology, the pollution-related attribute values ​​were determined using the spatial difference algorithm, the location of potential pollution sources was judged, and a scoring formula for river and lake shoreline factors was constructed to calculate the scores; the water quality pollution index method was used to calculate the comprehensive pollution index, and a scoring formula for water environment factors was set, and the scores were calculated based on the comparison results between the comprehensive pollution index and the set threshold value; the type and location of pollution sources were determined through material balance technology and actual removal amount, and the QUAL2K model was used to predict water quality change trends and pollution source development dynamics, and a scoring formula for water pollution prevention and control factors was constructed to calculate the scores.

5. The method for determining the non-point source pollution load of a smart river based on GIS vector map conversion according to claim 4 is characterized in that: The specific process of the preliminary positioning also includes: The Shannon-Wiener Index is used to measure regional biodiversity, and the water ecological restoration factor scoring formula is constructed based on the vegetation coverage rate and the presence or absence of specific sensitive species. The pollution frequency index is calculated using data statistical analysis technology. Video image analysis technology is used to count the number of frames of suspected pollution sources and the number of frames of actual confirmed pollution sources, calculate the recognition accuracy, and perform weighted calculations based on equipment performance parameters and installation conditions to obtain the video surveillance credibility coefficient.

6. The method for determining the non-point source pollution load of a smart river based on GIS vector map conversion according to claim 5 is characterized in that: The specific formula for the comprehensive scoring formula for pollution source location is as follows: ； in: 、 、 、 、 、 、 are the weights corresponding to each factor, and their value range is [0,1]. Score the shoreline factors of rivers and lakes. Score the water environment governance factor, Water pollution prevention and control factor score, Score the water ecological restoration factor. is the pollution frequency index, For recognition accuracy, is the video surveillance credibility coefficient.

7. The method for determining the non-point source pollution load of a smart river based on GIS vector map conversion according to claim 6 is characterized in that: The specific calculation process of the total pollution load is as follows: The daily emission load of the pollutant from the enterprise is calculated based on the pollutant concentration and wastewater discharge volume of the enterprise. The daily pollution load of the agricultural pollutant is calculated based on the crop varieties, area, fertilizer and pesticide usage and frequency collected from the farmland survey, combined with the water quality monitoring data of farmland irrigation water and drainage. The daily pollution load of the pollutant from domestic pollution sources is calculated based on the urban population, domestic sewage generation, sewage treatment plant treatment capacity and operating conditions. The total pollution load calculation formula is as follows: ； in: is the total pollution load, is the daily emission load of the pollutant of the enterprise; The daily pollution load of the pollutant in agriculture; is the daily pollution load of the pollutant from domestic pollution sources, For the Enterprises.

8. The method for determining the non-point source pollution load of a smart river based on GIS vector map conversion according to claim 7 is characterized in that: The specific process of parameter adjustment and weight optimization is as follows: Multiple verification monitoring points are set up in each zone to collect actual pollutant concentrations regularly; the actual pollutant concentrations collected are compared with the calculated pollutant concentrations, and the concentration error rate is calculated; an error threshold is set. If the concentration error rate is greater than the error threshold, the parameters are adjusted. Using feedback data, the hierarchical analysis method is used to re-determine the weights of each factor. If special influencing factors are found in some areas that are not included in the model, the corresponding influencing factors and calculation formulas are added to improve the model.

9. The method for determining the non-point source pollution load of a smart river based on GIS vector map conversion according to claim 8 is characterized in that: The push process of the information push management module is as follows: Information is classified and organized according to message type, and different push channels or multiple channels are used simultaneously according to the urgency and nature of different messages; relevant personnel set the message receiving preference priority according to needs, and the information push management module automatically pushes important information according to priority.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a method for determining a smart river non-point source pollution load based on GIS vector diagram conversion as described in any one of claims 1 to 9.

Images