Evaluation method and system for early warning level of soil and groundwater pollution in industrial parks

Abstract

The present application provides a method and system for evaluating the early warning level of soil and groundwater pollution in industrial parks, wherein the method includes: integrating the production raw material composition and waste emission data of pollution source enterprises with the evolution data of soil heavy metal concentrations in historical pollution events, and combining the optical sensing data of surface and underground monitoring points to construct a dynamic characteristic factor library reflecting the characteristics of the pollution source; calculating the spatial concentration gradient of the optical sensing data based on the characteristic factor library to generate a dynamic heat map that simultaneously includes the distribution and migration trends of heavy metals; performing cross-modal analysis on the pollution source characteristics and the dynamic heat map to establish the spatiotemporal evolution trajectory of the pollution diffusion path; dividing the differentiated pollution risk early warning intervals according to the diffusion rate and direction in the trajectory, and generating a targeted graded prevention and control strategy. The present application improves the timeliness of pollution early warnings and the targeting of prevention and control measures.

Description

Technical Field

[0001] The present application relates to the technical field of environmental monitoring and industrial pollution prevention and control, and in particular to a method and system for evaluating early warning levels of soil and groundwater pollution in industrial parks. Background Art

[0002] Soil and groundwater pollution prevention and control in industrial parks requires accurate identification of pollution sources, dynamic prediction of diffusion trends, and real-time assessment of risk levels. Due to the complexity of pollution sources in industrial parks and the multiple factors that influence pollutant migration, traditional monitoring methods are unable to meet the timeliness and accuracy requirements of pollution warnings. Therefore, a comprehensive evaluation method that can integrate multi-source data and reflect the spatiotemporal characteristics of pollution diffusion is urgently needed.

[0003] Existing solutions use heavy metal concentration data from fixed monitoring points, combined with spatial interpolation techniques from geographic information systems, to generate soil pollution distribution maps and delineate pollution risk areas using preset thresholds. This approach uses time series data to analyze pollution trends and, combined with information on pollution source locations, to establish a preliminary correlation model for pollution diffusion.

[0004] This plan relies on static monitoring data and cannot respond to dynamic emission changes of pollution sources in real time; the spatial interpolation method leads to deviations in the prediction of diffusion paths; at the same time, risk division only relies on concentration thresholds, which makes it difficult to support accurate prevention and control decisions. Summary of the Invention

[0005] The present application provides a soil and groundwater pollution early warning level evaluation method and system for industrial parks, which are used to solve the problems of poor timeliness of pollution early warning and low targeting of prevention and control measures in the existing technology.

[0006] In a first aspect, the present application provides a method for evaluating the early warning level of soil and groundwater pollution in an industrial park, comprising:

[0007] Obtaining data on the composition of raw materials and waste emissions from pollution source enterprises within the industrial park, monitoring data on the temporal evolution of heavy metal concentrations in soil during historical pollution incidents, and optical sensing data from target monitoring points within the industrial park, including surface and underground monitoring points;

[0008] Extracting pollution source characteristics from the production raw material composition data and the waste emission composition data, and generating a dynamic characteristic factor library based on the extracted pollution source characteristics and the monitoring data;

[0009] Based on the dynamic characteristic factor library, calculating the spatial concentration gradient of heavy metal element concentration distribution on the optical sensing data to generate a soil heavy metal migration heat map;

[0010] Performing a cross-modal spatiotemporal coupling analysis on the dynamic characteristic factor library and the soil heavy metal concentration dynamic heat map to generate a spatiotemporal evolution trajectory of the pollution source diffusion path within the industrial park;

[0011] Based on the spatiotemporal evolution trajectory, the industrial park is divided into different sub-intervals, and different sub-intervals correspond to different pollution risk warning intervals. According to the pollution risk warning intervals and the prevention and control rules corresponding to the pollution risk warning intervals, a graded prevention and control strategy for the soil and groundwater in the industrial park is generated.

[0012] Optionally, performing a cross-modal spatiotemporal coupling analysis on the dynamic characteristic factor library and the soil heavy metal concentration dynamic heat map to generate a spatiotemporal evolution trajectory of the pollution source diffusion path within the industrial park includes:

[0013] Extracting a time stamp sequence of pollution source emission events from the dynamic characteristic factor library, and extracting the concentration distribution state of heavy metal elements in different spatial regions from the soil heavy metal concentration dynamic heat map;

[0014] Performing event trigger matching on the time mark sequence and the concentration distribution state to screen out a target event set;

[0015] Combining the target event set with the concentration diffusion direction in the soil heavy metal concentration dynamic heat map to generate a diffusion path chain;

[0016] Based on the diffusion path chain and the dynamic heat map of soil heavy metal concentration, a spatiotemporal evolution trajectory of the pollution source diffusion path in the industrial park is generated.

