Rainfall runoff pollution early warning system and method

Abstract

The present application relates to the technical field of data processing, and discloses a rainfall runoff pollution early warning system and method, which comprises a sample analysis module, a pollutant model construction module, a water quality prediction module, an early warning signal generation module and a pollution control module. The road surface sediment samples and rainfall runoff samples of a service area are analyzed for physical and chemical properties to obtain pollutant concentration data and pollutant composition data. Based on the dynamic changes of pollutants in the runoff process in the pollutant concentration data and the pollutant composition data, a pollutant migration and transformation model is constructed. Based on the pollutant migration and transformation model, the hydrology and hydrodynamic force of the service area are predicted to obtain the runoff water quality change trend under different rainfall scenarios. When the water quality prediction index in the runoff water quality change trend exceeds the pollution early warning threshold, a pollution early warning signal is generated. The pollution early warning signal is pushed to a management terminal to trigger corresponding runoff pollution control measures. The present application can improve the accuracy of rainfall runoff pollution early warning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a rainfall runoff pollution early warning system and method. BACKGROUND

[0002] The prior art is not comprehensive in analyzing the physicochemical properties of samples in rainfall runoff pollution early warning, only focusing on a single type of sample or limited indicators, and failing to fully combine the pollutant concentration and composition data of road sediment and rainfall runoff samples, resulting in incomplete understanding of pollution sources and characteristics, and providing insufficient accurate basic data for subsequent model construction.

[0003] At the same time, the pollutant migration and transformation model constructed by the prior art lacks deep analysis of the dynamic changes of pollutants, and fails to effectively integrate the experience correlation rules and pollution propagation characteristics in historical monitoring data, making the model insufficient in predicting the water quality changes under different rainfall scenarios. In addition, the linkage between early warning signal generation and pollution control measures is weak, making it difficult to accurately trigger corresponding measures according to the early warning level and pollution area, affecting the timeliness and effectiveness of pollution prevention and control. SUMMARY

[0004] The present application provides a rainfall runoff pollution early warning system and method to solve the problems raised in the background art.

[0005] To achieve the above purpose, the present application provides a rainfall runoff pollution early warning system, characterized in that the system comprises a sample analysis module, a pollutant model construction module, a water quality prediction module, an early warning signal generation module and a pollution control module, wherein:

[0006] The sample analysis module is used to analyze the physicochemical properties of road sediment samples and rainfall runoff samples in the service area, and obtain the pollutant concentration data and pollutant composition data of the service area;

[0007] The pollutant model construction module is used to construct a pollutant migration and transformation model for the service area based on the dynamic changes of pollutants in the runoff process in the pollutant concentration data and the pollutant composition data;

[0008] The water quality prediction module is used to predict the hydrology and hydrodynamics of the service area based on the pollutant migration and transformation model, and obtain the runoff water quality change trend of the service area under different rainfall scenarios;

[0009] The early warning signal generation module is used to generate a pollution early warning signal for the service area when the water quality prediction index in the runoff water quality change trend exceeds the pollution early warning threshold of rainfall runoff;

[0010] The pollution control module is configured to push the pollution early warning signal to a management terminal of the service area, and trigger corresponding runoff pollution control measures.

[0011] In a preferred embodiment, the sample analysis module is configured to perform physicochemical property analysis on road surface deposit samples and rainfall runoff samples of the service area, and obtain pollution concentration data and pollution composition data of the service area.

[0012] collecting road surface deposit samples and runoff samples in a dry period and during a rainfall event at typical positions in the service area;

[0013] grinding and sieving the road surface deposit samples to obtain experimental samples of the service area with a standard particle size;

[0014] determining pollution concentration data in the experimental samples;

[0015] identifying types of organic pollutants in the runoff samples to obtain pollution composition data of the runoff samples.

[0016] In a preferred embodiment, the pollution model construction module is configured to construct a pollution migration and transformation model of the service area based on dynamic changes of pollutants in the runoff process in the pollution concentration data and the pollution composition data.

[0017] extracting initial concentration values and spatiotemporal distribution characteristics of pollutants from the pollution concentration data;

[0018] determining pollution propagation characteristics of the pollutants in the runoff process according to the pollution composition data;

[0019] establishing an empirical correlation rule according to changes of pollutant concentrations with runoff duration and hydraulic conditions in historical rainfall runoff monitoring data;

[0020] constructing a modular rule base of the service area based on the empirical correlation rule and the pollution propagation characteristics;

[0021] integrating the modular rule base and the spatiotemporal distribution characteristics to generate the pollution migration and transformation model of the service area.

[0022] In a preferred embodiment, the pollution model construction module is configured to integrate the modular rule base and the spatiotemporal distribution characteristics to generate the pollution migration and transformation model of the service area.

[0023] matching initial concentration spatial data of the pollutants in the spatiotemporal distribution characteristics with corresponding migration and transformation rules in the modular rule base;

[0024] According to the matching result, a behavior mapping relationship set is established with the pollutant type and spatial position in the pollutant concentration data as indexes;

[0025] According to the mapping relationship set, a simulation verification of a global scale pollutant dynamic process in the service area is performed;

[0026] Based on a verification result of the simulation verification, a structured model expression of pollutant migration from the road surface to the receiving water body in the service area under different rainfall scenarios is generated, and the structured model expression is taken as a pollutant migration and transformation model of the service area.

[0027] In a preferred embodiment, when the water quality prediction module performs hydrological and hydrodynamic prediction in the service area based on the pollutant migration and transformation model to obtain runoff water quality change trends in the service area under different rainfall scenarios, it is specifically used for:

[0028] Obtaining a plurality of preset rainfall scenario parameters of the service area;

[0029] Inputting hydrological and pollution coupling based on the pollutant migration and transformation model for the plurality of preset rainfall scenario parameters to obtain runoff hydrograph and pollutant load flux at the outlet section of the sub-region in the service area;

[0030] Performing time series correlation analysis on the runoff hydrograph and the pollutant load flux to obtain a runoff water quality change trend atlas of the sub-region;

[0031] Extracting a dynamic attribute list of a key water quality index in the runoff water quality change trend atlas, and performing runoff prediction on the service area based on the dynamic attribute list to obtain a runoff water quality change trend of the service area.

[0032] In a preferred embodiment, when the water quality prediction module extracts the dynamic attribute list of the key water quality index in the runoff water quality change trend atlas, it is specifically used for:

[0033] Identifying a feature turning point on a pollutant concentration curve in the runoff water quality change trend atlas;

[0034] According to the distribution of the feature turning point on the time axis, determining the starting phase, peak phase and duration of the change of the key water quality index in the service area;

[0035] According to the quantitative values of the starting phase, the peak phase and the duration, dividing the change intensity level of the change of the key water quality index;

[0036] Spatiotemporal correlation of the change phase of the feature turning point and the change intensity level is performed to obtain the dynamic attribute list of the key water quality index.

