Traceable pavement runoff pollutant monitoring method and system

Abstract

The invention discloses a traceable road surface runoff pollutant monitoring method and system, and relates to the technical field of water pollution monitoring. The method comprises the following steps: capturing environmental factors of precipitation, air temperature and traffic flow according to road surface basic monitoring data, extracting pollutant concentration data of sampling points, analyzing relevance of the environmental factors, identifying and classifying pollutant concentrations, and obtaining pollutant concentration change trend characteristics. According to the method, the relationship between the environmental factors and the pollutants is accurately analyzed by capturing the environmental factors and the pollutant concentration data, the understanding of the change trend of the pollutant concentration is improved, the pre-judgment precision of future changes is effectively improved, in real-time data comparison, error analysis helps to identify deviations and adjust model weights, the prediction accuracy is improved, and the prediction accuracy is improved. Through monitoring resource demand prediction, optimization of monitoring point layout and resource configuration and dynamic adjustment of a monitoring strategy, pollutant concentration monitoring is more flexible and accurate, and monitoring efficiency and response speed are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water pollution monitoring, and in particular to a traceable road runoff pollutant monitoring method and system. Background Art

[0002] The field of water pollution monitoring technology includes the detection, monitoring and evaluation of pollutants in water bodies, which is mainly used to ensure the safety of water resources and the control of environmental quality. The core content of this field includes the sampling, analysis and monitoring methods of water pollutants, with the focus on improving the accuracy and real-time nature of monitoring. Technical means include water quality sensors, remote sensing technology, data analysis technology and other methods to achieve comprehensive monitoring and evaluation of water pollution conditions. Systematic research focuses on the identification of pollution sources, quantitative analysis of pollutants and accurate feedback of monitoring data, so as to formulate more effective pollution control and prevention measures.

[0003] Among them, the road runoff pollutant monitoring method refers to a method for collecting, analyzing and monitoring runoff pollutants generated by road traffic pavement. The patent subject covers the collection of pollutant information in flowing water on the road surface by deploying monitoring equipment and sampling points, and based on specific technical means, accurate detection of the type and concentration of pollutants. This monitoring method involves tracking pollution sources and processing data to achieve effective monitoring of pollutants in road runoff, helping researchers understand the source and diffusion pattern of pollutants.

[0004] Existing technologies for water pollution monitoring generally have the problem of insufficient real-time response to changes in pollutant concentrations. Existing technologies mostly rely on fixed monitoring points and equipment and cannot be dynamically adjusted according to changes in environmental conditions, resulting in insufficient timely response to sudden pollution incidents and even missing important monitoring opportunities. The monitoring frequency and monitoring resource allocation of traditional methods lack flexibility and cannot be effectively optimized in real time according to the temporal and spatial distribution of changes in pollutant concentrations. This static monitoring method not only cannot provide sufficient monitoring data during high pollution periods, but also leads to the emergence of monitoring blind spots due to unreasonable resource allocation, reducing monitoring accuracy and response capabilities. Existing technologies still have limitations in tracking pollution sources and quantitative analysis of pollutants. It is difficult to accurately measure the temporal changes in pollutant concentrations and the environmental factors behind them, resulting in the feedback of monitoring data failing to accurately reflect the true situation of water pollution and affecting the effectiveness of pollution control measures. Summary of the invention

[0005] In order to solve the technical problems existing in the prior art, the embodiments of the present invention provide a traceable road runoff pollutant monitoring method and system. The technical solution is as follows:

[0006] In one aspect, a traceable method for monitoring road runoff pollutants is provided, the method comprising:

[0007] S1: Based on the basic road monitoring data, capture the environmental factors of precipitation, temperature, and traffic volume, extract the pollutant concentration data of the sampling points, analyze the correlation of environmental factors, identify and classify pollutant concentrations, and obtain the trend characteristics of pollutant concentration changes;

[0008] S2: Using the pollutant concentration change trend characteristics and combining them with the time period characteristics in the original data, a time series analysis model is constructed to extract key environmental factors that affect pollutant concentrations, optimize model parameters according to the temporal and spatial variation laws, and generate long-term pollutant concentration prediction results;

[0009] S3: Compare the long-term pollutant concentration prediction results with the real-time monitoring data, identify the error value and analyze the cause of the error, determine whether the model needs to be updated through error analysis, adjust the weight parameters of the model, and generate the pollutant concentration error correction result;

[0010] S4: Based on the pollutant concentration error correction result, analyze the relationship between pollutant concentration and monitoring resource demand, analyze the temporal and spatial distribution of pollutant concentration changes, predict the monitoring demand during high pollution periods and high pollution areas, and generate monitoring resource demand prediction results;

[0011] S5: Based on the monitoring resource demand prediction results, the monitoring frequency is adjusted during the period when the pollutant concentration changes greatly, the number of monitoring points and resource allocation are optimized, and the monitoring configuration is dynamically adjusted according to the sudden pollution situation and changing trends to generate a dynamic monitoring plan for road pollutants.

[0012] As a further scheme of the present invention, the pollutant concentration change trend characteristics include precipitation, temperature, traffic volume, pollutant concentration classification, and pollutant concentration change law; the long-term pollutant concentration prediction results include key environmental factors, temporal and spatial change laws, optimized model parameters, and long-term prediction values; the pollutant concentration error correction results include error values, error analysis, model update judgment, and model weight adjustment; the monitoring resource demand prediction results include the relationship between pollutant concentration and monitoring demand, high pollution time periods, and high pollution areas; the road pollutant dynamic monitoring plan includes monitoring frequency adjustment, optimization of the number of monitoring points, resource allocation optimization, and dynamic adjustment of monitoring configuration.

[0013] As a further solution of the present invention, based on the road surface basic monitoring data, the environmental factors of precipitation, temperature, and traffic volume are captured, the pollutant concentration data of the sampling points are extracted, the correlation of environmental factors is analyzed, the pollutant concentration is identified and classified, and the steps of obtaining the pollutant concentration change trend characteristics are specifically as follows:

[0014] S101: Based on the basic road surface monitoring data, environmental factors such as precipitation, temperature, and traffic volume are recorded, pollutant concentration data are extracted in time and location order, and the time stamp spatial nodes and pollutant concentrations are integrated to obtain the initial data table of environmental factors and pollutant concentrations at the sampling points;

[0015] S102: Based on the initial data table of environmental factors and pollutant concentrations at the sampling points, extract environmental factor parameters and pollutant concentration data, classify the correlation degree of each parameter, classify the classification results into concentration categories, and obtain a data table of pollutant concentration and environmental factor classification correlation;

[0016] S103: Based on the pollutant concentration and environmental factor classification association data table, extract the time series data of the concentration category, analyze the concentration change amplitude in the time dimension, summarize the change direction of the concentration value at the time point, integrate the concentration change trend data, and obtain the pollutant concentration change trend characteristics.