[0017] Optionally, combining the target event set with the concentration diffusion direction in the soil heavy metal concentration dynamic heat map to generate a diffusion path chain includes:

[0018] Extracting the enterprise spatial location and emission duration corresponding to each pollution source emission event from the target event set;

[0019] Extracting the concentration increasing trend of the adjacent areas around the spatial location of the enterprise from the soil heavy metal concentration dynamic heat map, wherein the concentration increasing trend includes the propagation order of the heavy metal concentration values ​​in each adjacent area as the monitoring time changes;

[0020] Determining an initial diffusion direction corresponding to the pollution source emission event according to the propagation sequence;

[0021] Based on the emission duration, the duration ratio of the concentration increasing trend in the adjacent area pointed by the initial diffusion direction is calculated, and the adjacent areas whose duration ratio exceeds a preset ratio threshold are selected as effective diffusion areas;

[0022] Connecting the spatial location of the enterprise where the pollution source emission event occurs with the spatial location of the effective diffusion area to generate a one-way diffusion link, wherein the one-way diffusion link takes the spatial location of the enterprise as a starting point and the spatial location of the effective diffusion area as a next node;

[0023] Repeatedly traverse the one-way diffusion links corresponding to all pollution source emission events in the target event set, connect the one-way diffusion links with the same nodes end to end, and generate a diffusion path chain.

[0024] Optionally, the step of calculating, based on the emission duration, a duration ratio of the concentration increasing trend in the adjacent area pointed by the initial diffusion direction, and selecting the adjacent area whose duration ratio exceeds a preset ratio threshold as the effective diffusion area includes:

[0025] Generate a pollution emission time interval according to the emission start time point and emission end time point of the emission duration;

[0026] Extracting the starting monitoring time point corresponding to the concentration increase in the adjacent area pointed by the initial diffusion direction and the ending monitoring time point corresponding to the end of the concentration increase from the soil heavy metal concentration dynamic heat map to generate a concentration change time interval;

[0027] Calculating the length of the overlapping time interval between the pollution emission time interval and the concentration change time interval, and defining the ratio of the overlapping time interval length to the total pollution emission time interval length as the duration ratio;

[0028] Among all adjacent areas pointed by the initial diffusion direction, the adjacent areas whose duration ratio is greater than a first preset ratio threshold are marked as primary diffusion areas, and the adjacent areas whose duration ratio is greater than a second preset ratio threshold and less than or equal to the first preset ratio threshold are marked as secondary diffusion areas;

[0029] The areas where the monitoring time points of the concentration increasing trend in the primary diffusion area and the secondary diffusion area continuously cover the pollution emission time interval are merged into the effective diffusion area.

[0030] Optionally, performing event-triggered matching on the time-stamp sequence and the concentration distribution state to screen out a target event set includes:

[0031] Extracting the starting monitoring time point corresponding to the concentration increase in each spatial region from the concentration distribution state;

[0032] Calculate the time difference between the emission start time point in the time mark sequence and the start monitoring time point corresponding to the concentration increase in each spatial region;

[0033] From the time difference calculation results, filter out emission events whose time difference is less than the preset time window and whose spatial location is downwind of the pollution source enterprise or in the direction of groundwater flow;

[0034] Based on the emission events, determining the triggering correlation between the pollution source emission events and the degree of change in soil heavy metal concentrations;

[0035] All pollution source emission events having the trigger association relationship are combined according to corresponding spatial regions to generate a target event set.

[0036] Optionally, the calculating of the spatial concentration gradient of the heavy metal element concentration distribution on the optical sensing data based on the dynamic characteristic factor library to generate a soil heavy metal migration heat map includes:

[0037] Obtaining a measured value of heavy metal element concentration at each monitoring point in the optical sensing data;

[0038] Extracting the heavy metal spatial distribution pattern corresponding to the historical pollution event from the dynamic characteristic factor library;

[0039] According to the geographic coordinate positions of the monitoring points, a spatial grid model including all monitoring points is established;

[0040] In the spatial grid model, for each grid node, comparing the difference between the heavy metal element concentration measurement value of the current grid node and the heavy metal element concentration measurement value of the adjacent grid node;

[0041] adjusting weight coefficients of adjacent grid nodes according to the heavy metal spatial distribution pattern;

[0042] Calculating the concentration change rate of each adjacent grid node from the current grid node according to the heavy metal element concentration difference and the weight coefficient;

[0043] Determine the migration direction of heavy metal elements in the spatial grid based on the concentration change rate of all points to adjacent grid nodes;

[0044] The heavy metal element concentration measurements at each grid node were combined with the corresponding migration direction to generate a soil heavy metal migration heat map.