[0037] In a preferred implementation, the water quality prediction module, when performing runoff prediction on the service area based on the dynamic attribute list to obtain the runoff water quality change trend of the service area, is specifically configured to:

[0038] obtain the change intensity level and the key time phase of the target pollutant from the dynamic attribute list;

[0039] determine the pollution response time sequence of the sub-area according to the key time phase;

[0040] calculate the predicted concentration time series value of the target pollutant at the outlet section of the sub-area based on the change intensity level and the pollution response time sequence, wherein the calculation formula of the predicted concentration time series value is as follows:

[0041]

[0042] wherein, is the predicted concentration time series value of the service area outlet section at time t, is the pollutant source intensity coefficient determined by the change intensity level, is a natural exponential function, is a comprehensive attenuation coefficient determined based on the underlying surface characteristics in the service area, is the pollutant transport time parameter of the sub-area determined based on the pollution response time sequence.

[0043] In a preferred implementation, the early warning signal generation module, when generating the pollution early warning signal of the service area when the water quality prediction index in the runoff water quality change trend exceeds the pollution early warning threshold of rainfall runoff, is specifically configured to:

[0044] call the early warning concentration limit value matched with the target pollutant from the preset pollution early warning threshold database;

[0045] real-time compare the time series data of the water quality prediction index in the runoff water quality change trend with the early warning concentration limit value;

[0046] when the water quality prediction index of a specific time period continuously exceeds the early warning concentration limit value, determine that the service area has a pollution early warning event of a corresponding level;

[0047] generate the pollution early warning signal of the service area according to the level of the pollution early warning event and the specific time period.

[0048] ​In a preferred embodiment, the pollution control module is specifically used for:

[0049] According to the warning level in the pollution warning signal and the core area, a corresponding control measure instruction set in a preset pollution control strategy library is matched;

[0050] The control measure instruction set is bound with the pollution warning signal to obtain a control instruction data packet of the service area;

[0051] The control instruction data packet is pushed to a corresponding on-site management terminal of the core area in real time;

[0052] After the on-site management terminal receives and analyzes the control instruction data packet, a pollution control process is started.

[0053] In order to solve the above problems, the application also provides a rainfall runoff pollution warning method, which comprises the following steps:

[0054] S1, the physicochemical property analysis of the road surface sediment sample and the rainfall runoff sample of the service area is carried out, and the pollutant concentration data and the pollutant composition data of the service area are obtained;

[0055] S2, based on the dynamic change of the pollutants in the runoff process in the pollutant concentration data and the pollutant composition data, a pollutant migration and transformation model of the service area is constructed;

[0056] S3, based on the pollutant migration and transformation model, the hydrology and hydrodynamics of the service area are predicted, and the runoff water quality change trend of the service area under different rainfall scenarios is obtained;

[0057] S4, when the water quality prediction index in the runoff water quality change trend exceeds the pollution warning threshold of rainfall runoff, a pollution warning signal of the service area is generated;

[0058] S5, the pollution warning signal is pushed to the management terminal of the service area, and a corresponding runoff pollution control measure is triggered.

[0059] Compared with the prior art, the application has the following beneficial effects:

[0060] 1. The application can accurately obtain the pollutant concentration and composition data by comprehensively analyzing the physicochemical properties of the road surface sediment and rainfall runoff sample of the service area, and can fully capture the pollution transmission characteristics and spatial and temporal distribution law by constructing the migration and transformation model combined with the dynamic change of the pollutants in the runoff process, so as to provide a reliable basis for water quality prediction and significantly improve the accuracy of runoff water quality change trend prediction under different rainfall scenarios.

[0061] 2. The present application realizes efficient connection of early warning and prevention and control by comparing the water quality prediction index with the pollution early warning threshold in real time to generate a corresponding grade of early warning signal and push it to the management terminal to trigger targeted control measures, thereby improving the accuracy of rainfall runoff pollution early warning and enhancing the timeliness and effectiveness of pollution control, providing strong support for service area runoff pollution prevention and control. BRIEF DESCRIPTION OF DRAWINGS

[0062] Figure 1 A system architecture diagram of a rainfall runoff pollution early warning system provided by an embodiment of the present application is provided.

[0063] Figure 2 A flowchart of a rainfall runoff pollution early warning method provided by an embodiment of the present application is provided.

[0064] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0065] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments belong to some of the embodiments of the present application but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0066] The terms used in the embodiments of the present application are merely for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms "the" and "said" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Multiple" generally includes at least two.

[0067] Depending on the context, the word "if" or "if" as used herein can be interpreted as "when" or "when" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0068] In addition, the step sequence in each of the following method embodiments is only an example and is not strictly limited.

[0069] In fact, the server device deployed by the rainfall runoff pollution early warning system can be composed of one or more devices. The rainfall runoff pollution early warning system can be implemented as a business instance, a virtual machine, or a hardware device. For example, the rainfall runoff pollution early warning system can be implemented as a business instance deployed on one or more devices in a cloud node. In short, the rainfall runoff pollution early warning system can be understood as a software deployed on a cloud node, which provides a rainfall runoff pollution early warning system for each user terminal. Alternatively, the rainfall runoff pollution early warning system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. The virtual machine has application software installed for managing each user terminal. Alternatively, the rainfall runoff pollution early warning system can also be implemented as a server composed of a plurality of same or different types of hardware devices, and one or more hardware devices are provided to provide a rainfall runoff pollution early warning system for each user terminal.

[0070] In an implementation form, the rainfall runoff pollution early warning system and the user terminal are mutually adapted. That is, the rainfall runoff pollution early warning system is installed as an application on a cloud service platform, and the user terminal is a client that establishes a communication connection with the application; or the rainfall runoff pollution early warning system is implemented as a website, and the user terminal is a webpage; or the rainfall runoff pollution early warning system is implemented as a cloud service platform, and the user terminal is a small program in an instant messaging application.

[0071] As shown in Figure 1 FIG. 1 is a system architecture diagram of a rainfall runoff pollution early warning system according to an embodiment of the present application.

[0072] The rainfall runoff pollution early warning system 100 can be provided in a cloud server, and in an implementation form, can be one or more service devices, or can be installed as an application on a cloud (such as a server of a mobile service operator, a server cluster, etc.), or can be developed as a website. According to the functions implemented, the rainfall runoff pollution early warning system 100 can include a sample analysis module 101, a pollutant model construction module 102, a water quality prediction module 103, an early warning signal generation module 104, and a pollution control module 105. The modules of the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, and are stored in the memory of the electronic device.

[0073] In this embodiment of the invention, in a rainfall runoff pollution early warning system, each of the above-mentioned modules can be implemented independently and can call other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. In the rainfall runoff pollution early warning system provided by this embodiment of the invention, the applicable scope of a rainfall runoff pollution early warning system architecture can be adjusted by adding modules and directly calling them without modifying the program code, achieving cluster-based horizontal expansion to quickly and flexibly expand the rainfall runoff pollution early warning system. In practical applications, the above-mentioned modules can be set in the same device or different devices, or they can be set in a virtual device, such as a service instance in a cloud server.

[0074] The following describes, with reference to specific embodiments, each component of a rainfall runoff pollution early warning system and its specific workflow:

[0075] The sample analysis module 101 is used to perform physicochemical property analysis on road surface sediment samples and rainfall runoff samples in the service area to obtain pollutant concentration data and pollutant composition data of the service area.

