A method and system for predicting implicit garbage pollution based on regional water quality

Abstract

The present application belongs to the technical field of water pollution detection and treatment, and specifically relates to a hidden garbage pollutant prediction method and system based on regional water quality. The present application can quickly trace the diffusion path of pollutants and accurately locate the pollution source by mining key indicators related to pollutant migration from historical data. After the pollution source is determined, the diffusion range of hidden garbage pollutants can be predicted according to the geographical distance between the pollution source and the monitoring point and the water quality change trend, so as to determine the possible diffusion area of hidden garbage pollutants. In addition, the future diffusion boundary of the pollutants can be predicted in combination with the preset water intervention improvement time, and the water area between the predicted pollution boundary and the pollution source is designated as the water area to be improved, providing clear guidance for treatment actions, achieving the purpose of cutting off the further diffusion of pollutants, effectively protecting the water environment, and further saving the cost of pollutant treatment and improving the efficiency of water area treatment.

Description

Technical Field

[0001] This invention belongs to the field of water pollutant detection and treatment technology, specifically relating to a method and system for predicting hidden garbage pollutants based on regional water quality. Background Technology

[0002] With the acceleration of industrialization, water pollution is becoming increasingly serious. In particular, the concealment and non-degradability of hidden waste pollutants pose a huge challenge to water quality management. Traditional management methods mostly rely on end-of-pipe treatment and periodic testing, which lack real-time monitoring and prediction of the spread trend of hidden waste pollutants. This makes it impossible to intervene in advance during the spread of pollutants, which leads to large areas of water pollution and high treatment costs, seriously affecting the development of the ecological environment around the water body.

[0003] While some monitoring technologies for hidden waste pollutants exist, most rely on fixed water quality parameters for monitoring and prediction, failing to consider the impact of varying water quality on the migration of different pollutants. This results in inaccurate predictions, affecting the formulation and implementation of remediation plans and hindering the effective containment of pollution. Therefore, this paper proposes a method for predicting hidden waste pollutants based on regional water quality to address these issues. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for predicting hidden waste pollutants based on regional water quality. This method can monitor water quality changes in real time, locate pollution sources, predict the spread of pollutants, and achieve early intervention by delineating water areas to be improved, thereby reducing treatment costs.

[0005] The specific technical solution adopted by this invention is as follows:

[0006] A method for predicting hidden litter pollutants based on regional water quality, comprising:

[0007] Water quality data and the concentration of hidden pollutants in the target water area are collected in real time through pre-deployed water quality sensors;

[0008] Obtain historical water quality data and pollution records for the target water area, and extract correlation indicators with pollutant migration from the historical water quality data based on the pollution records;

[0009] Based on real-time collected water quality data and the concentration of hidden waste pollutants, combined with related indicators, the diffusion path of hidden waste pollutants is traced, and the pollution source is located according to the diffusion path;

[0010] Based on the geographical distance between the pollution source and the collected water samples, and the trend of water quality changes, the diffusion range of hidden garbage pollutants is predicted;

[0011] The system collects real-time pollution boundaries of hidden litter pollutants and, in conjunction with a preset water body intervention and improvement time, predicts the predicted pollution boundaries of hidden litter pollutants. The water area between the predicted pollution boundary and the pollution source is then designated as the water area to be improved.

[0012] In a preferred embodiment, the water quality sensor includes a pH sensor, a dissolved oxygen sensor, a heavy metal ion sensor, and a pollutant sensor. The pH sensor is used to determine the acidity or alkalinity of the target water body, the dissolved oxygen sensor is used to monitor the dissolved oxygen content in the water body, the heavy metal ion sensor is used to detect the concentration of heavy metal ions in the water body, and the pollutant sensor is used to identify the types and concentrations of pollutants in the water body.

[0013] In a preferred embodiment, the step of extracting correlation indicators with pollutant migration from historical water quality data based on pollution records includes:

[0014] Collect all environmental factors related to the migration of pollutants in water bodies, perform correlation analysis between each environmental factor and the amount and rate of pollutant migration, and output correlation scores;

[0015] The association score is compared with a preset association threshold;

[0016] When the correlation score is higher than the correlation threshold, the environmental factor corresponding to the correlation score is directly used as the correlation indicator.

[0017] When the association score is lower than or equal to the association threshold, the environmental factor corresponding to the association score is labeled as a potential influencing factor.

[0018] By jointly analyzing potential impact factors and associated indicators, we can determine whether the absence of potential impact factors will affect the migration of pollutants under associated indicators.

[0019] If they exist, the potential influencing factors will be incorporated into the corresponding related indicators to form a comprehensive related indicator.