[0045] Optionally, the extracting pollution source characteristics of the production raw material composition data and the waste emission composition data, and generating a dynamic characteristic factor library based on the extracted pollution source characteristics and the monitoring data, includes:

[0046] Identify the types of heavy metal elements in the raw materials used by each pollution source enterprise from the production raw material composition data;

[0047] Extracting the transformation characteristics of heavy metal components in the waste discharged by each pollution source enterprise from the waste discharge composition data;

[0048] Match and associate the heavy metal element types of the same pollution source enterprise with the heavy metal component conversion characteristics to generate an enterprise-level pollution source characteristic label;

[0049] The enterprise-level pollution source characteristic labels are associated with the monitoring data in time series to generate a dynamic characteristic factor library.

[0050] In a second aspect, the present application provides an industrial park soil and groundwater pollution early warning level evaluation system, comprising:

[0051] An acquisition module is used to obtain production raw material composition data, waste discharge composition data, monitoring data on the temporal evolution of soil heavy metal concentrations in historical pollution incidents, and optical sensing data from target monitoring points within the industrial park, including surface and underground monitoring points.

[0052] A first generating module is configured to extract pollution source characteristics from the production raw material composition data and the waste emission composition data, and generate a dynamic characteristic factor library based on the extracted pollution source characteristics and the monitoring data;

[0053] a calculation module for calculating the spatial concentration gradient of the heavy metal element concentration distribution on the optical sensing data based on the dynamic characteristic factor library to generate a soil heavy metal migration heat map;

[0054] A second generation module is used to perform a cross-modal spatiotemporal coupling analysis on the dynamic characteristic factor library and the soil heavy metal concentration dynamic heat map to generate a spatiotemporal evolution trajectory of the pollution source diffusion path within the industrial park;

[0055] A division module is used to divide the industrial park into different sub-intervals based on the spatiotemporal evolution trajectory, where different sub-intervals correspond to different pollution risk warning intervals, and generate a graded prevention and control strategy for the soil and groundwater in the industrial park according to the pollution risk warning intervals and the prevention and control rules corresponding to the pollution risk warning intervals.

[0056] In a third aspect, the present application provides a computing device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a method for evaluating the soil and groundwater pollution warning level in an industrial park as described in any one of the first aspects.

[0057] In a fourth aspect, the present application provides a computer storage medium having computer program instructions stored thereon, which, when executed by a processor, implements a method for evaluating the early warning level of soil and groundwater pollution in an industrial park as described in any one of the first aspects.

[0058] The present application provides a method for evaluating the early warning level of soil and groundwater pollution in an industrial park, the method comprising: obtaining production raw material composition data, waste emission composition data, monitoring data on the temporal evolution of soil heavy metal concentrations in historical pollution events, and optical sensing data of target monitoring points in the industrial park, the target monitoring points including surface monitoring points and underground monitoring points; performing pollution source feature extraction on the production raw material composition data and the waste emission composition data, and generating a dynamic characteristic factor library based on the extracted pollution source features and the monitoring data; performing spatial concentration gradient calculation on the heavy metal element concentration distribution on the optical sensing data based on the dynamic characteristic factor library to generate a soil heavy metal migration heat map; performing cross-modal spatiotemporal coupling analysis on the dynamic characteristic factor library and the soil heavy metal concentration dynamic heat map to generate a spatiotemporal evolution trajectory of the pollution source diffusion path in the industrial park; dividing the industrial park into different sub-intervals based on the spatiotemporal evolution trajectory, wherein different sub-intervals correspond to different pollution risk early warning intervals, and generating a graded prevention and control strategy for the soil and groundwater in the industrial park based on the pollution risk early warning intervals and the prevention and control rules corresponding to the pollution risk early warning intervals.