[0076] In this embodiment of the invention, when the sample analysis module performs physicochemical property analysis on road surface sediment samples and rainfall runoff samples from the service area to obtain pollutant concentration data and pollutant composition data for the service area, it is specifically used for:

[0077] Collect dry-period pavement sediment samples and runoff samples during rainfall events at typical locations within the service area;

[0078] The road surface sediment samples were ground and sieved to obtain experimental samples of the service area with standard particle size.

[0079] Measure the concentration data of pollutants in the experimental sample;

[0080] Identify the types of organic pollutants in the runoff sample to obtain pollutant composition data of the runoff sample.

[0081] Specifically, when collecting road surface sediment samples during the dry season and runoff samples during rainfall events at typical locations within the service area, areas where pollutants are prone to accumulate, such as main roads with high traffic volume, parking lot entrances and exits, and the area around refueling areas, were selected as typical locations.

[0082] Furthermore, during prolonged dry periods with no rainfall, surface deposits at the aforementioned typical locations were collected using a clean sampling shovel, placed in clean polyethylene sample bags, and labeled as dry period road surface deposit samples.

[0083] Further, during the rainfall process, when the runoff is formed and the flow is stable, the runoff sample is collected at the main drainage outlet in the service area using a pre-cleaned polyethylene container, ensuring that the container is completely immersed in the runoff to avoid collecting surface floating matter, and after collection, it is sealed and marked as a runoff sample in the rainfall event.

[0084] Further, when grinding and screening the road sediment sample to obtain the standard particle size experimental sample of the service area, the dry period road sediment sample is taken out, laid flat on a clean porcelain plate, and placed in an oven at an appropriate temperature to dry to a constant weight.

[0085] Further, the dried sample is taken out and placed in an agate mortar, and repeatedly ground with a pestle until there is no obvious particulate matter in the sample; the ground sample is poured into a pre-cleaned and dried standard sieve, and the sieve is shaken horizontally for a certain period of time, and the sample that passes through the sieve is collected in a clean sample bottle. This part of the sample is the experimental sample of the service area with standard particle size.

[0086] Further, when measuring the pollutant concentration data in the experimental sample, a certain amount of sample is taken from the experimental sample and placed in a polytetrafluoroethylene digestion tube, an appropriate amount of mixed digestion solution is added, the tube is covered and placed in a microwave digestion instrument, and the digestion is carried out according to the preset program.

[0087] Further, after digestion is complete, the digestion tube is cooled to room temperature, and the digestion solution is filtered into a volumetric flask. The digestion tube and filter paper are washed several times with deionized water, and the washing liquid is transferred into the volumetric flask. Finally, the volume is adjusted with deionized water.

[0088] Further, the concentration of heavy metal elements such as lead, zinc, and copper in the solution is measured using an atomic absorption spectrophotometer, and the concentration of total nitrogen and total phosphorus is measured using a UV-visible spectrophotometer. All measurements are performed in multiple parallel experiments, and the average value is taken as the pollutant concentration data in the experimental sample.

[0089] Further, when identifying the types of organic pollutants in the runoff sample to obtain the pollutant composition data of the runoff sample, a certain amount of runoff sample in the rainfall event is taken and poured into a separatory funnel, an appropriate amount of n-hexane is added, the separatory funnel is shaken for a certain period of time, and then left to stand for a period of time. After the liquid is layered, the lower aqueous phase is discharged, and the upper organic phase is collected into a rotary evaporation flask.

[0090] Further, the above extraction process is repeated several times, and the organic phases obtained by multiple extractions are combined and placed in a rotary evaporator under reduced pressure at an appropriate temperature water bath condition, and concentrated to a certain volume; the concentrated solution is filtered through an organic phase filter membrane with an appropriate pore size, and transferred to a sample bottle.

[0091] Further, the filtrate is analyzed by using a gas chromatograph-mass spectrometer, a suitable type of capillary column is selected for the chromatographic column, helium is used as the carrier gas, and a certain flow rate and temperature program are set.

[0092] Further, an electron impact ion source is used for the mass spectrometer, and a certain scanning range is set; the detected mass spectrum is compared with a standard spectrum library, and substances with a high matching degree are identified as organic pollutants present in the runoff sample, the names of these organic pollutants are recorded, and the pollutant composition data of the runoff sample are formed.

[0093] In summary, the dry period road surface deposit samples at typical positions in the service area and the runoff samples in the rainfall event are collected, the pollution conditions of the areas where pollutants are prone to accumulate can be captured, the pollution background and migration state in the dry period and the rainfall period are covered, and comprehensive sample basis is provided for subsequent analysis.

[0094] In summary, the standard particle size experimental samples are obtained by grinding and screening the road surface deposit samples, the interference of particle size difference on the detection results can be eliminated, the uniformity and representativeness of the experimental samples are ensured, and the accuracy of the determination of the pollutant concentration is improved.

[0095] In summary, the pollutant concentration data in the experimental samples are determined, the specific content of the pollutants in the road surface deposit can be accurately mastered, a quantitative basis for analyzing the pollution degree and source is provided, and the pollutant migration and transformation model is supported by basic data.

[0096] In summary, the types of organic pollutants in the runoff sample are identified to obtain the pollutant composition data, the specific components of the organic pollutants in the rainfall runoff can be determined, the deficiency of inorganic pollutant analysis is supplemented, the chemical composition characteristics of pollution are comprehensively reflected, and more detailed pollution information is provided for subsequent targeted prevention and control.

[0097] The pollutant model construction module 102 is configured to construct a pollutant migration and transformation model of the service area based on dynamic changes of pollutants in the runoff process in the pollutant concentration data and the pollutant composition data.

[0098] In the embodiment of the present application, when the pollutant model construction module is used to construct the pollutant migration and transformation model of the service area based on the dynamic changes of pollutants in the runoff process in the pollutant concentration data and the pollutant composition data, it is specifically used for:

[0099] extracting initial concentration values and spatiotemporal distribution characteristics of the pollutants from the pollutant concentration data;

[0100] determining pollution propagation characteristics of the pollutants in the runoff process according to the pollutant composition data;

[0101] According to the historical rainfall runoff monitoring data, an empirical correlation rule is established for the change of pollutant concentration with runoff duration and hydraulic condition;

[0102] Based on the empirical correlation rule and the pollution propagation characteristics, a modular rule library of the service area is constructed;

[0103] The modular rule library and the spatio-temporal distribution characteristics are integrated to generate a pollutant migration and transformation model of the service area.

[0104] When the pollutant model construction module integrates the modular rule library and the spatio-temporal distribution characteristics to generate the pollutant migration and transformation model of the service area, it is specifically used for:

[0105] Matching the initial concentration spatial data of the pollutant in the spatio-temporal distribution characteristics with the corresponding migration and transformation rules in the modular rule library;

[0106] According to the matching result, a set of behavior mapping relationships is established with the pollutant type and spatial position in the pollutant concentration data as the index;

[0107] According to the set of mapping relationships, the simulation and verification of the dynamic process of the pollutant in the service area at the global scale are performed;

[0108] Based on the verification result of the simulation and verification, a structured model expression of the pollutant migration and transformation from the road surface to the receiving water body in the service area under different rainfall scenarios is generated, and the structured model expression is taken as the pollutant migration and transformation model of the service area.