[0017] As a further solution of the present invention, the steps of constructing a time series analysis model by utilizing the pollutant concentration change trend characteristics and combining the time period characteristics in the original data, extracting key environmental factors affecting pollutant concentrations, optimizing model parameters according to the temporal and spatial variation rules, and generating long-term pollutant concentration prediction results are as follows:

[0018] S201: Based on the pollutant concentration change trend characteristics, the original data is divided into time intervals, the extreme concentration values ​​of each interval are counted, the mean fluctuation range is identified, the concentration change trend over time is analyzed, the interval trend index is extracted, and the time period concentration distribution result is obtained;

[0019] S202: Based on the concentration distribution results of the time period, filter the environmental factor records, identify the difference ratio between the environmental factor values ​​and the change values ​​of the pollutant concentration within the time interval, calculate the correlation coefficients and arrange them, extract the factor set within the correlation threshold range, and obtain the key environmental factor correlation data;

[0020] S203: Based on the key environmental factor association data, determine the interval weight factor distribution parameters, adjust the factor association coefficient and the interval contribution value, optimize the factor set weight distribution, and generate long-term pollutant concentration prediction results.

[0021] As a further solution of the present invention, the formula for obtaining the long-term pollutant concentration prediction result is:

[0022] ;

[0023] in, represents the long-term pollutant concentration prediction value, Expression and key environmental factors The associated weighting coefficient, Indicates Real-time observations of key environmental factors, Representation and Factor The associated adjustment coefficient, Representation and Factor The associated weight normalization parameter, represents the interaction intensity factor with the associated factor group within the interval, Indicates The time scale influencing factor of the interval.

[0024] As a further solution of the present invention, the steps of comparing the long-term pollutant concentration prediction result with the real-time monitoring data, identifying the error value and analyzing the cause of the error, judging whether the model needs to be updated through error analysis, adjusting the weight parameters of the model, and generating the pollutant concentration error correction result are specifically as follows:

[0025] S301: Based on the long-term pollutant concentration prediction result, extract the time interval value of the prediction value and the real-time monitoring data, identify the difference between the prediction and the real-time value, calculate the error mean and fluctuation range, analyze the error distribution characteristics of each time interval, and obtain the pollutant concentration error data;

[0026] S302: Based on the pollutant concentration error data, analyze the relationship between the error distribution and the environmental factor records, adjust the weight parameters and distribution intervals in the factor set, reallocate the numerical weights of the parameters in the model, and obtain the adjusted model parameters;

[0027] S303: Based on the adjusted model parameters and according to the weight parameter distribution data, the pollutant concentration prediction value is calculated to generate a pollutant concentration error correction result.

[0028] As a further solution of the present invention, based on the pollutant concentration error correction result, the relationship between the pollutant concentration and the monitoring resource demand is analyzed, the temporal and spatial distribution of the pollutant concentration change is analyzed, and the monitoring demand for high pollution periods and high pollution areas is predicted. The steps of generating the monitoring resource demand prediction result are specifically as follows:

[0029] S401: Based on the pollutant concentration error correction result, extract the regional and time interval concentration change data, count the regional pollutant peak value and time interval concentration fluctuation range, analyze the relationship between the concentration change trend and the monitoring resource demand ratio, and obtain the monitoring resource demand distribution data;

[0030] S402: Based on the monitoring resource demand distribution data, the pollutant concentration change data of the time interval is processed in groups, the change range of the high pollution period is analyzed, the total resource demand of the high pollution area is extracted in combination with the regional data, the resource demand peak value of the high pollution period of the region is identified, and the high pollution spatiotemporal monitoring demand data is obtained;

[0031] S403: Based on the high-pollution spatiotemporal monitoring demand data, the total resource demand data for high-pollution periods and regions is summarized, the overall distribution of monitoring resource demand is analyzed, and a monitoring resource demand prediction result is generated.

[0032] As a further solution of the present invention, the formula for obtaining the monitoring resource demand prediction result is:

[0033] ;

[0034] in, Represents the predicted value of monitoring resource demand, Represents the proportion of monitoring resources invested in high pollution periods, Represents the proportion of monitoring resources invested in high-pollution areas, represents the monitoring time span, Represents the difference value of pollution level in the high pollution spatiotemporal monitoring demand data, is the resource weight adjustment coefficient for high pollution periods, is the resource weight adjustment coefficient of high-pollution areas, It is the adjustment coefficient of the impact of pollution level differences on monitoring resource prediction.

[0035] As a further solution of the present invention, according to the monitoring resource demand prediction results, the monitoring frequency is adjusted for the period when the pollutant concentration changes greatly, the number of monitoring points and resource allocation are optimized, and the monitoring configuration is dynamically adjusted according to the sudden pollution situation and change trend. The steps of generating a dynamic monitoring plan for road pollutants are specifically as follows:

[0036] S501: Based on the monitoring resource demand prediction result, extract the time interval data of pollutant concentration changes, analyze the matching situation between time interval resource configuration and monitoring frequency, calculate the monitoring frequency adjustment ratio, optimize the adjustment parameter distribution, and obtain the time period monitoring frequency optimization data;

[0037] S502: Based on the monitoring frequency optimization data of the time period, analyze the relationship between the distribution of monitoring points and the resource demand of the high-pollution area, identify the adjustment ratio of the number of monitoring points in the high-pollution area, reallocate the spatial layout and resource quantity of the monitoring points, and obtain the resource configuration data of the monitoring points;

[0038] S503: Based on the resource configuration data of the monitoring points and in combination with the records of sudden pollution changes, the dynamic adjustment range of the monitoring points is analyzed, the spatial location of the monitoring points and the allocation of resource quantities are optimized, the regional monitoring configuration is updated, and a dynamic monitoring plan for road pollutants is generated.