[0059] The technical solution provided by this application has the following beneficial effects:

[0060] This application integrates the production raw materials, waste emission data and historical pollution event monitoring data of pollution source enterprises, and combines surface and underground optical sensing data to build a multi-dimensional data foundation that comprehensively reflects the pollution characteristics of industrial parks, solving the problem of single and one-sided traditional monitoring data. Through the professional extraction of pollution source characteristics and the fusion analysis of historical data, a dynamic characteristic factor library with time evolution characteristics is established, realizing the organic combination of pollution source emission characteristics and historical pollution laws. Based on the dynamic characteristic factor library, the spatial gradient calculation of optical sensing data is performed, and the generated migration heat map not only reflects the current concentration distribution, but also reveals the spatial migration trend of heavy metals, breaking through the limitations of static distribution analysis. Through cross-modal analysis of the dynamic characteristic factor library and the migration heat map, the complete causal chain from the pollution source to the diffusion path is accurately restored, and the spatiotemporal dynamic visualization of the pollution diffusion process is realized. Based on the risk interval division and prevention and control rule matching of the spatiotemporal evolution trajectory, differentiated prevention and control plans for different pollution characteristics are formed, which improves the accuracy and effectiveness of prevention and control measures.

[0061] Furthermore, this application also extracts the pollution source time mark sequence from the dynamic characteristic factor library, extracts the spatial concentration distribution state from the heat map, and after event trigger matching and screening the target event set, combines it with the concentration diffusion direction to generate a diffusion path chain, and finally forms a complete pollution diffusion spatiotemporal evolution trajectory.

[0062] In addition, the program innovatively established a spatiotemporal correlation model between pollution source emission events and changes in soil heavy metal concentrations. Through event matching and path chain construction, it achieved traceability and predictability of the pollution diffusion process in industrial parks, providing key technical support for accurately identifying major pollution sources and predicting diffusion trends.

[0063] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0065] Figure 1 A flow chart of the method for evaluating the early warning level of soil and groundwater pollution in an industrial park provided in an embodiment of the present application;

[0066] Figure 2 A schematic diagram of the structure of the industrial park soil and groundwater pollution early warning level evaluation system provided in an embodiment of the present application;

[0067] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0068] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0069] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0070] Researchers have found that the prevention and control of soil and groundwater pollution in industrial parks faces difficulties such as complex pollution sources, difficult to track the diffusion process, and delayed risk warnings. Existing technologies make it difficult to achieve dynamic correlation analysis between pollution emission characteristics and diffusion trends. Based on this, a method for evaluating the early warning level of soil and groundwater pollution in industrial parks is provided. This method can build a dynamic feature factor library by integrating production data of pollution source enterprises, historical pollution events and real-time monitoring data, and generate a heavy metal migration heat map in combination with optical sensing data to achieve spatiotemporal evolution prediction of pollution diffusion paths and accurate graded early warnings. The technical solution of this application can be applied to real-time monitoring and prevention and control decision-making scenarios of heavy metal pollution in industrial parks.

[0071] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0072] Figure 1 A flowchart of a method for evaluating soil and groundwater pollution warning levels in an industrial park provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes:

[0073] Step 101: Obtain production raw material composition data, waste emission composition data, monitoring data on the temporal evolution of soil heavy metal concentrations in historical pollution events, and optical sensing data of target monitoring points in the industrial park, including surface monitoring points and underground monitoring points, from pollution source enterprises within the industrial park.

[0074] In this step, raw material composition data represents the heavy metal composition and proportions of raw materials used in the production process of pollution source enterprises, and is used to identify potential sources of pollution. Waste emission composition data represents the types and concentrations of heavy metals contained in waste generated during the production process of enterprises, reflecting actual emission characteristics. Historical pollution event monitoring data represents the changes in soil heavy metal concentrations over time recorded from previous pollution events in the park, providing a reference for pollution diffusion patterns. Optical sensing data represents optical characteristic data reflecting the heavy metal content in the soil, collected by spectral sensors deployed at surface and underground monitoring points.

[0075] In an embodiment of the present application, a list of production raw materials and waste emission records are first retrieved from the enterprise archives of the industrial park to obtain raw material composition and emission composition data; at the same time, monitoring records of pollution incidents that have occurred in the area in history are extracted from the environmental protection department database; surface monitoring stations and underground monitoring wells are arranged in the industrial park, and optical sensors are installed to collect soil spectral data in real time, ultimately forming a comprehensive data set that includes enterprise production characteristics, historical pollution patterns and real-time monitoring data.

[0076] For example, taking a chemical park as an example, the data on the proportion of chromate raw materials and wastewater treatment records used by electroplating enterprises in the park are collected, and the data on changes in soil chromium concentration in past chromium pollution incidents in the park are retrieved; 30 surface monitoring points and 15 underground monitoring wells are evenly distributed in the park, and laser-induced spectral sensors are used to collect soil spectral data every 2 hours. All data are uniformly stored in the park's environmental monitoring platform.