[0109] Specifically, when extracting the initial concentration value and spatio-temporal distribution characteristics of the pollutant from the pollutant concentration data, the pollutant concentration data of the road surface sediment sample and the runoff sample at the monitoring start time are selected as the initial concentration value; the data is classified and arranged according to different sampling time points and positions, the concentration values at each time point and position are recorded, the distribution difference is presented through drawing curves and charts, and the spatio-temporal distribution characteristics are obtained.

[0110] Further, when determining the pollution propagation characteristics according to the pollutant composition data, the types of organic and inorganic pollutants are sorted out, and their physical and chemical properties such as solubility, density, adsorbability, etc. are analyzed.

[0111] Further, it is judged that the easily soluble pollutants diffuse in dissolved state, the pollutants with large density or easy to be adsorbed are easy to settle or migrate with particulate matter, and the diffusion speed, migration direction and aggregation rule are comprehensively determined to obtain the pollution propagation characteristics.

[0112] Further, the empirical correlation rules are established according to historical rainfall runoff monitoring data. Monitoring data of multiple past rainfalls are collected, and hydraulic conditions such as runoff duration, flow rate, water depth and corresponding pollutant concentrations are extracted. The rainfalls are grouped according to rainfall events, and the variation law of the concentration with the runoff duration and the hydraulic conditions is analyzed to form descriptive rules, thereby forming the empirical correlation rules.

[0113] Further, when the modular rule base is constructed based on the empirical correlation rules and the pollutant propagation characteristics, the empirical correlation rules are classified according to the types of the hydraulic conditions to form hydraulic condition correlation modules, and the pollutant propagation characteristics are classified according to the types of the pollutants or the propagation modes to form propagation characteristic modules. The modules are integrated to establish a structured storage system, thereby obtaining the modular rule base.

[0114] Further, when the pollutant migration and transformation model is generated by integrating the modular rule base and the spatiotemporal distribution characteristics, the rules in the rule base are corresponded to the framework based on the time and space dimensions of the spatiotemporal distribution characteristics. The rules and the framework are combined through a computer program, and input and output items are set to enable the model to dynamically calculate the concentration variation and the form transformation of the pollutants, thereby generating the pollutant migration and transformation model.

[0115] Specifically, when the pollutant initial concentration spatial data in the spatiotemporal distribution characteristics is matched with the corresponding migration and transformation rules in the modular rule base, the pollutant initial concentration spatial data containing the position information and the corresponding initial concentration is formed by extracting the pollutant initial concentration data of different spatial positions from the spatiotemporal distribution characteristics.

[0116] Further, the modular rule base is consulted again, and the migration and transformation rules for the type of the pollutant at the type of the spatial position are searched in the rule base according to the type of the pollutant and the environmental characteristics of the spatial position. The initial concentration data of each spatial position is corresponded to the searched corresponding rules one by one to ensure that the initial concentration of a type of pollutant at a position is matched with the migration and transformation rule applicable to the pollutant at the position, thereby completing the matching process.

[0117] Further, according to the matching result, the behavior mapping relationship set is established by taking the type of the pollutant and the spatial position in the pollutant concentration data as indexes. The specific type of each type of pollutant and the spatial position thereof are extracted from the matching result. The combination of the type of the pollutant and the spatial position is taken as an index for retrieval, and is corresponded to the behavior of the pollutant described in the matched migration and transformation rule.

[0118] Further, all the index and corresponding behavior association relationships are sorted into a set, wherein each entry contains the type of the pollutant, the spatial position and the corresponding migration and transformation behavior description, thereby forming the behavior mapping relationship set.

[0119] Further, according to the mapping relationship set, when simulating and verifying the dynamic process of the pollutants in the service area at the global scale, the entire service area is taken as the simulation range, covering all sampling locations and runoff paths connecting these locations; based on the behavior mapping relationship set, the dynamic changes of the pollutants in the rainfall process are simulated in chronological order, including the processes of being washed away from the initial location by rainwater, migrating along the runoff in different areas, settling or dissolving due to physical and chemical properties, and changes in concentration over time and space.

[0120] Further, at the same time, the pollutant concentration monitoring data of different locations in the historical rainfall events of the service area are called, and the simulated dynamic change results of the pollutants are compared with the historical monitoring data. If the simulated concentration at a certain location at a certain time deviates greatly from the actual monitoring concentration, the mapping relationship set is traced back, the corresponding migration and transformation rules are checked for applicability, the rules are adjusted, and the simulation is re-performed until the simulation results are consistent with the historical data trend, and the simulation verification at the global scale is completed.

[0121] Further, based on the verification results of the simulation verification, a structured model expression of the pollutants in the service area from the road surface to the receiving water body under different rainfall scenarios is generated. When the structured model expression is taken as the pollutant migration and transformation model of the service area, different rainfall scenarios are first set, including light rain, moderate rain, heavy rain, and different rainfall durations.

[0122] Further, for each scenario, according to the behavior mapping relationship set confirmed after the simulation verification, the entire process of the pollutants being washed away from the road surface by rainwater, entering the runoff system, flowing along the drainage path, passing through the catchment area in the service area, and finally entering the receiving water body is simulated, and the concentration changes, migration paths, and transformation forms of the pollutants at each link are recorded.

[0123] Further, these simulation results are arranged into a structured framework containing time dimension, space dimension, and pollutant behavior dimension, and the pollutant states and associated relationships of each node under different scenarios are clearly marked in the framework. The structured model expression is the pollutant migration and transformation model of the service area.

[0124] In summary, the initial concentration and spatiotemporal distribution characteristics are extracted from the pollutant concentration data, the initial state and distribution differences of the pollutants are clearly defined, and the model is provided with a benchmark and rules to ensure accurate depiction of the initial state.

[0125] In summary, the propagation characteristics are determined according to the pollutant composition data, the diffusion and migration rules are clearly defined in combination with the physical and chemical properties, and the model is improved in terms of the pertinence of the simulation of the pollution process.

[0126] In summary, the experience correlation rules are established based on historical data, the change rules of concentration and runoff duration, and hydraulic conditions are integrated to enhance the fitting degree of the model to the actual situation.

[0127] Overall, based on the empirical rule and the propagation characteristics, a modular rule base is constructed, the rules are stored in a structured manner, and the model provides a clear framework.

[0128] Overall, the rule base is integrated with the space-time distribution characteristics to generate a migration and transformation model, which combines dynamic rules and distribution characteristics to simulate the whole process and improve prediction accuracy, providing a reliable tool for water quality prediction.

[0129] Overall, the initial concentration of pollutants in the space-time distribution characteristics is matched with the corresponding migration and transformation rules in the modular rule base, so that the initial concentration of different spatial positions can accurately correspond to the applicable migration rules, forming an effective association and providing precise basic association data for model construction.