[0039] On the other hand, a traceable road runoff pollutant monitoring system is provided, the system is used to perform the traceable road runoff pollutant monitoring method, the system comprising:

[0040] The environmental factor identification module extracts precipitation, temperature, and traffic volume data based on the basic road surface monitoring data, calibrates and screens the environmental factors, compares the monitoring point data, performs spatiotemporal feature analysis, screens the compliance data interval, analyzes the pollutant concentration trend, and obtains the pollutant concentration change trend characteristics;

[0041] The pollutant classification module classifies the pollutant concentrations at the sampling points based on the pollutant concentration change trend characteristics, groups the data using statistical analysis, screens the correlation characteristics between pollutant concentrations and environmental factors, classifies pollutants according to grouping rules, and generates pollutant risk level classification results;

[0042] The spatiotemporal analysis module performs spatiotemporal distribution analysis based on the pollutant risk level classification results, uses the differentiated sampling point data in the region to identify high pollution periods and areas, extracts pollutant concentration distribution trends, compares change data, determines potential pollution sources, and obtains pollutant spatiotemporal distribution characteristic data;

[0043] The pollutant concentration adjustment module calculates the difference value based on the temporal and spatial distribution characteristic data of the pollutants, analyzes the source of the error, determines whether the error is caused by the model parameters, adjusts the model parameters according to the error value change rules, adjusts the model weights with reference to the pollution source inference results, and generates the pollutant concentration error correction results;

[0044] Based on the pollutant concentration error correction results, the monitoring demand prediction module predicts the temporal and spatial variation trends of pollutant concentrations, analyzes high pollution periods and areas, calculates monitoring needs, adjusts monitoring frequency, optimizes monitoring points and resource allocation, and generates a dynamic monitoring plan for road pollutants.

[0045] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0046] By capturing environmental factors (such as precipitation, temperature, and traffic volume) and extracting pollutant concentration data, we can not only enhance our understanding of pollutant concentration trends, but also more accurately analyze the correlation between different environmental factors and pollutants. This prediction model based on time series analysis and optimization of spatiotemporal change rules effectively improves the accuracy of predicting future changes in pollutant concentrations. In the process of comparing with real-time monitoring data, error analysis helps to timely identify deviations in prediction results, and makes corrections by adjusting the model's weight parameters, further improving the accuracy of prediction results. By monitoring resource demand forecasts, we can efficiently optimize the layout of monitoring points and resource allocation, and dynamically adjust monitoring strategies based on sudden pollution situations and changing trends, making pollutant concentration monitoring more flexible and accurate, and able to schedule resources within different time and space ranges, effectively improving monitoring efficiency and response speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0048] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0049] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0050] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0051] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0052] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0053] Figure 7 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0054] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0055] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0056] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0057] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0058] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0059] See also Figure 1 The embodiment of the present invention provides a traceable road runoff pollutant monitoring method, and the processing flow of the method may include the following steps:

[0060] S1: Based on the basic road monitoring data, capture the environmental factors of precipitation, temperature, and traffic volume, extract the pollutant concentration data of the sampling points, analyze the correlation of environmental factors, identify and classify pollutant concentrations, and obtain the trend characteristics of pollutant concentration changes;

[0061] S2: Using the trend characteristics of pollutant concentration changes and combining the time period characteristics in the original data, a time series analysis model is constructed to extract key environmental factors that affect pollutant concentrations, optimize model parameters according to the temporal and spatial variation laws, and generate long-term pollutant concentration prediction results;

[0062] S3: Compare the long-term pollutant concentration prediction results with the real-time monitoring data, identify the error value and analyze the cause of the error, determine whether the model needs to be updated through error analysis, adjust the model's weight parameters, and generate the pollutant concentration error correction results;

[0063] S4: Based on the pollutant concentration error correction results, analyze the relationship between pollutant concentration and monitoring resource demand, analyze the temporal and spatial distribution of pollutant concentration changes, predict the monitoring demand in high pollution periods and high pollution areas, and generate monitoring resource demand prediction results;

[0064] S5: Based on the monitoring resource demand forecast results, adjust the monitoring frequency during periods of large changes in pollutant concentration, optimize the number of monitoring points and resource allocation, dynamically adjust the monitoring configuration according to sudden pollution situations and changing trends, and generate a dynamic monitoring plan for road pollutants.

[0065] The characteristics of pollutant concentration change trends include precipitation, temperature, traffic volume, pollutant concentration classification, and pollutant concentration change patterns. The long-term pollutant concentration prediction results include key environmental factors, temporal and spatial change patterns, optimized model parameters, and long-term prediction values. The pollutant concentration error correction results include error values, error analysis, model update judgment, and model weight adjustment. The monitoring resource demand prediction results include the relationship between pollutant concentration and monitoring demand, high pollution periods, and high pollution areas. The dynamic monitoring plan for road pollutants includes monitoring frequency adjustment, optimization of the number of monitoring points, resource allocation optimization, and dynamic adjustment of monitoring configuration.

[0066] Specifically, if Figure 2 As shown in the figure, based on the basic road monitoring data, the environmental factors of precipitation, temperature, and traffic volume are captured, the pollutant concentration data of the sampling points are extracted, the correlation of environmental factors is analyzed, the pollutant concentration is identified and classified, and the steps to obtain the trend characteristics of the pollutant concentration are as follows:

[0067] S101: Based on the basic road surface monitoring data, environmental factors such as precipitation, temperature, and traffic volume are recorded, pollutant concentration data are extracted in time and location order, and the time stamp spatial nodes and pollutant concentrations are integrated to obtain the initial data table of environmental factors and pollutant concentrations at the sampling points;

[0068] According to the sampling time series and spatial node coordinates, the integrity and accuracy of pollutant concentration data are obtained and verified one by one, outliers and missing values ​​are eliminated, and the data are rearranged to form time series data for continuity analysis. In the process of pollutant concentration extraction, the precipitation, temperature and traffic flow data of each sampling point are normalized to ensure the unit consistency of various environmental factors. Combined with the timestamp and spatial node, linear interpolation is used to supplement the existing spatiotemporal data breakpoints to avoid deviations in subsequent calculations due to uneven data intervals. When integrating the environmental factors and pollutant concentrations of the sampling points, the environmental factors are decomposed into two forms: daily average values ​​and hourly values, so as to analyze the impact of environmental factors on pollutant concentrations from multiple dimensions, and obtain the initial data table of environmental factors and pollutant concentrations of the sampling points, which contains the time nodes, spatial nodes, environmental factor values ​​and corresponding pollutant concentration values ​​of each sampling point.

[0069] S102: Based on the initial data table of environmental factors and pollutant concentrations at the sampling points, extract environmental factor parameters and pollutant concentration data, classify the correlation degree of each parameter, classify the classification results into concentration categories, and obtain a data table of pollutant concentration and environmental factor classification correlation;

[0070] Firstly, the numerical pairs of each environmental factor parameter and pollutant concentration are normalized to ensure the rationality of the comparison between different dimensions. By setting different concentration intervals, such as low concentration interval, medium concentration interval and high concentration interval, the distribution characteristics of each environmental factor in different concentration intervals are statistically analyzed, and the degree of influence is graded and classified using the proportional distribution method. Each classification result is re-merged according to the pollutant concentration category to generate a data table of pollutant concentration and environmental factor classification association. This data table records in detail the correlation between the distribution characteristics of environmental factors and pollutant concentrations, and provides the distribution weight of each environmental factor for a specific concentration category, so as to further explore the influence mechanism between them.