[0077] Step 102: Extract pollution source characteristics from the production raw material composition data and the waste emission composition data, and generate a dynamic characteristic factor library based on the extracted pollution source characteristics and the monitoring data.

[0078] In this step, pollution source characteristics are used to reflect the key indicators of the enterprise's pollution emission characteristics, including emission substances, emission cycle, emission intensity, etc. The dynamic characteristic factor library contains a characteristic database of pollution source characteristics and their temporal changes.

[0079] In an embodiment of the present application, the collected raw material and waste composition data are subjected to component analysis to extract the main pollutant types and their concentration characteristics; combined with historical pollution event data, the migration and transformation patterns of pollutants in the soil are analyzed; the extracted pollution source characteristics are associated with historical pollution patterns to establish a characteristic factor library containing information such as pollutant emission characteristics and diffusion patterns, and this factor library can be continuously updated with new data.

[0080] For example, for the above-mentioned electroplating enterprises, their chromate raw material usage records and wastewater discharge data were analyzed to extract the emission characteristics of chromium elements; combined with historical chromium pollution incidents, the migration rate and transformation form of chromium in the park soil were summarized; a characteristic factor library containing parameters such as chromium emission intensity, emission cycle, and soil adsorption characteristics was established, and a monthly update mechanism was set up.

[0081] Step 103: Based on the dynamic characteristic factor library, the spatial concentration gradient of the heavy metal element concentration distribution is calculated for the optical sensing data to generate a soil heavy metal migration heat map.

[0082] In this step, the spatial concentration gradient is a quantitative indicator reflecting the spatial distribution heterogeneity of heavy metals in the soil. The soil heavy metal migration heat map is a visual chart that directly displays the spatial distribution and migration trends of heavy metal concentrations.

[0083] In an embodiment of the present application, the credibility weight of the data at each monitoring point is determined based on the pollutant migration law in the dynamic characteristic factor library; a spatial interpolation model is established according to the location of the monitoring point to calculate the heavy metal concentration value of each grid node; combined with the historical diffusion law, the spatial change trend of the concentration is analyzed to generate a heat map containing the concentration distribution and migration direction.

[0084] For example, based on the characteristic factor library of the electroplating park, different weights are assigned to the chromium concentration data of 30 surface and 15 underground monitoring points; the inverse distance weighted method is used to calculate the chromium concentration of each node in the park's 500m x 500m grid; combined with historical chromium diffusion data, a heat map reflecting the chromium concentration distribution and main migration direction is drawn, which is updated every 6 hours.

[0085] Step 104: Perform a cross-modal spatiotemporal coupling analysis on the dynamic characteristic factor library and the soil heavy metal concentration dynamic heat map to generate a spatiotemporal evolution trajectory of the pollution source diffusion path within the industrial park.

[0086] In this step, cross-modal spatiotemporal coupling analysis involves correlating data from different sources and types across time and space. Spatiotemporal evolution trajectories are continuous curves that describe the diffusion paths of pollutants in both time and space.

[0087] In an embodiment of the present application, the pollution source emission time series in the dynamic characteristic factor library is matched with the spatial diffusion pattern in the migration heat map; the main path of pollution diffusion is determined by analyzing the spatiotemporal correspondence between emission events and concentration changes; and multi-period data is integrated to construct a spatiotemporal trajectory reflecting the complete diffusion process of pollutants from the emission source to the affected area.

[0088] For example, by matching the chromium wastewater discharge records of electroplating enterprises with the changes in soil chromium concentration heat maps, it was found that the concentration at the east monitoring point began to rise 8 hours after the discharge; tracking the diffusion pattern for three consecutive days, it was determined that chromium pollutants mainly diffused in the northeast direction along the groundwater flow, and a complete diffusion trajectory was constructed from the electroplating workshop to the boundary of the park.

[0089] Step 105: Based on the spatiotemporal evolution trajectory, the industrial park is divided into different sub-intervals, where different sub-intervals correspond to different pollution risk warning intervals. According to the pollution risk warning intervals and the prevention and control rules corresponding to the pollution risk warning intervals, a graded prevention and control strategy for the soil and groundwater in the industrial park is generated.

[0090] In this step, pollution risk warning intervals represent differentiated control areas based on pollution severity. Prevention and control rules refer to differentiated governance measures and technical standards developed for different pollution risk warning intervals. Tiered prevention and control strategies represent differentiated governance measures developed for areas with different risk levels.