[0130] Overall, according to the matching results, a behavior mapping relationship set is established based on the pollutant type and spatial position as the index, so that the pollutant type, position and its migration and transformation behavior are clearly corresponding, and the behavior characteristics of various pollutants in different regions are presented, providing structured behavior basis for subsequent simulation.

[0131] Overall, according to the mapping relationship set, the dynamic process of pollutants in the service area is simulated and verified at the global scale, and the dynamic changes such as migration and transformation of pollutants in the entire service area are simulated, and the rules are adjusted by comparing with historical data to ensure that the simulation results fit the actual situation and improve the reliability of the model.

[0132] Overall, based on the simulation verification results, a structured model expression of pollutants from the road surface to the receiving water body under different rainfall scenarios is generated as a migration and transformation model, which fully reflects the whole process of pollutants from generation to entering the receiving water body under different rainfall conditions, and the model structure is clear and covers the time and space dimensions, which can accurately predict the pollution changes under different scenarios, providing high-quality model support for water quality prediction.

[0133] The water quality prediction module 103 is configured to predict the hydrology and hydrodynamics of the service area based on the pollutant migration and transformation model, and obtain the runoff water quality change trend of the service area under different rainfall scenarios.

[0134] In the embodiment of the present application, when the water quality prediction module performs prediction of the hydrology and hydrodynamics of the service area based on the pollutant migration and transformation model, and obtains the runoff water quality change trend of the service area under different rainfall scenarios, it is specifically used for:

[0135] Obtain a plurality of preset rainfall scenario parameters of the service area;

[0136] Input the hydrology and pollution coupling of the plurality of preset rainfall scenario parameters based on the pollutant migration and transformation model, and obtain the runoff process line and pollutant load flux of the outlet cross section of the sub-region in the service area;

[0137] performing time-series correlation analysis on the runoff hydrograph and the pollutant load flux to obtain a runoff water quality change trend atlas of the sub-region;

[0138] extracting a dynamic attribute list of a key water quality index in the runoff water quality change trend atlas, and performing runoff prediction on the service area based on the dynamic attribute list to obtain a runoff water quality change trend of the service area.

[0139] When the water quality prediction module performs extraction of the dynamic attribute list of the key water quality index in the runoff water quality change trend atlas, it is specifically used for:

[0140] identifying feature turning points on a pollutant concentration curve in the runoff water quality change trend atlas;

[0141] determining a starting phase, a peak phase and a duration of a change of a key water quality index in the service area according to a distribution of the feature turning points on a time axis;

[0142] dividing a change intensity level of the change of the key water quality index according to quantitative values of the starting phase, the peak phase and the duration;

[0143] spatiotemporally correlating a change phase of the feature turning points with the change intensity level to obtain the dynamic attribute list of the key water quality index.

[0144] When the water quality prediction module performs runoff prediction on the service area based on the dynamic attribute list to obtain a runoff water quality change trend of the service area, it is specifically used for:

[0145] obtaining a change intensity level and a key time phase of a target pollutant from the dynamic attribute list;

[0146] determining a pollution response time sequence of the sub-region according to the key time phase;

[0147] calculating a predicted concentration time series value of the target pollutant at an outlet section of the sub-region based on the change intensity level and the pollution response time sequence, wherein a calculation formula of the predicted concentration time series value is as follows:

[0148]

[0149] wherein, is a predicted concentration time series value of the service area outlet section at time t, is a pollutant source intensity coefficient determined according to the change intensity level, is a natural exponential function, is a comprehensive attenuation coefficient determined based on a surface feature of the service area,​ the sub-area pollutant transport time parameter determined based on the pollution response time series.

[0150] Specifically, when obtaining multiple preset rainfall scenario parameters of the service area, historical rainfall data of the region is collected, covering characteristics of different intensities, durations, and frequencies, combined with local meteorological department rainfall grade classification standards, multiple scenarios containing rainfall intensity, duration, and other parameters are set, and are arranged as structured data sets as the basis for subsequent prediction input.

[0151] Further, when hydrology and pollution coupling is performed on the multiple preset rainfall scenario parameters based on the pollutant migration and transformation model to obtain the runoff process line and pollutant load flux of the outlet section of the sub-area in the service area, each scenario parameter is input into the model one by one, the model simulates the runoff process of each sub-area, forms the runoff process line of the outlet section, and calculates the pollutant load flux by combining the initial concentration of the pollutant and the migration and transformation rule, to ensure that the two correspond to the corresponding scenario parameter one by one.

[0152] Further, when the runoff process line and the pollutant load flux are subjected to time series correlation analysis to obtain the runoff water quality change trend spectrum of the sub-area, the curves of the two are plotted in the same coordinate system with time as the horizontal axis, the synchronization of the change is analyzed, different colors are used to mark the trajectories and key time nodes, and the spectrum is formed to directly show the change rule of the runoff water quality of the sub-area with time.

[0153] Further, the dynamic attribute list of the key water quality indicators in the runoff water quality change trend spectrum is extracted, and the runoff of the service area is predicted based on the dynamic attribute list to obtain the runoff water quality change trend of the service area. The key water quality indicators are selected from the spectrum, the dynamic attributes are extracted to form a list, the change trend is integrated in combination with the spatial position of the sub-area and the drainage connection mode, the migration and transfer of the pollutant are simulated, and the overall change rule of the runoff water quality of the entire service area with time is obtained.

[0154] Specifically, when identifying the characteristic turning points on the pollutant concentration curve in the runoff water quality change trend spectrum, the curve trend is observed, and positions where the slope changes significantly are focused on, such as the starting point of the concentration rising, the inflection point of the rising speed, the vertex of the highest value, the inflection point of the falling speed, and the endpoint of the stable trend. These points are marked in the spectrum to clearly indicate the specific positions.

[0155] Further, the starting phase, peak phase, and duration of the change of the key water quality indicators are determined according to the distribution of the characteristic turning points on the time axis. The time scale corresponding to each turning point is viewed, the starting time of the concentration rising is determined as the starting phase, the vertex time of the highest concentration value is determined as the peak phase, and the time interval from the starting phase to the stable endpoint of the concentration is calculated as the duration, to ensure accurate correspondence with the time axis moment.

[0156] Further, when dividing the change intensity level according to the quantized values of the starting phase, peak phase and duration, the change intensity is divided into strong, medium and weak levels in combination with the peak concentration value and duration, compared with the time interval from the starting to the peak. The strong level is fast rising, high peak and long duration, the medium level is slow rising, medium peak and medium duration, and the weak level is slow rising, low peak and short duration.

[0157] Further, when obtaining the dynamic attribute list by spatiotemporally correlating the change phase of the characteristic turning point and the change intensity level, the starting phase, peak phase and change intensity level of each index are corresponded in units of key water quality indicators, and the spatial position where the change occurs is marked. The structured list is classified and arranged according to the index, including the index name, each phase time and position, and the change intensity level.

[0158] Specifically, when obtaining the change intensity level and key time phase of the target pollutant from the dynamic attribute list, the target pollutant to be predicted is determined, the corresponding entry is searched in the list, and the change intensity level and key time phase are extracted to ensure that the information matches the target pollutant and provide basic data for subsequent prediction.