[0071] S103: Based on the pollutant concentration and environmental factor classification association data table, extract the time series data of the concentration category, analyze the concentration change amplitude in the time dimension, summarize the change direction of the concentration value at the time point, integrate the concentration change trend data, and obtain the pollutant concentration change trend characteristics;

[0072] The concentration values ​​at different time nodes are calculated to quantify the concentration change amplitude in the time dimension. By comparing the difference in concentration values ​​before and after each time point, the change direction is analyzed and integrated into a trend data table. When summarizing the change direction of concentration values, the concentration change at continuous time nodes is used to extract the change law of each concentration category. By combining the daily average concentration data with the hourly concentration data, a multi-scale analysis of the concentration change in the time dimension is performed to identify the characteristics of short-term fluctuations and long-term trends. The trend characteristics of pollutant concentration changes are obtained, and the change amplitude, fluctuation cycle and mutation point time nodes of each concentration category in different time periods are marked in detail, providing key data support for subsequent pollutant source tracing analysis and pollution control decision-making.

[0073] Specifically, if Figure 3 As shown in the figure, the time series analysis model is constructed by using the trend characteristics of pollutant concentration changes and combining the time characteristics in the original data. The key environmental factors affecting pollutant concentrations are extracted, and the model parameters are optimized according to the temporal and spatial variation laws. The specific steps for generating long-term pollutant concentration prediction results are as follows:

[0074] S201: Based on the pollutant concentration change trend characteristics, the original data is divided into time intervals, the extreme concentration values ​​of each interval are counted, the mean fluctuation range is identified, the concentration change trend over time is analyzed, the interval trend index is extracted, and the time period concentration distribution results are obtained;

[0075] The original data is divided into equal-length sub-intervals according to the time interval. The extreme concentration values ​​in each interval, including the maximum and minimum values, are counted one by one, and the mean and standard deviation of each interval are calculated. By comparing the extreme values ​​with the mean, the upper and lower limits of the fluctuation of pollutant concentration in the interval are clarified, and then the time trend of the concentration is analyzed. In the statistical process, the distribution range of hourly concentration values ​​is integrated based on the daily hourly data, and a concentration change graph over time is constructed based on this. When extracting interval trend indicators, the extreme value difference, mean change amplitude and fluctuation frequency of each interval are used as key evaluation indicators. The continuous intervals are compared through a dynamic sliding window to identify high-frequency fluctuation areas in the short term and stable concentration areas in the long term. Based on the analysis, the time period concentration distribution results are generated to clarify the concentration characteristics and trend laws of each interval, laying the foundation for subsequent environmental factor screening.

[0076] S202: Based on the concentration distribution results of the time period, filter the environmental factor records, identify the difference ratio between the environmental factor values ​​and the change values ​​of the pollutant concentration within the time interval, calculate the correlation coefficients and arrange them, extract the factor set within the correlation threshold range, and obtain the key environmental factor correlation data;

[0077] Environmental factor records are screened from the corresponding time interval, the numerical characteristics of environmental factors and the change values ​​of pollutant concentrations are extracted item by item, and the difference ratio between the numerical value of environmental factors and the change value of concentration is calculated. In the process of statistical proportion, the change values ​​of environmental factors and concentrations are compared with each hour as the time unit, and the abnormal points where the change amplitude exceeds the specific range are marked. At the same time, the proportional relationship between each environmental factor and the concentration change is recorded. By calculating the correlation coefficients one by one, the correlation coefficients are arranged from high to low, and the factor set with correlation exceeding the threshold is screened to form key environmental factor correlation data. In the data, the impact of different environmental factors on the change of pollutant concentration is layered and classified, and the intensity of the key factors is clarified to provide a basis for the subsequent adjustment of the weight distribution.

[0078] S203: Based on the key environmental factor correlation data, determine the interval weight factor distribution parameters, adjust the factor correlation coefficient and the interval contribution value, optimize the factor set weight distribution, and generate long-term pollutant concentration prediction results;

[0079] The formula for obtaining the long-term pollutant concentration prediction results is:

[0080] ;

[0081] in, represents the long-term pollutant concentration prediction value, Expression and key environmental factors The associated weighting coefficient, Indicates Real-time observations of key environmental factors, Representation and Factor The associated adjustment coefficient, Representation and Factor The associated weight normalization parameter, represents the interaction intensity factor with the associated factor group within the interval, Indicates The time scale influencing factor of each interval;

[0082] Detailed explanation of the formula and the process of formula calculation and derivation:

[0083] This formula is used to calculate the long-term pollutant concentration prediction results , the results obtained are used to assess environmental quality and guide the formulation of pollution control strategies;

[0084] :Indicates key environmental factors The associated weighting coefficient is used to adjust the contribution of each environmental factor to the prediction result. The setting value is 0.2, which reflects the relative importance of this factor in multi-objective optimization;

[0085] :Indicates the The real-time observation value of a key environmental factor is derived from long-term environmental monitoring data. The setting value is 50, which reflects the current measurement level of the factor;

[0086] :Represents and factors The associated adjustment coefficient reflects the internal dynamic change characteristics of the factor. The setting value is 10, which is calculated based on the volatility of historical data;

[0087] :Represents and factors The associated weight normalization parameter is used to maintain the consistency of the calculation results under different dimensions. The setting value is 5, and the normalization is performed according to the dimension and unit of each factor;

[0088] : It represents the interaction intensity factor with the associated factor group within the interval, reflecting the synergy between multiple factors. The set value is 0.8, obtained based on statistical analysis;

[0089] :Indicates the The time scale influencing factor of each interval reflects the changing rules of factor weights in different time periods. The setting value is 2, and it is dynamically adjusted according to the time window distribution;

[0090] Substitute the parameters into the formula for calculation:

[0091] Compute the internal terms: ;

[0092] Calculate the absolute difference: ;

[0093] Compute the weighted product: ;

[0094] Calculate the numerator part: ;

[0095] Compute the term inside the denominator: ;

[0096] Calculate the denominator: ;

[0097] Calculate the final result: ;

[0098] The result 7.683 indicates that under the current parameter settings, the long-term pollutant concentration prediction value is 7.683 units. This result can be used to evaluate environmental quality and provide a basis for the formulation of pollution control strategies.