[0020] If it does not exist, the original related indicators will remain unchanged.

[0021] In a preferred embodiment, the step of performing correlation analysis between each environmental factor and the pollutant migration amount and pollutant migration rate, and outputting a correlation score, includes:

[0022] Different concentration gradients were set for each environmental factor, and the migration amount and migration rate of pollutants under each concentration gradient were measured and recorded as the first correlation condition parameter and the second correlation condition parameter, respectively.

[0023] The first and second correlation condition parameters are vectorized.

[0024] The vectorized first and second correlation condition parameters are fused and calculated, and the fusion calculation result is recorded as the association score.

[0025] In a preferred embodiment, the step of tracing the diffusion path of hidden waste pollutants includes:

[0026] Collect real-time water quality data and hidden pollutant concentrations of the target water area, and compare them with historical water quality data and hidden pollutant concentrations to determine the pollution pattern of the target water area.

[0027] Multi-directional offset processing is performed on real-time water quality data sampling points to obtain multiple traceability sample points;

[0028] Identify the differences in the concentration of hidden waste pollutants between each traceable sample point and the real-time water quality sampling point, select the offset direction with the largest concentration difference as the diffusion direction of the hidden waste pollutants, and draw the diffusion path of the hidden waste pollutants in the diffusion direction.

[0029] In a preferred embodiment, the step of locating the pollution source based on the diffusion path includes:

[0030] Multiple monitoring points were set up along the diffusion path of hidden waste pollutants, and the concentration of hidden waste pollutants at each monitoring point was collected and recorded as sample condition parameters.

[0031] The sample condition parameters at adjacent monitoring points are subtracted to output the pollutant concentration fluctuation, which includes both positive and negative fluctuations.

[0032] The monitoring points where the negative fluctuations transition to positive fluctuations are located and recorded as potential pollution source nodes. The difference processing is then performed on the monitoring points after the potential pollution source nodes until the sample condition parameters of N consecutive monitoring points all show positive fluctuations. Then, the potential pollution source nodes are determined as pollution sources.

[0033] In a preferred embodiment, the step of predicting the diffusion range of hidden waste pollutants based on the geographical distance between the pollution source and the collected water samples and the trend of water quality changes includes:

[0034] Obtain the geographical distance between the pollution source and each monitoring point, and record it as a distance parameter;

[0035] Collect the concentration difference of hidden waste pollutants between the pollution source and each monitoring point, and record it as a prediction condition parameter;

[0036] Based on the prediction condition parameters and the distance parameters, the maximum diffusion distance of hidden waste pollutants is predicted, and a diffusion range map of hidden waste pollutants is drawn based on the maximum diffusion distance.

[0037] In a preferred embodiment, the step of collecting the real-time pollution boundary of hidden litter pollutants and predicting the predicted pollution boundary of hidden litter pollutants in conjunction with a preset water body intervention and improvement time includes:

[0038] Real-time collection of hidden waste pollutants' real-time pollution boundary, and the distance between the real-time pollution boundary and the maximum diffusion boundary;

[0039] The remaining diffusion time of pollutants is calculated based on the distance between the real-time pollution boundary and the maximum diffusion boundary, combined with the diffusion trend of hidden waste pollutants.

[0040] Compare the remaining dispersion time of pollutants with the time required for water body intervention and improvement;

[0041] When the remaining diffusion time of pollutants is less than the water body intervention and improvement time, the water area between the maximum diffusion boundary and the pollution source is directly designated as the water area to be improved.

[0042] When the remaining diffusion time of pollutants is greater than the water body intervention and improvement time, the predicted pollution boundary is calculated based on the pollutant diffusion trend and the water body intervention and improvement time, and the water area between the predicted pollution boundary and the pollution source is designated as the water area to be improved.

[0043] This invention also provides a system for predicting hidden litter pollutants based on regional water quality, using the aforementioned method for predicting hidden litter pollutants based on regional water quality, comprising:

[0044] The data acquisition module is used to collect water quality data and hidden pollutant concentrations in the target water area in real time through pre-deployed water quality sensors;

[0045] The correlation index extraction module is used to obtain historical water quality data and pollution records of the target water area, and extract correlation indicators with pollutant migration from the historical water quality data based on the pollution records.

[0046] The pollution source location module is used to trace the diffusion path of hidden waste pollutants based on real-time collected water quality data and the concentration of hidden waste pollutants, combined with related indicators, and to locate the pollution source based on the diffusion path.

[0047] The prediction module is used to predict the spread range of hidden garbage pollutants based on the geographical distance between the pollution source and the collected water samples and the trend of water quality changes.