[0091] In the embodiment of the present application, the park is divided into a core pollution area, a diffusion impact area and a safety area according to the diffusion speed and concentration changes in the spatiotemporal evolution trajectory; corresponding monitoring frequencies and treatment plans are formulated for each area; source treatment is implemented in the core area, isolation measures are strengthened in the impact area, and routine monitoring is maintained in the safety area.

[0092] For example, based on the spread trajectory of chromium pollution, the area surrounding the electroplating workshop was designated as a core zone, where production was suspended for rectification. The northeastern diffusion path was designated as an impact zone, where an underground barrier wall was constructed. Other areas maintained routine monitoring. A differentiated plan was developed: daily monitoring of the core zone, weekly monitoring of the impact zone, and monthly monitoring of the safe zone.

[0093] This method integrates multi-source data to build a dynamic feature library, achieving accurate extraction of pollution source characteristics; based on optical sensing and spatial analysis technology, it accurately restores the migration process of heavy metals; and establishes a complete trajectory of pollution diffusion through spatiotemporal coupling analysis. The resulting hierarchical prevention and control strategy improves the targetedness and effectiveness of pollution control in industrial parks, providing a scientific basis for environmental risk management.

[0094] To solve the problem of accurately predicting the diffusion path of pollution sources in industrial parks, in some embodiments, step 104: performing a cross-modal spatiotemporal coupling analysis of the dynamic characteristic factor library and the soil heavy metal concentration dynamic heat map to generate the spatiotemporal evolution trajectory of the pollution source diffusion path in the industrial park includes:

[0095] Step 201: extracting a time stamp sequence of pollution source emission events from the dynamic characteristic factor library, and extracting the concentration distribution state of heavy metal elements in different spatial regions from the soil heavy metal concentration dynamic heat map.

[0096] In step 201, the time stamp sequence represents a collection of time data recording the start and duration of each emission activity by a pollution source enterprise. Generation process: Based on the dynamic characteristic factor library, which records the time points of raw material feeding, waste discharge operations, and peak concentrations at the outfall, a pollution event time series containing the temporal characteristics of pollution source activities is generated. The concentration distribution represents a data structure reflecting the heavy metal concentration values ​​in each monitoring area and their temporal trends.

[0097] In this example, a dynamic feature factor library was used to retrieve recent records of raw material inputs and wastewater discharges from the enterprise, extracting pollution emission events with clear time stamps. Simultaneously, the heavy metal concentration values ​​and their slopes for each grid cell were extracted from the dynamic heat map to form a spatiotemporal distribution matrix. Through data time alignment, an initial correspondence between emission events and concentration changes was established.

[0098] Step 202: performing event trigger matching on the time mark sequence and the concentration distribution state to filter out a target event set.

[0099] In step 202, event trigger matching represents an analytical method for establishing a causal relationship between pollution emission events and soil concentration changes. The target event set represents a set of pollution events that have been screened and confirmed to have a clear causal relationship.

[0100] In an embodiment of the present application, the time difference between the time mark of each emission event and the time when the concentration in the surrounding area begins to rise is calculated, and emission events whose time difference is within a reasonable range of pollutant migration are screened; at the same time, the correlation between the duration of the emission event and the duration of the concentration rise is verified, and finally a target event set with statistical correlation is determined.

[0101] Step 203: combining the target event set with the concentration diffusion direction in the soil heavy metal concentration dynamic heat map to generate a diffusion path chain.

[0102] In step 203, the concentration diffusion direction represents the main migration direction of heavy metal pollutants in space. The diffusion path chain represents the pollution diffusion path composed of multiple continuous spatial nodes.

[0103] In an embodiment of the present application, for each emission event in the target event set, the spatial variation trend of the concentration gradient in the affected area is analyzed to determine the main diffusion direction; multiple spatial diffusion directions triggered by the same pollution source are connected in chronological order to form a preliminary diffusion path chain.

[0104] Step 204: Generate a spatiotemporal evolution trajectory of the pollution source diffusion path in the industrial park based on the diffusion path chain and the soil heavy metal concentration dynamic heat map.

[0105] In step 204, the relationship and distinction between diffusion path chains and pollution source diffusion paths are as follows: Diffusion path chains are the basic building blocks of pollution source diffusion paths, formed by combining multiple target event sets and concentration diffusion directions, and directly reflect the spatial transfer relationship of pollutants. Pollution source diffusion paths are the final output of diffusion path chains after spatiotemporal integration, containing complete temporal evolution information and spatial coverage. Diffusion path chains: composed of discrete "target event set + concentration diffusion direction" segments; they only represent the unidirectional diffusion relationship between local pollution sources and adjacent areas. Pollution source diffusion paths: formed by integrating all diffusion path chains to form a continuous spatiotemporal trajectory; they contain the complete migration path (multi-hop transfer) and temporal evolution characteristics of pollutants.