[0099] Specifically, if Figure 4As shown in the figure, the long-term pollutant concentration prediction results are compared with the real-time monitoring data, the error values ​​are identified and the causes of the errors are analyzed, and the error analysis is used to determine whether the model needs to be updated, and the weight parameters of the model are adjusted to generate the pollutant concentration error correction results. The specific steps are as follows:

[0100] S301: Based on the long-term pollutant concentration prediction results, extract the time interval values ​​of the prediction value and the real-time monitoring data, identify the difference between the prediction and the real-time value, calculate the error mean and fluctuation range, analyze the error distribution characteristics of each time interval, and obtain the pollutant concentration error data;

[0101] The predicted values ​​are matched with the real-time monitoring data according to the time interval, the predicted concentration values ​​and the monitored concentration values ​​in each time interval are extracted, and the difference between the two is calculated. In the process of identifying the difference between the predicted values ​​and the real-time values, the difference values ​​are statistically classified, the difference change amplitude and its mean in each time interval are recorded, and the extreme points of the maximum error and the minimum error are extracted. The standard deviation of the overall error and the interval fluctuation range are calculated. When calculating the error mean, the difference data in each interval are accumulated according to the time series, and the mean is taken as the error characteristic value. The error distribution characteristics of each interval are generated in combination with the time dimension. When analyzing the error distribution of each time interval, the distribution frequency of the difference value is used to clarify the location of the high error interval and the low error interval, and the pollutant concentration error data is integrated to provide data support for subsequent model adjustments.

[0102] S302: Based on the pollutant concentration error data, analyze the relationship between the error distribution and the environmental factor records, adjust the weight parameters and distribution intervals in the factor set, reallocate the numerical weights of the parameters in the model, and obtain the adjusted model parameters;

[0103] The error characteristics of each time interval are analyzed in correlation with the environmental factor records one by one to clarify the changing rules of error distribution and environmental factors. When analyzing the error distribution, the environmental factor values ​​are stratified and statistically analyzed according to the time interval to identify the correlation between the environmental factor values ​​and the error data. Based on the analysis results, the weight parameters in the factor set are adjusted, and the weight distribution values ​​in the model are redistributed according to the degree of influence of the environmental factors. When adjusting the distribution interval, the distribution interval of highly correlated factors is refined to improve the sensitivity of the model to subtle changes in the factors. At the same time, the distribution range of low-correlation factors is appropriately expanded to reduce their impact on error correction. When redistributing the parameter weights in the model, the factor contribution value in the interval and the overall error change trend are combined to optimize the balance between the weight parameters and the distribution interval, generate the adjusted model parameters, and lay the foundation for subsequent prediction corrections.

[0104] S303: Based on the adjusted model parameters and according to the weight parameter distribution data, the pollutant concentration prediction value is calculated to generate a pollutant concentration error correction result;

[0105] The pollutant concentration in each time interval is corrected and the predicted value is recalculated. In the calculation process, the contribution value of environmental factors and error data in each interval are superimposed with the adjusted weight parameters as the core to generate a corrected concentration prediction value. The difference between the corrected prediction value and the real-time monitoring value is extracted, and the error mean and fluctuation range in each interval are counted again. The error changes before and after correction are compared to verify the correction effect. The correction results detail the concentration value change characteristics of each time interval and the corrected error distribution characteristics, which provides quantifiable analysis results for optimizing long-term pollutant concentration predictions, further improves the accuracy and operability of the monitoring system, and generates pollutant concentration error correction results.

[0106] Specifically, if Figure 5 As shown in the figure, based on the pollutant concentration error correction results, the relationship between pollutant concentration and monitoring resource demand is analyzed, the temporal and spatial distribution of pollutant concentration changes is analyzed, and the monitoring demand in high pollution periods and high pollution areas is predicted. The specific steps for generating the monitoring resource demand prediction results are as follows:

[0107] S401: Based on the pollutant concentration error correction result, extract the regional and time interval concentration change data, count the regional pollutant peak and time interval concentration fluctuation range, analyze the relationship between the concentration change trend and the monitoring resource demand ratio, and obtain the monitoring resource demand distribution data;

[0108] The concentration change data of each region and time interval are extracted from the monitoring data, the peak pollutant concentration in each region is counted one by one, and the concentration fluctuation range within the time interval is calculated. The regional data are sorted according to the extreme values ​​of the pollutant concentration, and the high-pollution areas are marked. Combined with the fluctuation range data of the time interval, the change trend of the pollutant concentration over time is analyzed. Taking hours and days as the time basis, the change slope and fluctuation amplitude of the concentration value are recorded, and the high-fluctuation interval and the low-fluctuation interval are classified. The demand ratio of monitoring resources is calculated through the concentration change characteristics of high-pollution areas and time intervals, the time priority and spatial distribution characteristics of the monitoring resource demand are clarified, the monitoring resource demand distribution data is obtained, and the specific impact of the pollutant concentration change trend on resource demand is fully presented.

[0109] S402: Based on the monitoring resource demand distribution data, the pollutant concentration change data of the time interval is processed in groups, the change range of the high pollution period is analyzed, and the total resource demand of the high pollution area is extracted in combination with the regional data, and the resource demand peak value of the high pollution period in the region is identified to obtain the high pollution spatiotemporal monitoring demand data;

[0110] The pollutant concentration change data within the time interval are grouped and processed, and the concentration change amplitude of the high pollution period is calculated based on the hour and region as the division standards. When analyzing the change amplitude of the high pollution period, the change in the hourly concentration value is compared with the mean, and the time period where the change amplitude exceeds the set threshold is marked. The regional data corresponding to the time period is identified, and the total resource demand in the high pollution area is calculated one by one in combination with the regional data. By matching the concentration peak with the time continuity, the resource demand peak of the regional high pollution period is further identified. The high pollution demand data in regional and time dimensions are integrated to obtain the high pollution spatiotemporal monitoring demand data, providing a basis for the precise allocation of monitoring resources.