[0159] Further, when determining the pollution response time sequence of the sub-region according to the key time phase, the starting phase is taken as the starting point, the peak phase is taken as the key node, and the response end time point is determined in combination with the duration. The time period is divided into continuous time intervals as sequence units in time sequence, the time range of each unit is determined, and the time sequence covering the whole pollution process is formed.

[0160] Further, when calculating the predicted concentration time series value of the target pollutant at the outlet section of the sub-region based on the change intensity level and the pollution response time sequence, the concentration change rate is determined according to the level. The strong level corresponds to fast rising, high peak and slow falling, the medium level corresponds to medium rate and peak, and the weak level corresponds to slow rising, low peak and fast falling. The concentration is calculated in each time unit according to the rate, from the initial concentration to the peak and then to the stable. The concentration of each unit is arranged in time to obtain the predicted concentration time series value.

[0161] Specifically, the pollutant source intensity coefficient determined by the change intensity level is obtained from the change intensity level in the dynamic attribute list. The strong level corresponds to a larger source intensity coefficient, the medium level corresponds to a medium source intensity coefficient, and the weak level corresponds to a smaller source intensity coefficient. The coefficient directly reflects the initial release ability of the target pollutant under different intensity levels.

[0162] Further, the comprehensive attenuation coefficient determined based on the characteristics of the underlying surface in the service area is obtained from an on-site investigation of the underlying surface in the service area. The characteristics of the underlying surface include road surface material, vegetation coverage, drainage facility type, etc. By analyzing the adsorption, filtration and degradation of pollutants by these characteristics, the attenuation degree of the pollutant concentration under different underlying surface conditions is determined, and then the comprehensive attenuation coefficient is obtained.

[0163] Further, the pollutant transport time parameter of the sub-area determined based on the pollution response time sequence is obtained from the pollution response time sequence, which covers the entire time period from the initial phase to the end of the response. The transport time parameter is determined according to the time interval of the migration of pollutants from the interior of the sub-area to the outlet section in the sequence, and directly reflects the migration speed of the pollutants in the sub-area.

[0164] Further, the pollutant source strength coefficient determined by the change in intensity level is combined with the calculation based on the comprehensive attenuation coefficient and the pollutant transport time parameter of the sub-area in the natural exponential function to obtain the predicted concentration time sequence value of the outlet section of the service area at the moment, which comprehensively reflects the initial release intensity of the pollutants, the attenuation degree in the migration process, and the influence of the migration time on the concentration, and is used for accurately predicting the pollutant concentration of the outlet section at different moments.

[0165] Further, when other conditions remain unchanged, the pollutant source strength coefficient determined by the change in intensity level increases, the predicted concentration time sequence value of the outlet section of the service area at the moment increases; the pollutant source strength coefficient determined by the change in intensity level decreases, the predicted concentration time sequence value of the outlet section of the service area at the moment decreases.

[0166] Further, when other conditions remain unchanged, the comprehensive attenuation coefficient determined based on the characteristics of the underlying surface in the service area increases, and the result of the natural exponential function decreases, the predicted concentration time sequence value of the outlet section of the service area at the moment decreases; the comprehensive attenuation coefficient determined based on the characteristics of the underlying surface in the service area decreases, and the result of the natural exponential function increases, the predicted concentration time sequence value of the outlet section of the service area at the moment increases.

[0167] Further, when other conditions remain unchanged, the pollutant transport time parameter of the sub-area determined based on the pollution response time sequence increases, and the result of the natural exponential function increases, the predicted concentration time sequence value of the outlet section of the service area at the moment increases; the pollutant transport time parameter of the sub-area determined based on the pollution response time sequence decreases, and the result of the natural exponential function decreases, the predicted concentration time sequence value of the outlet section of the service area at the moment decreases.

[0168] Overall, obtaining multiple preset rainfall scenario parameters can cover different rainfall characteristics, provide diverse inputs for prediction, and ensure effective prediction of water quality changes under various scenarios.

[0169] Overall, based on the model, the hydrology and pollution are coupled with the preset rainfall parameters to obtain the runoff process line and pollutant load flux of the sub-region. This can combine hydrology and pollution rules, capture the runoff and pollution changes during rainfall in the sub-region, and provide specific data support.

[0170] Overall, the time series correlation analysis of runoff and pollutant load can obtain the water quality change trend map of the sub-region, which can intuitively show the time correlation law of the two and present the influence of runoff on pollutant load, providing visual basis.

[0171] Overall, extracting the dynamic attribute list of key water quality indicators and predicting based on it can focus on core features and integrate sub-region trends, achieving comprehensive and accurate prediction of water quality changes in service areas under different rainfall scenarios, and providing reliable basis for subsequent early warning and control.

[0172] Overall, identifying the characteristic turning points on the pollutant concentration curve can capture key nodes and provide clear time markers for analyzing water quality dynamic changes, ensuring that key stages are not missed.

[0173] Overall, determining the starting phase, peak phase, and duration according to the distribution of characteristic turning points on the time axis can clearly define the water quality change stages and duration, providing precise time dimension data.

[0174] Overall, dividing the change intensity level according to the quantitative values of the starting phase, peak phase, and duration can comprehensively evaluate the change intensity and achieve scientific classification, enhancing the understanding of the change degree.

[0175] Overall, obtaining the dynamic attribute list by spatiotemporal correlation of change phase and intensity level can integrate time, intensity, and spatial information, providing comprehensive and accurate dynamic basis for subsequent runoff prediction, and improving prediction reliability.

[0176] Overall, obtaining the change intensity level and key time phase of the target pollutant from the dynamic attribute list can extract core feature parameters, ensuring that runoff prediction focuses on the intensity and time node of specific pollutants, and avoiding parameter generalization bias.

[0177] Overall, determining the pollution response time series of the sub-region according to the key time phase can clearly define the complete time process of pollution, convert abstract phases into continuous time units, provide a clear framework for concentration time series simulation, and cover the entire cycle of pollution response.

[0178] In general, the predicted concentration time series value is calculated based on the change intensity level and the pollution response time series, which can combine the concentration change rate corresponding to the intensity and the time unit, and dynamically simulate the whole process of concentration change, so that it is more in line with the actual migration law.

[0179] In general, the formula integrates the source intensity coefficient, the comprehensive attenuation coefficient and the transport time parameter, comprehensively reflects the influence of initial release intensity, attenuation effect and transport time, covers multiple dimensions, improves the concentration prediction accuracy, and provides reliable data for grasping the runoff water quality change trend.

[0180] The early warning signal generation module 104 is configured to generate a pollution early warning signal of the service area when the water quality prediction index in the runoff water quality change trend exceeds the pollution early warning threshold of rainfall runoff.

[0181] In the embodiment of the present application, when the early warning signal generation module generates a pollution early warning signal of the service area when the water quality prediction index in the runoff water quality change trend exceeds the pollution early warning threshold of rainfall runoff, it is specifically used for:

[0182] Calling the early warning concentration limit value matched with the target pollutant from the preset pollution early warning threshold database;

[0183] Real-time comparison of the time series data of the water quality prediction index in the runoff water quality change trend with the early warning concentration limit value;

[0184] When the water quality prediction index in a specific time period continuously exceeds the early warning concentration limit value, it is determined that a pollution early warning event of a corresponding level occurs in the service area;

[0185] According to the level of the pollution early warning event and the specific time period, a pollution early warning signal of the service area is generated.