[0048] The water area delineation module is used to collect real-time pollution boundaries of hidden waste pollutants, and predict the predicted pollution boundaries of hidden waste pollutants by combining the preset water body intervention and improvement time. The water area between the predicted pollution boundary and the pollution source is delineated as the water area to be improved.

[0049] And, an electronic device, the electronic device comprising:

[0050] At least one processor;

[0051] and a memory communicatively connected to the at least one processor;

[0052] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the above-described method for predicting hidden waste pollutants based on regional water quality.

[0053] The technical effects achieved by this invention are as follows:

[0054] This invention, by mining key indicators related to pollutant migration from historical data, can quickly trace the diffusion path of pollutants and accurately locate the pollution source. After the pollution source is identified, the invention predicts the diffusion range of hidden waste pollutants based on the geographical distance between the pollution source and the monitoring point and the water quality change trend, thereby clarifying the possible diffusion area of ​​hidden waste pollutants. In addition, it also predicts the future diffusion boundary of pollutants by combining the preset water body intervention and improvement time, and delineates the water area between the predicted pollution boundary and the pollution source as the water area to be improved, providing clear guidance for the treatment action, achieving the goal of cutting off the further diffusion of pollutants, so that the aquatic environment can be effectively protected, and correspondingly, it can further save pollutant treatment costs and improve the efficiency of water treatment. Attached Figure Description

[0055] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0056] Figure 2 This is a schematic diagram of the system modules of the present invention;

[0057] Figure 3 This is a schematic diagram of the electronic device structure of the present invention. Detailed Implementation

[0058] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0059] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0060] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that mutually excludes other embodiments.

[0061] Please see Figure 1 As shown, this invention provides a method for predicting hidden litter pollutants based on regional water quality, including:

[0062] S1. Real-time collection of water quality data and concentration of hidden garbage pollutants in the target water area through pre-deployed water quality sensors;

[0063] In step S1, some hidden pollutants, such as microplastics, drug residues, and chemical additives, often exist in aquatic environments and are difficult to detect in conventional water body testing. However, they can still pollute the aquatic environment. This embodiment uses corresponding water quality sensors to monitor water quality changes in the target water area and feed back water quality data and hidden pollutant concentrations, thereby providing basic data support for subsequent predictive analysis. The water quality sensors may include pH sensors, dissolved oxygen sensors, heavy metal ion sensors, and pollutant sensors. The pH sensor is used to determine the acidity or alkalinity of the target water area, the dissolved oxygen sensor is used to monitor the dissolved oxygen content in the water, the heavy metal ion sensor is used to detect the concentration of heavy metal ions in the water, and the pollutant sensor is used to identify the types and concentrations of pollutants in the water. In practical applications, it is necessary to deploy appropriate sensor types and quantities according to the specific aquatic environment to ensure the accuracy of the data feedback results and enable effective monitoring of the aquatic environment.

[0064] S2. Obtain historical water quality data and pollution records for the target water area, and extract correlation indicators with pollutant migration from the historical water quality data based on the pollution records;

[0065] In step S2, within the same target water area, due to the influence of the surrounding environment, there are generally multiple instances of the same type of latent pollution. Therefore, analyzing historical water quality data and pollution records can quickly pinpoint the migration patterns of latent pollutants. Specifically, this involves determining correlation indicators related to pollutant migration based on the water environment, such as water temperature and pH value. Determining these correlation indicators can effectively reveal the migration characteristics of latent waste pollutants and assist in identifying the location of pollution sources and their diffusion paths. The step of extracting correlation indicators related to pollutant migration from historical water quality data based on pollution records includes:

[0066] Collect all environmental factors related to the migration of pollutants in water bodies, perform correlation analysis between each environmental factor and the amount and rate of pollutant migration, and output correlation scores;

[0067] The association score is compared with a preset association threshold;

[0068] When the correlation score is higher than the correlation threshold, the environmental factor corresponding to the correlation score is directly used as the correlation indicator.

[0069] When the association score is lower than or equal to the association threshold, the environmental factor corresponding to the association score is labeled as a potential influencing factor.

[0070] By jointly analyzing potential impact factors and associated indicators, we can determine whether the absence of potential impact factors will affect the migration of pollutants under associated indicators.

[0071] If they exist, the potential influencing factors will be incorporated into the corresponding related indicators to form a comprehensive related indicator.