[0111] S403: Based on the high pollution spatiotemporal monitoring demand data, the total resource demand data of high pollution periods and regions are summarized, the overall distribution of monitoring resource demand is analyzed, and the monitoring resource demand prediction results are generated;

[0112] The formula for obtaining the monitoring resource demand forecast results is as follows:

[0113] ;

[0114] in, Represents the predicted value of monitoring resource demand, Represents the proportion of monitoring resources invested in high pollution periods, Represents the proportion of monitoring resources invested in high-pollution areas, represents the monitoring time span, Represents the difference value of pollution level in the high pollution spatiotemporal monitoring demand data, is the resource weight adjustment coefficient for high pollution periods, is the resource weight adjustment coefficient of high-pollution areas, is the adjustment coefficient for the impact of differences in pollution levels on the prediction of monitoring resources;

[0115] Detailed explanation of the formula and calculation process:

[0116] This formula is used to calculate the forecast value of monitoring resource demand ,The results are used to guide resource allocation during high pollution periods and regions;

[0117] :The proportion of monitoring resources invested in high-pollution periods. By statistically analyzing the pollution levels of each period in historical data, the high-pollution period is determined, and the proportion of monitoring resources invested in this period is calculated. For example, if the total amount of runoff pollutants SS (suspended solids) introduced by a certain highway section during the rainy season (July-August) increases significantly, then this period is considered a high-pollution period. It is assumed that during this period, the investment in monitoring resources accounts for 60% of the total annual investment. ;

[0118] :The proportion of monitoring resources invested in high-pollution areas. By analyzing the pollution data of different areas, we can identify the pollution hotspots and calculate the proportion of monitoring resources invested in the area. For example, if a road or bridge pavement near a water body is more sensitive to runoff pollutants due to high water quality requirements, then this area is considered a high-pollution area. If the monitoring resource investment in this area accounts for 50% of the total investment of the city, then ;

[0119] :Monitoring time span, which indicates the length of the monitoring period. According to the monitoring plan, the monitoring time range is determined. For example, if the monitoring period is one year, then months;

[0120] : Pollution level difference value, which indicates the difference in pollution degree between different areas or time periods. The difference is obtained by calculating the mean pollutant concentration of each area or time period. For example, if the average suspended matter pollutant density in road runoff is 150mg / m 3 , other areas are 80mg / m 3 ,but mg / m 3 ;

[0121] : The resource weight adjustment coefficient for high pollution periods is set according to the degree of impact of high pollution periods on overall pollution. If high pollution periods contribute more to annual pollution, then Take a higher value and set ;

[0122] : The resource weight adjustment coefficient of the high-pollution area is set according to the impact of the high-pollution area on the overall pollution. If the high-pollution area contributes more to the pollution of the whole city, then Take a higher value and set ;

[0123] : The adjustment coefficient of the impact of pollution level differences on monitoring resource prediction is set according to the degree of impact of pollution level differences on monitoring resource demand. If the impact of pollution level differences on monitoring resource demand is significant, then Take a higher value and set ;

[0124] Substitute the parameters into the formula for calculation:

[0125] calculate : ;

[0126] calculate :

[0127] calculate :

[0128] calculate : ;

[0129] calculate : ;

[0130] calculate : ;

[0131] calculate : ;

[0132] Take the absolute value and square root: ;

[0133] Calculation results The results show that the predicted value of monitoring resource demand is 62.63. This result is used to guide the rational allocation of monitoring resources in high-pollution periods and areas to ensure the effectiveness and pertinence of monitoring work.

[0134] Specifically, if Figure 6 As shown in the figure, according to the monitoring resource demand forecast results, the monitoring frequency is adjusted during the period when the pollutant concentration changes greatly, the number of monitoring points and resource allocation are optimized, and the monitoring configuration is dynamically adjusted according to the sudden pollution situation and change trend. The specific steps for generating a dynamic monitoring plan for road pollutants are as follows:

[0135] S501: Based on the monitoring resource demand prediction results, extract the time interval data of pollutant concentration changes, analyze the matching of time interval resource allocation and monitoring frequency, calculate the monitoring frequency adjustment ratio, optimize the adjustment parameter distribution, and obtain the time period monitoring frequency optimization data;

[0136] The monitoring frequency and resource allocation records are extracted from the time interval data of pollutant concentration changes, and the monitoring frequency of different time periods is matched and analyzed with the actual resource usage. The monitoring frequency and pollutant concentration change trends are compared, and the time periods where the monitoring frequency and concentration changes do not match are identified. The frequency deviation of the time period is recorded. Combined with the analysis results, the adjustment ratio of the monitoring frequency in each time interval is calculated. By setting the segment weight, the monitoring frequency of the high-concentration fluctuation period is increased, and the monitoring frequency of the low-concentration fluctuation period is appropriately reduced. When optimizing the parameter distribution, the adjustment ratio of each time period is combined with the resource allocation ratio to ensure that the matching degree of resources and monitoring frequency reaches the optimal balance. After the optimization is completed, the optimization data of the time period monitoring frequency is obtained, and the optimized frequency and adjustment parameters of each time interval are recorded, providing an accurate basis for the subsequent resource allocation of monitoring points.

[0137] S502: Based on the period monitoring frequency optimization data, analyze the relationship between the distribution of monitoring points and the resource demand in the high-pollution area, identify the adjustment ratio of the number of monitoring points in the high-pollution area, reallocate the spatial layout of the monitoring points and the number of resources, and obtain the resource configuration data of the monitoring points;

[0138] An in-depth analysis is conducted on the relationship between the distribution of monitoring points and resource demand in high-pollution areas. The number of monitoring points and the monitoring frequency in time periods in high-pollution areas are extracted to identify whether the existing number of monitoring points meets the resource demand ratio. By statistically analyzing the concentration change records and monitoring frequencies of each monitoring point in the high-pollution area, the coverage of each monitoring point and its contribution to resource demand are calculated. When identifying the adjustment ratio of the number of monitoring points in high-pollution areas, the number of monitoring points with insufficient coverage is expanded, the density of monitoring points in high-frequency change areas is adjusted, and the allocation of monitoring point resources in low-demand areas is reduced. Based on the reallocated spatial layout and resource quantity of monitoring points, the monitoring resources in high-pollution areas and other areas are redistributed according to demand priority, and the resource configuration data of monitoring points is obtained, which provides a reliable basis for optimizing the spatial layout of monitoring points.

[0139] S503: Based on the resource configuration data of the monitoring points and combined with the records of sudden pollution changes, the dynamic adjustment range of the monitoring points is analyzed, the spatial location of the monitoring points and the allocation of resource quantities are optimized, the regional monitoring configuration is updated, and a dynamic monitoring plan for road pollutants is generated;

[0140] The concentration change trends and resource demands of high-pollution points in emergencies are statistically analyzed time period by time. When optimizing the spatial positions of monitoring points, areas with frequent sudden pollution changes are marked as dynamic adjustment areas. Combined with the coverage of monitoring points and resource distribution records, the boundaries of the adjustment range and the amount of resource allocation are calculated. In the allocation of resource quantities, priority is given to ensuring the resource supply of monitoring points in high-pollution areas, while leaving a flexible allocation ratio for dynamic adjustment areas to cope with the uncertainty of pollution changes. When updating the regional monitoring configuration, the re-optimized monitoring point locations and resource quantities are integrated to generate a dynamic monitoring plan for road pollutants. This plan comprehensively covers the resource demands of high-pollution areas and sudden pollution events, and provides a practical implementation plan for building a real-time and efficient monitoring system.