[0186] Specifically, when the early warning concentration limit value matched with the target pollutant is called from the preset pollution early warning threshold database, the database stores the early warning concentration limit values corresponding to various pollutants, which are set according to relevant standards and the environmental sensitivity of the service area; after the target pollutant is determined, the corresponding limit value is retrieved and extracted by name or code, so as to ensure the matching with the target pollutant.

[0187] Further, when the time series data of the water quality prediction index in the runoff water quality change trend is compared with the early warning concentration limit value in real time, the water quality prediction index values at each time point are extracted in time sequence from the time series data, and are compared with the early warning concentration limit value one by one, whether the limit value is exceeded is recorded, and a comparison result sequence is formed, so that each time point data is compared.

[0188] Further, when the water quality prediction index of a specific time period continuously exceeds the early warning concentration limit value, it is determined that a pollution early warning event of a corresponding level occurs in the service area, and the specific time period is a preset time length for judging the pollution duration; the comparison result is checked, if the value in a certain continuous specific time period exceeds the limit value, the early warning determination is triggered, and the early warning level is determined according to the preset level standard combined with the exceeding standard.

[0189] Further, according to the level of the pollution early warning event and the specific time period, a pollution early warning signal of the service area is generated, the signal contains information such as early warning level, specific time period, target pollution type and service area name, and these information is integrated in a preset format to form a pollution early warning signal that can trigger subsequent measures.

[0190] In general, the matching early warning concentration limit value is called from the preset database to ensure that the threshold value is accurately corresponding to the pollutant, avoid misjudgment and omission, and provide scientific judgment standard.

[0191] In general, the water quality prediction time series data is compared with the early warning limit value in real time, the change is dynamically tracked, and the exceeding is found in time, which lays the foundation for rapid response.

[0192] In general, when the specific time period continuously exceeds the limit value, the corresponding level early warning event is determined, the instantaneous exceeding is avoided, the level division reflects the pollution degree, and the early warning reliability and distinguishability are improved.

[0193] In general, the signal is generated according to the early warning level and the specific time period, which contains the pollution severity and duration, provides clear basis for subsequent prevention and control, and ensures the pertinence of measures.

[0194] The pollution control module 105 is configured to push the pollution early warning signal to the management terminal of the service area, and trigger corresponding runoff pollution control measures.

[0195] In the embodiment of the application, when the pollution control module pushes the pollution early warning signal to the management terminal of the service area and triggers the corresponding runoff pollution control measures, it is specifically used for:

[0196] According to the early warning level in the pollution early warning signal and the core area, the corresponding control measure instruction set in the preset pollution control strategy library is matched;

[0197] The control measure instruction set and the pollution early warning signal are bound to obtain the control instruction data packet of the service area;

[0198] The control instruction data packet is pushed to the corresponding field management terminal of the core area in real time;

[0199] After the field management terminal receives and analyzes the control instruction data packet, the pollution control process is started.

[0200] Specifically, when matching the corresponding control measure instruction set in the preset pollution control strategy library according to the warning level in the pollution warning signal and the core area, the preset strategy library stores the control measures instructions corresponding to different warning levels and core areas, including emergency dredging and other operations; the warning level and the core area are extracted from the warning signal, and the corresponding entry is found by joint searching the strategy library to extract the instruction set containing operation steps, equipment, and responsible person, ensuring matching with the warning level and the core area.

[0201] Further, when binding the control measure instruction set with the pollution warning signal to obtain the control instruction data packet of the service area, merging the two parts of information into a structured data packet through a data integration tool, the warning signal as the header and the instruction set as the main body, adding a unique identification number to form the control instruction data packet.

[0202] Further, when pushing the control instruction data packet to the on-site management terminal corresponding to the core area in real time, the on-site management terminal corresponding to the core area is pre-allocated, the terminal identification is queried through the wireless communication network, the data packet format is converted and sent, and the receiving confirmation feedback ensures the success of the push.

[0203] Further, when the on-site management terminal receives and parses the control instruction data packet and starts the pollution control process, the terminal receives the data packet and decodes, separates the warning signal and the instruction set and displays, the management personnel start the equipment according to the steps to execute the operation, and record the operation to form the start record.

[0204] In summary, according to the matching of the warning level and the core area corresponding to the control measure instruction set, the control measures can be accurately matched with the pollution degree and range, avoiding insufficient response or resource waste, and improving the pertinence and effectiveness.

[0205] In summary, binding the control measure instruction set with the warning signal into a control instruction data packet can integrate the warning information and operation instructions, avoid information dispersion leading to deviation or omission, and provide complete basis for rapid response.

[0206] In summary, pushing the control instruction data packet to the on-site management terminal corresponding to the core area in real time can quickly deliver information and instructions, reduce delay, accurately locate the terminal, and improve the timeliness and accuracy of response.

[0207] In summary, the on-site management terminal parses and starts the pollution control process, which can quickly and clearly inform the management personnel of the pollution situation and operation steps, ensure the implementation of the measures, form a closed-loop management, improve the execution and traceability, and ensure the effectiveness of prevention and control.

[0208] Reference Figure 2As shown, a flowchart of a rainfall runoff pollution early warning method provided by an embodiment of the present application is shown. In this embodiment, the rainfall runoff pollution early warning method comprises the following steps:

[0209] S1, performing physicochemical property analysis on road sediment samples and rainfall runoff samples in a service area to obtain pollutant concentration data and pollutant composition data of the service area;

[0210] S2, constructing a pollutant migration and transformation model of the service area based on dynamic changes of pollutants in the runoff process in the pollutant concentration data and the pollutant composition data;

[0211] S3, predicting hydrology and hydrodynamics of the service area based on the pollutant migration and transformation model to obtain runoff water quality change trends of the service area under different rainfall scenarios;

[0212] S4, generating a pollution early warning signal of the service area when a water quality prediction index in the runoff water quality change trend exceeds a pollution early warning threshold of rainfall runoff;

[0213] S5, pushing the pollution early warning signal to a management terminal of the service area to trigger corresponding runoff pollution control measures.

[0214] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0215] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence is to use digital computers or machine controlled by digital computers to simulate, extend and expand human intelligence, perceive environment, acquire knowledge and use knowledge to obtain the best results.