[0072] If it does not exist, the original related indicators will remain unchanged;

[0073] Specifically, when extracting correlation indicators, a comprehensive collection of environmental factors is first conducted on the target water area. These factors include, but are not limited to, water pH, water temperature, light intensity, and sediment properties. Correlation analysis is performed on each environmental factor with the amount and rate of pollutant migration, quantifying the corresponding correlation score. This score directly reflects the strength of the correlation between each environmental factor and pollutant migration. To ensure the accuracy and effectiveness of the correlation indicators, a pre-set correlation threshold is established. This threshold, based on extensive historical data and expert experience, distinguishes between key factors that significantly influence pollutant migration and potential factors with weaker influence. After obtaining the correlation score, it is compared with the pre-set threshold. Environmental factors with correlation scores higher than the threshold are directly identified as key factors. For environmental factors with correlation scores below or equal to the threshold, they are initially recorded as potential influencing factors. Although potential influencing factors do not affect pollutant migration when analyzed independently, they may interact with correlation indicators. For example, while light intensity may not have a significant impact on its own, it can alter the pollutant migration rate when combined with water temperature. Therefore, further joint analysis of potential influencing factors and identified correlation indicators is needed to assess whether they affect pollutant migration. If the absence of potential influencing factors does indeed affect pollutant migration under the correlation indicators, the corresponding potential influencing factors will be included in the corresponding correlation indicators to form a relatively comprehensive integrated correlation indicator. This ensures that no factors that may affect pollutant migration are overlooked during the analysis.

[0074] Secondly, the steps of performing correlation analysis between each environmental factor and pollutant migration amount and pollutant migration rate, and outputting correlation scores, include:

[0075] Different concentration gradients were set for each environmental factor, and the migration amount and migration rate of pollutants under each concentration gradient were measured and recorded as the first correlation condition parameter and the second correlation condition parameter, respectively.

[0076] The first and second correlation condition parameters are vectorized.

[0077] The vectorized first and second correlation condition parameters are fused and calculated, and the fusion calculation result is recorded as the association score.

[0078] In the above process, when determining the correlation score between environmental factors and the amount and speed of pollutant migration, gradient concentrations are first set for each environmental factor to simulate the migration of pollutants under different environmental conditions. By measuring the amount and speed of pollutant migration under different concentration gradients, the first and second correlation condition parameters are obtained to reflect the degree of influence of environmental factors on pollutant migration. For quantitative analysis, the first and second correlation condition parameters are vectorized to convert the influence of environmental factors into a calculable numerical form. Then, the vectorized parameters are fused and calculated to comprehensively consider the influence of each environmental factor on pollutant migration. The result of the fusion calculation is the correlation score. The fusion calculation method can be weighted average or principal component analysis. The higher the final correlation score, the stronger the correlation between the corresponding environmental factor and pollutant migration, and the greater the influence on pollutant migration.

[0079] S3. Based on real-time collected water quality data and the concentration of hidden waste pollutants, combined with related indicators, trace the diffusion path of hidden waste pollutants and locate the pollution source according to the diffusion path.

[0080] In step S3, after identifying the hidden pollutants, further pollution source tracing and pollutant diffusion path delineation will be conducted to provide corresponding data support for subsequent pollutant treatment. The step of tracing the diffusion path of hidden pollutants includes:

[0081] Collect real-time water quality data and hidden pollutant concentrations of the target water area, and compare them with historical water quality data and hidden pollutant concentrations to determine the pollution pattern of the target water area.

[0082] Multi-directional offset processing is performed on real-time water quality data sampling points to obtain multiple traceability sample points;

[0083] Identify the differences in the concentration of hidden waste pollutants between each traceable sample point and the real-time water quality sampling point, select the offset direction with the largest concentration difference as the diffusion direction of the hidden waste pollutants, and draw the diffusion path of the hidden waste pollutants in the diffusion direction.

[0084] Specifically, when tracing the diffusion path of hidden litter pollutants, it is first necessary to collect real-time water quality data and hidden litter pollutant concentrations in the target water area. By comparing these data with historical data, the pollution pattern of the target water area can be identified, making it easier to directly extract the corresponding correlation indicators. Of course, if the corresponding pollution pattern is not found in the historical data, the correlation indicators need to be measured again to ensure the accuracy of pollutant migration identification. Then, multi-directional offset processing is performed on the real-time water quality data sampling points. The offset direction covers the possible diffusion of pollutants in different directions, thereby generating multiple traceability sample points. Then, by comparing the difference in hidden litter pollutant concentrations between these traceability sample points and the original real-time water quality sampling points, the offset direction with the largest concentration difference can be found. The offset direction with the largest concentration difference is considered to be the main diffusion direction of hidden litter pollutants. Based on the main diffusion direction, the diffusion path of hidden litter pollutants can be drawn on the map, providing data support for subsequent pollution source location and pollution range prediction.