[0141] like Figure 7 As shown, the traceable road runoff pollutant monitoring system includes:

[0142] The environmental factor identification module extracts precipitation, temperature, and traffic volume data based on the basic road surface monitoring data, calibrates and screens the environmental factors, compares the monitoring point data, performs spatiotemporal feature analysis, screens the compliance data interval, analyzes the pollutant concentration trend, and obtains the pollutant concentration change trend characteristics;

[0143] The pollutant classification module classifies the pollutant concentrations at sampling points based on the trend characteristics of pollutant concentration changes, groups the data using statistical analysis, screens the correlation characteristics between pollutant concentrations and environmental factors, classifies pollutants according to grouping rules, and generates pollutant risk level classification results;

[0144] The spatiotemporal analysis module conducts spatiotemporal distribution analysis based on the results of pollutant risk level classification, uses the differentiated sampling point data in the region to identify high-pollution periods and areas, extracts pollutant concentration distribution trends, compares change data, identifies potential pollution sources, and obtains pollutant spatiotemporal distribution characteristic data;

[0145] The pollutant concentration adjustment module calculates the difference value based on the temporal and spatial distribution characteristic data of pollutants, analyzes the source of error, determines whether the error is caused by the model parameters, adjusts the model parameters according to the error value change rules, adjusts the model weights based on the pollution source speculation results, and generates the pollutant concentration error correction results;

[0146] The monitoring demand prediction module predicts the temporal and spatial variation trends of pollutant concentrations based on the pollutant concentration error correction results, analyzes high-pollution periods and areas, estimates monitoring needs, adjusts monitoring frequency, optimizes monitoring points and resource allocation, and generates a dynamic monitoring plan for road pollutants.

[0147] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A traceable road runoff pollutant monitoring method, characterized in that: The following steps are involved: S1: Based on the basic road monitoring data, capture the environmental factors of precipitation, temperature, and traffic volume, extract the pollutant concentration data of the sampling points, analyze the correlation of environmental factors, identify and classify pollutant concentrations, and obtain the trend characteristics of pollutant concentration changes; S2: Using the pollutant concentration change trend characteristics and combining them with the time period characteristics in the original data, a time series analysis model is constructed to extract key environmental factors that affect pollutant concentrations, optimize model parameters according to the temporal and spatial variation laws, and generate long-term pollutant concentration prediction results; S3: Compare the long-term pollutant concentration prediction results with the real-time monitoring data, identify the error value and analyze the cause of the error, determine whether the model needs to be updated through error analysis, adjust the weight parameters of the model, and generate the pollutant concentration error correction result; S4: Based on the pollutant concentration error correction result, analyze the relationship between pollutant concentration and monitoring resource demand, analyze the temporal and spatial distribution of pollutant concentration changes, predict the monitoring demand during high pollution periods and high pollution areas, and generate monitoring resource demand prediction results; S5: Based on the monitoring resource demand prediction results, the monitoring frequency is adjusted during the period when the pollutant concentration changes greatly, the number of monitoring points and resource allocation are optimized, and the monitoring configuration is dynamically adjusted according to the sudden pollution situation and changing trends to generate a dynamic monitoring plan for road pollutants.

2. The traceable road runoff pollutant monitoring method according to claim 1 is characterized in that: The pollutant concentration change trend characteristics include precipitation, temperature, traffic volume, pollutant concentration classification, and pollutant concentration change law. The long-term pollutant concentration prediction results include key environmental factors, temporal and spatial change laws, optimized model parameters, and long-term prediction values. The pollutant concentration error correction results include error values, error analysis, model update judgment, and model weight adjustment. The monitoring resource demand prediction results include the relationship between pollutant concentration and monitoring demand, high pollution periods, and high pollution areas. The road pollutant dynamic monitoring plan includes monitoring frequency adjustment, optimization of the number of monitoring points, resource allocation optimization, and dynamic adjustment of monitoring configuration.

3. The traceable road runoff pollutant monitoring method according to claim 1 is characterized in that: Based on the basic road monitoring data, the environmental factors of precipitation, temperature, and traffic volume are captured, the pollutant concentration data of the sampling points are extracted, the correlation of environmental factors is analyzed, the pollutant concentration is identified and classified, and the steps to obtain the trend characteristics of the pollutant concentration are as follows: S101: Based on the basic road surface monitoring data, environmental factors such as precipitation, temperature, and traffic volume are recorded, pollutant concentration data are extracted in time and location order, and the time stamp spatial nodes and pollutant concentrations are integrated to obtain the initial data table of environmental factors and pollutant concentrations at the sampling points; S102: Based on the initial data table of environmental factors and pollutant concentrations at the sampling points, extract environmental factor parameters and pollutant concentration data, classify the correlation degree of each parameter, classify the classification results into concentration categories, and obtain a data table of pollutant concentration and environmental factor classification correlation; S103: Based on the pollutant concentration and environmental factor classification association data table, extract the time series data of the concentration category, analyze the concentration change amplitude in the time dimension, summarize the change direction of the concentration value at the time point, integrate the concentration change trend data, and obtain the pollutant concentration change trend characteristics.

4. The traceable road runoff pollutant monitoring method according to claim 1 is characterized in that: The steps of constructing a time series analysis model by using the pollutant concentration change trend characteristics and combining the time period characteristics in the original data, extracting the key environmental factors affecting the pollutant concentration, optimizing the model parameters according to the temporal and spatial variation rules, and generating long-term pollutant concentration prediction results are as follows: S201: Based on the pollutant concentration change trend characteristics, the original data is divided into time intervals, the extreme concentration values ​​of each interval are counted, the mean fluctuation range is identified, the concentration change trend over time is analyzed, the interval trend index is extracted, and the time period concentration distribution result is obtained; S202: Based on the concentration distribution results of the time period, filter the environmental factor records, identify the difference ratio between the environmental factor values ​​and the change values ​​of the pollutant concentration within the time interval, calculate the correlation coefficients and arrange them, extract the factor set within the correlation threshold range, and obtain the key environmental factor correlation data; S203: Based on the key environmental factor association data, determine the interval weight factor distribution parameters, adjust the factor association coefficient and the interval contribution value, optimize the factor set weight distribution, and generate long-term pollutant concentration prediction results.