[0216] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A rainfall-runoff pollution early warning system, characterized in that, The system includes a sample analysis module, a pollutant model construction module, a water quality prediction module, an early warning signal generation module, and a pollution control module, wherein: The sample analysis module is used to perform physicochemical property analysis on road surface sediment samples and rainfall runoff samples in the service area to obtain pollutant concentration data and pollutant composition data of the service area. The pollutant model construction module is used to construct a pollutant migration and transformation model for the service area based on the spatiotemporal distribution characteristics of pollutants in the pollutant concentration data and the pollution propagation characteristics corresponding to pollutants in the pollutant composition data, including: The initial concentration spatial data of pollutants in the spatiotemporal distribution features are matched with the corresponding migration and transformation rules in the modular rule base of the service area; Based on the matching results, a set of behavioral mapping relationships is established using the pollutant type and spatial location in the pollutant concentration data as indexes. Based on the mapping relationship set, the dynamic process of pollutants in the service area is simulated and verified at a global scale; Based on the simulation verification results, a structured model expression of pollutants from the road surface to the receiving water body in the service area under different rainfall scenarios is generated, and the structured model expression is used as the pollutant migration and transformation model of the service area. The water quality prediction module is used to generate a runoff water quality change trend map of the service area based on the pollutant migration and transformation model under different rainfall scenarios, and to predict the runoff water quality change trend of the service area according to the dynamic attribute list of key water quality indicators in the runoff water quality change trend map, including: Identify the characteristic inflection points on the pollutant concentration curves in the runoff water quality change trend map; Based on the distribution of the characteristic inflection points on the time axis, the starting phase, peak phase, and duration of the changes in key water quality indicators in the service area are determined. Based on the quantified values ​​of the initial phase, the peak phase, and the duration, the intensity level of the change in the key water quality index is classified. By spatiotemporally correlating the change phase of the characteristic inflection point with the change intensity level, a dynamic attribute list of the key water quality indicators is obtained. The warning signal generation module is used to generate a pollution warning signal for the service area when the water quality prediction index in the water quality change trend exceeds the pollution warning threshold of the rainfall runoff. The pollution control module is used to push the pollution early warning signal to the management terminal of the service area to trigger corresponding runoff pollution control measures.

2. The rainfall runoff pollution early warning system as described in claim 1, characterized in that, When the sample analysis module performs physicochemical property analysis on road surface sediment samples and rainfall runoff samples from the service area to obtain pollutant concentration data and pollutant composition data for the service area, it is specifically used for: Collect dry-period pavement sediment samples and runoff samples during rainfall events at typical locations within the service area; The road surface sediment samples were ground and sieved to obtain experimental samples of the service area with standard particle size. Measure the concentration data of pollutants in the experimental sample; Identify the types of organic pollutants in the runoff sample to obtain pollutant composition data of the runoff sample.

3. The rainfall runoff pollution early warning system as described in claim 1, characterized in that, When the pollutant model building module constructs a pollutant migration and transformation model for the service area based on the spatiotemporal distribution characteristics of pollutants in the pollutant concentration data and the pollution propagation characteristics corresponding to pollutants in the pollutant composition data, it is specifically used for: Extract the initial concentration values ​​and spatiotemporal distribution characteristics of pollutants from the pollutant concentration data; Based on the pollutant composition data, the pollution propagation characteristics of the pollutants during the runoff process are determined; Empirical correlation rules were established based on the changes in pollutant concentrations with runoff duration and hydraulic conditions in historical rainfall-runoff monitoring data. Based on the aforementioned empirical association rules and the characteristics of pollution propagation, a modular rule base for the service area is constructed. By integrating the modular rule base with the spatiotemporal distribution features, a pollutant migration and transformation model for the service area is generated.

4. The rainfall-runoff pollution early warning system as described in claim 1, characterized in that, When the water quality prediction module generates a runoff water quality change trend map of the service area based on the pollutant migration and transformation model under different rainfall scenarios, and predicts the runoff water quality change trend of the service area according to the dynamic attribute list of key water quality indicators in the runoff water quality change trend map, it is specifically used for: Obtain various preset rainfall scenario parameters for the service area; The pollutant migration and transformation model is used to couple the hydrological and pollution parameters of the various preset rainfall scenarios to obtain the runoff process line and pollutant load flux of the sub-region outlet section within the service area. A time-series correlation analysis was performed on the runoff process curve and the pollutant load flux to obtain a runoff water quality change trend map of the sub-region; Extract the dynamic attribute list of key water quality indicators from the runoff water quality change trend map, and predict the runoff in the service area based on the dynamic attribute list to obtain the runoff water quality change trend of the service area.

5. A rainfall-runoff pollution early warning system as described in claim 4, characterized in that, When the water quality prediction module performs runoff prediction on the service area based on the dynamic attribute list and obtains the runoff water quality change trend of the service area, it is specifically used for: Obtain the intensity level and key time phase of the target pollutant change from the dynamic attribute list; Based on the key time phase, determine the pollution response time series of the sub-region; Based on the change intensity level and the pollution response time series, the predicted concentration time series value of the target pollutant at the outlet section of the sub-region is calculated, wherein the calculation formula for the predicted concentration time series value is as follows: ； In the formula, To indicate The predicted concentration time series value at the service area exit section at the specified time. The pollutant source strength coefficient determined for the aforementioned intensity level of change. It is a natural exponential function. The comprehensive attenuation coefficient is determined based on the underlying surface characteristics of the service area. These are the pollutant transport time parameters for the sub-region determined based on the pollution response time series.

6. A rainfall-runoff pollution early warning system as described in claim 5, characterized in that, When the warning signal generation module generates a pollution warning signal for the service area when the predicted water quality index in the trend of water quality change exceeds the pollution warning threshold of rainfall runoff, it is specifically used for: From the preset pollution warning threshold database, retrieve the warning concentration limit that matches the target pollutant; The time-series data of water quality prediction indicators in the runoff water quality change trend are compared with the warning concentration limit in real time. When the predicted water quality index exceeds the warning concentration limit for a specific period of time, the service area is determined to have experienced a pollution warning event of the corresponding level. Based on the level of the pollution warning event and the specific time period, a pollution warning signal for the service area is generated.

7. A rainfall-runoff pollution early warning system as described in claim 1, characterized in that, When the pollution control module pushes the pollution warning signal to the management terminal of the service area and triggers corresponding runoff pollution control measures, it is specifically used for: Based on the warning level and core area in the pollution warning signal, match the corresponding set of control measures instructions in the preset pollution control strategy library; The control measure instruction set is bound to the pollution early warning signal to obtain the control instruction data package for the service area; The control command data packet is pushed to the field management terminal corresponding to the core area in real time. After receiving and parsing the control command data packet, the on-site management terminal starts the pollution control process.

8. A method for early warning of rainfall runoff pollution, characterized in that, The method for using the rainfall runoff pollution early warning system according to claim 1: S1. Perform physicochemical property analysis on road surface sediment samples and rainfall runoff samples from the service area to obtain pollutant concentration data and pollutant composition data for the service area; S2. Based on the pollutant concentration data and the pollutant composition data, the dynamic changes of pollutants during the runoff process are constructed to form a pollutant migration and transformation model for the service area. S3. Based on the pollutant migration and transformation model, predict the hydrodynamics of the service area to obtain the runoff water quality change trend of the service area under different rainfall scenarios; S4. When the predicted water quality index in the trend of water quality change exceeds the pollution warning threshold of rainfall runoff, a pollution warning signal for the service area is generated. S5. Push the pollution warning signal to the management terminal of the service area to trigger corresponding runoff pollution control measures.

Images