[0106] In an embodiment of the present application, the concentration change rate of each node in the diffusion path chain is superimposed and verified with the dynamic heat map to eliminate abnormal nodes; the missing nodes in the path chain are supplemented by the spatiotemporal interpolation method, and finally a smooth and continuous spatiotemporal evolution trajectory is generated.

[0107] Here's a specific example:

[0108] In the case of chromium pollution monitoring in the electroplating park, the dynamic characteristic factor library was used to extract the company's 6 chromium wastewater discharge records in the past three months (including the abnormal discharge event from 9:00 to 14:00 on March 5), and the concentration data of each monitoring area in the corresponding period was extracted from the dynamic heat map of soil chromium concentration (among which the concentration at the east monitoring point 300 meters away from the discharge port increased 7 hours after the discharge, with an increase rate of 1.2 mg / kg per hour). The time stamps of the 6 discharge events were matched with the concentration change curves of the 12 surrounding monitoring points, and 4 events with clear causal relationships were screened out (with a time difference of 6-8 hours). , which is consistent with the calculated historical chromium migration rate); based on the analysis of these four events, it was found that the pollutants mainly diffused along the northeast 35° direction (this angle is calculated by the time difference and spacing between the concentration peaks of consecutive monitoring points: diffusion angle = arctan(north-south spacing / east-west spacing)), forming a diffusion path chain starting from the electroplating workshop and passing through three key monitoring nodes (150 meters, 320 meters, and 500 meters away from the source respectively); finally, a complete spatiotemporal evolution trajectory was generated based on the concentration change rate of each node in the path chain (an average diffusion of 42 meters per hour, which is calculated by dividing the node spacing by the time difference between the arrival of the concentration peak).

[0109] In the embodiments of the present application, by establishing a precise spatiotemporal correlation between pollution emissions and soil responses, the visualization tracking and prediction of pollution diffusion paths in industrial parks are achieved, providing a scientific basis for precise prevention and control, and improving the timeliness and pertinence of pollution control.

[0110] To further improve the accuracy of pollution diffusion path analysis in industrial parks, in some embodiments, step 203: combining the target event set with the concentration diffusion direction in the soil heavy metal concentration dynamic heat map to generate a diffusion path chain includes:

[0111] Step 301: extracting the enterprise spatial location and emission duration corresponding to each pollution source emission event from the target event set.

[0112] In step 301, the enterprise spatial location represents the specific geographical coordinate location of the pollution source enterprise within the industrial park. The emission duration represents the length of time from the start to the end of a single emission activity of the pollution source.

[0113] In an embodiment of the present application, detailed information of each valid pollution event is extracted from the screened and confirmed target event set, including the precise geographic location of the emitting enterprise (obtained through the park enterprise distribution map) and the start and end time of the emission (extracted from the enterprise production log and pollution discharge record), providing a spatial and temporal benchmark for subsequent diffusion analysis.

[0114] Step 302: Extract the concentration increasing trend of the adjacent areas around the spatial location of the enterprise from the soil heavy metal concentration dynamic heat map, and the concentration increasing trend includes the propagation order of the heavy metal concentration values ​​in each adjacent area as the monitoring time changes.

[0115] In step 302, adjacent areas refer to the geographical areas within the industrial park that directly border the location of the pollution source enterprise or are covered by the nearest soil / groundwater monitoring point. The criteria for determining adjacent areas are: physical contact between the geographic boundaries of the two areas (e.g., adjacent grids above, below, or on the left, and right of the monitoring point grid); and physical connectivity between pre-deployed sensor arrays (e.g., groundwater flows toward adjacent monitoring wells). In the absence of physical contact, all monitoring areas within a preset radius (e.g., 500 meters) centered on the pollution source are considered adjacent. The increasing concentration trend indicates the characteristic of a continuous increase in heavy metal concentrations in the monitoring area over time. The propagation order indicates the temporal order in which pollutant concentrations begin to rise in different spatial regions. The discharge duration is extracted from the pollution source discharge events in the target event set. It refers to the length of time from the start to the end of a single discharge event by the pollution source enterprise (e.g., a wastewater discharge by an enterprise lasting 5 hours). It is used to assess the impact of the persistence of pollution discharges on the diffusion of heavy metals in soil. The monitoring time is the timestamp of the monitoring data recorded in the soil heavy metal concentration dynamic heat map. It refers to the specific time point or time series when the sensor collects the soil heavy metal concentration value (for example: monitoring data at 10 am every day) for analyzing the spatial variation trend of heavy metal concentration over time.