5. The traceable road runoff pollutant monitoring method according to claim 4 is characterized in that: The formula for obtaining the long-term pollutant concentration prediction result is: ； in, represents the long-term pollutant concentration prediction value, Expression and key environmental factors The associated weighting coefficient, Indicates Real-time observations of key environmental factors, Representation and Factor The associated adjustment coefficient, Representation and Factor The associated weight normalization parameter, represents the interaction intensity factor with the associated factor group within the interval, Indicates The time scale influencing factor of the interval.

6. The traceable road runoff pollutant monitoring method according to claim 1 is characterized in that: The steps of comparing the long-term pollutant concentration prediction results with the real-time monitoring data, identifying the error value and analyzing the cause of the error, judging whether the model needs to be updated through error analysis, adjusting the weight parameters of the model, and generating the pollutant concentration error correction results are as follows: S301: Based on the long-term pollutant concentration prediction result, extract the time interval value of the prediction value and the real-time monitoring data, identify the difference between the prediction and the real-time value, calculate the error mean and fluctuation range, analyze the error distribution characteristics of each time interval, and obtain the pollutant concentration error data; S302: Based on the pollutant concentration error data, analyze the relationship between the error distribution and the environmental factor records, adjust the weight parameters and distribution intervals in the factor set, reallocate the numerical weights of the parameters in the model, and obtain the adjusted model parameters; S303: Based on the adjusted model parameters and according to the weight parameter distribution data, the pollutant concentration prediction value is calculated to generate a pollutant concentration error correction result.

7. The traceable road runoff pollutant monitoring method according to claim 1 is characterized in that: Based on the pollutant concentration error correction result, the relationship between pollutant concentration and monitoring resource demand is analyzed, the temporal and spatial distribution of pollutant concentration changes is analyzed, and the monitoring demand in high pollution periods and high pollution areas is predicted. The steps of generating the monitoring resource demand prediction result are specifically as follows: S401: Based on the pollutant concentration error correction result, extract the regional and time interval concentration change data, count the regional pollutant peak value and time interval concentration fluctuation range, analyze the relationship between the concentration change trend and the monitoring resource demand ratio, and obtain the monitoring resource demand distribution data; S402: Based on the monitoring resource demand distribution data, the pollutant concentration change data of the time interval is processed in groups, the change range of the high pollution period is analyzed, the total resource demand of the high pollution area is extracted in combination with the regional data, the resource demand peak value of the high pollution period of the region is identified, and the high pollution spatiotemporal monitoring demand data is obtained; S403: Based on the high-pollution spatiotemporal monitoring demand data, the total resource demand data for high-pollution periods and regions is summarized, the overall distribution of monitoring resource demand is analyzed, and a monitoring resource demand prediction result is generated.

8. The traceable road runoff pollutant monitoring method according to claim 7 is characterized in that: The formula for obtaining the monitoring resource demand prediction result is: ； in, Represents the predicted value of monitoring resource demand, Represents the proportion of monitoring resources invested in high pollution periods, Represents the proportion of monitoring resources invested in high-pollution areas, represents the monitoring time span, Represents the difference value of pollution level in the high pollution spatiotemporal monitoring demand data, is the resource weight adjustment coefficient for high pollution periods, is the resource weight adjustment coefficient of high-pollution areas, It is the adjustment coefficient of the impact of pollution level differences on monitoring resource prediction.

9. The traceable road runoff pollutant monitoring method according to claim 1 is characterized in that: According to the monitoring resource demand prediction results, the monitoring frequency is adjusted during the period when the pollutant concentration changes greatly, the number of monitoring points and resource allocation are optimized, and the monitoring configuration is dynamically adjusted according to the sudden pollution situation and change trend. The specific steps of generating a dynamic monitoring plan for road pollutants are as follows: S501: Based on the monitoring resource demand prediction result, extract the time interval data of pollutant concentration changes, analyze the matching situation between time interval resource configuration and monitoring frequency, calculate the monitoring frequency adjustment ratio, optimize the adjustment parameter distribution, and obtain the time period monitoring frequency optimization data; S502: Based on the monitoring frequency optimization data of the time period, analyze the relationship between the distribution of monitoring points and the resource demand of the high-pollution area, identify the adjustment ratio of the number of monitoring points in the high-pollution area, reallocate the spatial layout and resource quantity of the monitoring points, and obtain the resource configuration data of the monitoring points; S503: Based on the resource configuration data of the monitoring points and in combination with the records of sudden pollution changes, the dynamic adjustment range of the monitoring points is analyzed, the spatial location of the monitoring points and the allocation of resource quantities are optimized, the regional monitoring configuration is updated, and a dynamic monitoring plan for road pollutants is generated.

10. A traceable road runoff pollutant monitoring system, characterized in that: According to any one of claims 1 to 9, the traceable road runoff pollutant monitoring method, the system comprising: The environmental factor identification module extracts precipitation, temperature, and traffic volume data based on the basic road surface monitoring data, calibrates and screens the environmental factors, compares the monitoring point data, performs spatiotemporal feature analysis, screens the compliance data interval, analyzes the pollutant concentration trend, and obtains the pollutant concentration change trend characteristics; The pollutant classification module classifies the pollutant concentrations at the sampling points based on the pollutant concentration change trend characteristics, groups the data using statistical analysis, screens the correlation characteristics between pollutant concentrations and environmental factors, classifies pollutants according to grouping rules, and generates pollutant risk level classification results; The spatiotemporal analysis module performs spatiotemporal distribution analysis based on the pollutant risk level classification results, uses the differentiated sampling point data in the region to identify high pollution periods and areas, extracts pollutant concentration distribution trends, compares change data, determines potential pollution sources, and obtains pollutant spatiotemporal distribution characteristic data; The pollutant concentration adjustment module calculates the difference value based on the temporal and spatial distribution characteristic data of the pollutants, analyzes the source of the error, determines whether the error is caused by the model parameters, adjusts the model parameters according to the error value change rules, adjusts the model weights with reference to the pollution source inference results, and generates the pollutant concentration error correction results; Based on the pollutant concentration error correction results, the monitoring demand prediction module predicts the temporal and spatial variation trends of pollutant concentrations, analyzes high pollution periods and areas, calculates monitoring needs, adjusts monitoring frequency, optimizes monitoring points and resource allocation, and generates a dynamic monitoring plan for road pollutants.

Images