[0085] In addition, the steps for locating the pollution source based on the diffusion path include:

[0086] Multiple monitoring points were set up along the diffusion path of hidden waste pollutants, and the concentration of hidden waste pollutants at each monitoring point was collected and recorded as sample condition parameters.

[0087] The sample condition parameters at adjacent monitoring points are subtracted to output the pollutant concentration fluctuation, which includes both positive and negative fluctuations.

[0088] Locate the monitoring point where the negative fluctuation value transitions to the positive fluctuation value and record it as a potential pollution source node. Continue to perform subtraction processing on the monitoring points after the potential pollution source node until the sample condition parameters under N consecutive monitoring points all show positive fluctuations. Then, determine the potential pollution source node as the pollution source.

[0089] Specifically, when identifying the source of hidden litter pollution, multiple monitoring points are first set up along the diffusion path of the hidden litter pollutants. By collecting the concentration of hidden litter pollutants at each monitoring point, the corresponding sample condition parameters are obtained. Then, the sample condition parameters of adjacent monitoring points are subtracted to determine the pollutant concentration fluctuation between adjacent monitoring points. Pollutant concentration fluctuation includes positive and negative fluctuations. It should be noted that monitoring points are assigned corresponding numbers, starting from the initial water sampling point and increasing sequentially in all directions to ensure that each monitoring point has a unique identifier. When subtracting the sample condition parameters of adjacent monitoring points, the order of numbering is increased. Therefore, a positive fluctuation indicates that the pollutant concentration decreases between adjacent monitoring points, indicating pollution. The direction of diffusion is indicated by negative fluctuations, which represent an increase in pollutant concentration pointing towards the pollution source. During this process, it is necessary to extract the monitoring points where the negative fluctuations transition to positive fluctuations and mark them as potential pollution source nodes. To ensure the accuracy of the pollution source location results, it is also necessary to continue to perform subtraction processing on the monitoring points after the potential pollution source nodes, that is, to continue tracking. When the sample condition parameters under N consecutive monitoring points all show positive fluctuations (N is a natural number greater than 0. Generally speaking, to ensure the accuracy of the source tracing results, the value of N is not less than 3, and the specific value needs to be set according to the actual situation), it means that the concentration of hidden garbage pollutants is the highest at the potential pollution source node. At this time, the area between the potential pollution source node and all adjacent monitoring points will be designated as the pollution source area to facilitate subsequent targeted water treatment.

[0090] S4. Based on the geographical distance between the pollution source and the collected water samples and the trend of water quality changes, predict the diffusion range of hidden garbage pollutants;

[0091] In step S4, after the source of the hidden waste pollutants is determined, the specific diffusion range of the hidden waste pollutants is predicted by analyzing the geographical distance between the pollution source and the collected water samples and the water quality change trend. The step of predicting the diffusion range of the hidden waste pollutants based on the geographical distance between the pollution source and the collected water samples and the water quality change trend includes:

[0092] Obtain the geographical distance between the pollution source and each monitoring point, and record it as a distance parameter;

[0093] Collect the concentration difference of hidden waste pollutants between the pollution source and each monitoring point, and record it as a prediction condition parameter;

[0094] Based on the prediction condition parameters and the distance parameters, the maximum diffusion distance of hidden waste pollutants is predicted, and a diffusion range map of hidden waste pollutants is drawn based on the maximum diffusion distance.

[0095] Specifically, when predicting the spread range of hidden waste pollutants, the geographical distance between the pollution source and each monitoring point is first obtained and recorded as a distance parameter to clearly assess the spread distance of the pollutants. Simultaneously, the concentration difference of hidden waste pollutants between the pollution source and each monitoring point is collected, reflecting the concentration change of pollutants at different locations, and recorded as a prediction condition parameter. Then, by combining the prediction condition parameter and the geographical distance parameter, the maximum spread distance of the hidden waste pollutants can be predicted. First, based on the prediction condition parameter and the distance parameter, the attenuation coefficient of the hidden pollutant concentration during the spread process is calculated, where the attenuation coefficient = (current concentration - initial concentration) / (distance). The attenuation constant (or distance / attenuation constant) can be obtained from historical data and experimental measurements. It describes the rate at which pollutant concentration decreases with increasing distance. The attenuation coefficient can then be used to predict the concentration change of hidden waste pollutants at different distances, thereby determining its maximum diffusion distance (maximum diffusion distance = (attenuation coefficient × distance) / initial concentration). Finally, a corresponding diffusion range map is drawn. Specifically, a circle can be drawn with the pollution source as the center and the maximum diffusion distance as the radius. The area inside the circle is the predicted diffusion range of hidden waste pollutants. Of course, the diffusion range can also be appropriately adjusted according to the actual water flow direction and topographic features to ensure that the prediction results are closer to the actual situation.

[0096] S5. Collect the real-time pollution boundary of hidden garbage pollutants, and combine it with the preset water body intervention improvement time to predict the predicted pollution boundary of hidden garbage pollutants, and delineate the water area between the predicted pollution boundary and the pollution source as the water area to be improved.

[0097] In step S5, when it is determined that there are hidden pollutants in the target water area, corresponding intervention and improvement measures will be implemented to ensure the safety of the target water area. There is a certain time difference between the discovery of pollution and the intervention; this embodiment records this time as the intervention and improvement time. Then, based on the diffusion rate of the hidden pollutants in the target water area and the real-time pollution boundary, the predicted pollution boundary of the hidden pollutants within the intervention and improvement time can be calculated, thereby determining the area of ​​water to be improved. The step of collecting the real-time pollution boundary of the hidden pollutants and predicting the predicted pollution boundary of the hidden pollutants in conjunction with the preset water body intervention and improvement time includes:

[0098] Real-time collection of hidden waste pollutants' real-time pollution boundary, and the distance between the real-time pollution boundary and the maximum diffusion boundary;

[0099] The remaining diffusion time of pollutants is calculated based on the distance between the real-time pollution boundary and the maximum diffusion boundary, combined with the diffusion trend of hidden waste pollutants.

[0100] Compare the remaining dispersion time of pollutants with the time required for water body intervention and improvement;

[0101] When the remaining diffusion time of pollutants is less than the water body intervention and improvement time, the water area between the maximum diffusion boundary and the pollution source is directly designated as the water area to be improved.

[0102] When the remaining diffusion time of pollutants is greater than the water body intervention and improvement time, the predicted pollution boundary is calculated based on the pollutant diffusion trend and the water body intervention and improvement time, and the water area between the predicted pollution boundary and the pollution source is designated as the water area to be improved.

[0103] In the above-mentioned process, when determining the predicted pollution boundary, it is also necessary to consider the time required for hidden pollutants to diffuse to the maximum diffusion boundary. In this implementation method, this time is recorded as the remaining diffusion time of pollutants. That is, when the remaining diffusion time of pollutants is lower than the water body intervention and improvement time, the water area to be improved is directly delineated based on the maximum diffusion boundary, and there is no need to calculate the predicted pollution boundary again, because the pollutants are already close to the maximum diffusion range at this time. Only when the remaining diffusion time of pollutants is higher than the water body intervention and improvement time will the predicted pollution boundary be calculated. Then, the water area between the predicted pollution boundary and the pollution source is delineated as the water area to be improved, ensuring that the intervention measures are timely and effective, preventing further diffusion of pollution, and ensuring the safety of the aquatic environment.

[0104] Please see Figure 2 A system for predicting hidden litter pollutants based on regional water quality, using the aforementioned method for predicting hidden litter pollutants based on regional water quality, includes:

[0105] The data acquisition module is used to collect water quality data and hidden pollutant concentrations in the target water area in real time through pre-deployed water quality sensors;

[0106] The correlation index extraction module is used to obtain historical water quality data and pollution records of the target water area, and extract correlation indicators with pollutant migration from the historical water quality data based on the pollution records.

[0107] The pollution source location module is used to trace the diffusion path of hidden waste pollutants based on real-time collected water quality data and the concentration of hidden waste pollutants, combined with related indicators, and to locate the pollution source based on the diffusion path.

[0108] The prediction module is used to predict the spread range of hidden garbage pollutants based on the geographical distance between the pollution source and the collected water samples and the trend of water quality changes.

[0109] The water area delineation module is used to collect real-time pollution boundaries of hidden waste pollutants, and combine them with preset water body intervention and improvement times to predict the predicted pollution boundaries of hidden waste pollutants. The water area between the predicted pollution boundary and the pollution source is delineated as the water area to be improved.

[0110] In the above-mentioned modules, the data acquisition module is responsible for acquiring real-time water quality data and the concentration of hidden garbage pollutants in the target water area, providing a data foundation for subsequent analysis and processing. The correlation index extraction module uses historical data and pollution records to extract correlation indicators related to pollutant migration. These correlation indicators can reflect the migration characteristics of pollutants under different environmental conditions. The pollution source location module, based on real-time data and correlation indicators, quickly traces the diffusion path of pollutants and locates the pollution source, providing strong support for the control and treatment of pollution sources. The prediction module predicts the diffusion range of hidden garbage pollutants by comprehensively analyzing factors such as the geographical distance between the pollution source and the collected water samples and the trend of water quality changes, providing a scientific basis for the delineation of pollution control areas. The water area delineation module combines real-time pollution boundaries and water body intervention and improvement time to predict the predicted pollution boundary of pollutants within the intervention and improvement time, thereby accurately delineating the water area to be improved, ensuring the effective implementation of treatment measures, and preventing further diffusion of hidden garbage pollutants.

[0111] Please see Figure 3 An electronic device, comprising:

[0112] At least one processor;

[0113] and memory that is communicatively connected to at least one processor;

[0114] The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to perform the aforementioned method for predicting hidden litter pollutants based on regional water quality.

[0115] The processor of the aforementioned electronic device can be a high-performance central processing unit (CPU), whose computing power can ensure the rapid execution of the hidden waste pollutant prediction method, improving prediction efficiency and accuracy. Alternatively, the processor can be a graphics processing unit (GPU), which can accelerate the large amount of data processing involved in the prediction method through parallel computing, shortening the prediction time. In addition, to adapt to different application scenarios and computing needs, the processor can also be a programmable logic device (PLD), such as a field-programmable gate array (FPGA), which can be programmed to implement specific algorithms and functions to meet the customized needs of the hidden waste pollutant prediction method. The memory can be of various types, such as solid-state drives (SSDs) or random access memory (RAMs), to ensure high-speed data reading and writing and smooth program operation. The electronic device can also include an arithmetic logic unit (ALU), input devices, and output devices. The ALU can be an arithmetic logic unit, etc., used to perform complex mathematical operations and logical judgments. Input devices such as keyboards and mice are used to facilitate user input of data and instructions. Output devices such as monitors and printers are used to display prediction results and reports, ensuring timely feedback of information.

[0116] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0117] The above description is merely a preferred embodiment of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention. Structures, devices, and operating methods not specifically described or explained in this invention are implemented according to conventional methods in the art unless otherwise specified or limited.

Claims

1. A method for predicting hidden litter pollutants based on regional water quality, characterized in that: include: Water quality data and the concentration of hidden pollutants in the target water area are collected in real time through pre-deployed water quality sensors; Obtain historical water quality data and pollution records for the target water area, and extract correlation indicators with pollutant migration from the historical water quality data based on the pollution records; Based on real-time collected water quality data and the concentration of hidden waste pollutants, combined with related indicators, the diffusion path of hidden waste pollutants is traced, and the pollution source is located according to the diffusion path; Based on the geographical distance between the pollution source and the collected water samples, and the trend of water quality changes, the diffusion range of hidden garbage pollutants is predicted; The real-time pollution boundary of hidden waste pollutants is collected, and the predicted pollution boundary of hidden waste pollutants is predicted in combination with the preset water body intervention improvement time. The water area between the predicted pollution boundary and the pollution source is designated as the water area to be improved. The step of extracting correlation indicators with pollutant migration from historical water quality data based on pollution records includes: Collect all environmental factors related to the migration of pollutants in water bodies, perform correlation analysis between each environmental factor and the amount and rate of pollutant migration, and output correlation scores; The association score is compared with a preset association threshold; When the correlation score is higher than the correlation threshold, the environmental factor corresponding to the correlation score is directly used as the correlation indicator. When the association score is lower than or equal to the association threshold, the environmental factor corresponding to the association score is labeled as a potential influencing factor. By jointly analyzing potential impact factors and associated indicators, we can determine whether the absence of potential impact factors will affect the migration of pollutants under associated indicators. If they exist, the potential influencing factors will be incorporated into the corresponding related indicators to form a comprehensive related indicator. If it does not exist, the original related indicators will remain unchanged; The step of collecting real-time pollution boundaries of hidden litter pollutants and predicting predicted pollution boundaries of hidden litter pollutants in conjunction with a preset water body intervention and improvement time includes: Real-time collection of hidden waste pollutants' real-time pollution boundary, and the distance between the real-time pollution boundary and the maximum diffusion boundary; The remaining diffusion time of pollutants is calculated based on the distance between the real-time pollution boundary and the maximum diffusion boundary, combined with the diffusion trend of hidden waste pollutants. Compare the remaining dispersion time of pollutants with the time required for water body intervention and improvement; When the remaining diffusion time of pollutants is less than the water body intervention and improvement time, the water area between the maximum diffusion boundary and the pollution source is directly designated as the water area to be improved. When the remaining diffusion time of pollutants is greater than the water body intervention and improvement time, the predicted pollution boundary is calculated based on the pollutant diffusion trend and the water body intervention and improvement time, and the water area between the predicted pollution boundary and the pollution source is designated as the water area to be improved.

2. The method for predicting hidden litter pollutants based on regional water quality according to claim 1, characterized in that: The water quality sensor includes a pH sensor, a dissolved oxygen sensor, a heavy metal ion sensor, and a pollutant sensor. The pH sensor is used to determine the acidity or alkalinity of the target water body, the dissolved oxygen sensor is used to monitor the dissolved oxygen content in the water body, the heavy metal ion sensor is used to detect the concentration of heavy metal ions in the water body, and the pollutant sensor is used to identify the types and concentrations of pollutants in the water body.

3. The method for predicting hidden litter pollutants based on regional water quality according to claim 1, characterized in that: The step of performing correlation analysis between each environmental factor and pollutant migration amount and pollutant migration rate, and outputting a correlation score, includes: Different concentration gradients were set for each environmental factor, and the migration amount and migration rate of pollutants under each concentration gradient were measured and recorded as the first correlation condition parameter and the second correlation condition parameter, respectively. The first and second correlation condition parameters are vectorized. The vectorized first and second correlation condition parameters are fused and calculated, and the fusion calculation result is recorded as the association score.

4. The method for predicting hidden litter pollutants based on regional water quality according to claim 1, characterized in that: The steps for tracing the diffusion path of hidden waste pollutants include: Collect real-time water quality data and hidden pollutant concentrations of the target water area, and compare them with historical water quality data and hidden pollutant concentrations to determine the pollution pattern of the target water area. Multi-directional offset processing is performed on real-time water quality data sampling points to obtain multiple traceability sample points; Identify the differences in the concentration of hidden waste pollutants between each traceable sample point and the real-time water quality sampling point, select the offset direction with the largest concentration difference as the diffusion direction of the hidden waste pollutants, and draw the diffusion path of the hidden waste pollutants in the diffusion direction.

5. The method for predicting hidden litter pollutants based on regional water quality according to claim 1, characterized in that: The step of locating the pollution source based on the diffusion path includes: Multiple monitoring points were set up along the diffusion path of hidden waste pollutants, and the concentration of hidden waste pollutants at each monitoring point was collected and recorded as sample condition parameters. The sample condition parameters at adjacent monitoring points are subtracted to output the pollutant concentration fluctuation, which includes both positive and negative fluctuations. The monitoring points where the negative fluctuations transition to positive fluctuations are located and recorded as potential pollution source nodes. The difference processing is then performed on the monitoring points after the potential pollution source nodes until the sample condition parameters of N consecutive monitoring points all show positive fluctuations. Then, the potential pollution source nodes are determined as pollution sources.

6. The method for predicting hidden litter pollutants based on regional water quality according to claim 5, characterized in that: The step of predicting the diffusion range of hidden waste pollutants based on the geographical distance between the pollution source and the collected water samples and the trend of water quality changes includes: Obtain the geographical distance between the pollution source and each monitoring point, and record it as a distance parameter; Collect the concentration difference of hidden waste pollutants between the pollution source and each monitoring point, and record it as a prediction condition parameter; Based on the prediction condition parameters and the distance parameters, the maximum diffusion distance of hidden waste pollutants is predicted, and a diffusion range map of hidden waste pollutants is drawn based on the maximum diffusion distance.

7. A system for predicting hidden litter pollutants based on regional water quality, characterized in that: The method for predicting hidden litter pollutants based on regional water quality, according to any one of claims 1 to 6, includes: The data acquisition module is used to collect water quality data and hidden pollutant concentrations in the target water area in real time through pre-deployed water quality sensors; The correlation index extraction module is used to obtain historical water quality data and pollution records of the target water area, and extract correlation indicators with pollutant migration from the historical water quality data based on the pollution records. The pollution source location module is used to trace the diffusion path of hidden waste pollutants based on real-time collected water quality data and the concentration of hidden waste pollutants, combined with related indicators, and to locate the pollution source based on the diffusion path. The prediction module is used to predict the spread range of hidden garbage pollutants based on the geographical distance between the pollution source and the collected water samples and the trend of water quality changes. The water area delineation module is used to collect real-time pollution boundaries of hidden litter pollutants, and predict the predicted pollution boundaries of hidden litter pollutants by combining the preset water body intervention and improvement time. The water area between the predicted pollution boundary and the pollution source is delineated as the water area to be improved.

8. An electronic device, characterized in that: The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the method for predicting hidden litter pollutants based on regional water quality as described in any one of claims 1 to 6.

Images