[0116] In an embodiment of the present application, with the enterprise location as the center, the concentration time series data of all monitoring areas within a radius of 500 meters are extracted from the dynamic heat map, the specific time point when the concentration in each area begins to rise is analyzed, and the spatial propagation order of pollutants is determined by chronological order, and the duration of the concentration increase in each area is recorded.

[0117] Step 303: Determine the initial diffusion direction corresponding to the pollution source emission event according to the propagation order.

[0118] In step 303 , the initial diffusion direction represents the initial main migration direction of the pollutants after leaving the pollution source.

[0119] In the embodiment of the present application, based on the spatial distribution of the three adjacent areas where the concentration first increases in the propagation order, the average direction angle of the line connecting them with the enterprise location is calculated, and this direction is determined as the initial diffusion direction to ensure that the direction judgment is spatially representative.

[0120] Step 304: Based on the emission duration, calculate the duration ratio of the concentration increasing trend in the adjacent area pointed by the initial diffusion direction, and select the adjacent area whose duration ratio exceeds a preset ratio threshold as the effective diffusion area.

[0121] In step 304, the duration ratio represents the ratio of the duration of the pollution emission to the duration of the concentration increase. The effective diffusion area represents the spatial area that has been screened and confirmed to be directly related to the pollution emission.

[0122] In an embodiment of the present application, the ratio of the duration of concentration rise in each sector in the initial diffusion direction to the duration of emission is calculated, and the area where the ratio exceeds 60% is determined as the effective diffusion area (this threshold is determined based on historical data analysis) to eliminate interference caused by accidental concentration fluctuations.

[0123] Step 305: Connect the spatial location of the enterprise of the pollution source emission event with the spatial location of the effective diffusion area to generate a one-way diffusion link, which takes the spatial location of the enterprise as the starting point and the spatial location of the effective diffusion area as the next node.

[0124] In step 305 , a unidirectional diffusion link represents a unidirectional propagation path of pollutants from a source to a certain area caused by a single pollution event.

[0125] In an embodiment of the present application, a straight line connection is established between the spatial location of the enterprise and the center point of each effective diffusion area, forming a one-way propagation path with the enterprise as the starting point and the effective area as the end point. Each path carries characteristic information such as emission time, duration and concentration change rate.

[0126] Step 306: Repeatedly traverse the one-way diffusion links corresponding to all pollution source emission events in the target event set, connect the one-way diffusion links with the same nodes end to end, and generate a diffusion path chain.

[0127] In an embodiment of the present application, a spatial topological analysis is performed on the unidirectional links of all target events, and the links whose end points coincide with the starting points are connected. At the same time, the rationality of the link connection is verified based on the continuity of concentration changes, and finally a path chain reflecting the complete migration process of pollutants is formed.

[0128] Here's a specific example:

[0129] In the case of chromium pollution monitoring in the electroplating park, for the four effective emission events screened out (including the abnormal emission from 9:00-14:00 on March 5), the company coordinates and emission duration (5 hours) corresponding to each event were first extracted. Chromium concentration data for eight monitoring areas within 500 meters of the company were extracted from the dynamic heat map. It was found that concentrations at three monitoring points in the northeast direction (point A 150 meters, point B 320 meters, and point C 500 meters) began to rise 6.5 hours, 8 hours, and 10 hours after the emission, respectively, forming a clear northeastward propagation order (calculated in the 35° direction using tanθ = north-south spacing difference 320 meters / east-west spacing difference 450 meters). The proportion of the duration of concentration increase at each monitoring point to the duration of emission was calculated (82% at point A, 78% at point B, and 65% at point C), all of which exceeded the preset threshold of 60%. The enterprise location was connected with these three effective areas to form three unidirectional diffusion links (enterprise to A, A to B, and B to C). By analyzing the 12 unidirectional links of the four events, it was found that the three links of the March 5 event and the two links of the March 12 event overlapped at point B, and finally connected to form a complete diffusion path chain from the enterprise through A and B to C. The total length of the path was 500 meters (obtained by the cumulative distance between each node), and the average diffusion speed was 41.7 meters / hour (500 meters / 12 hours).

[0130] In the embodiments of the present application, by establishing a precise correlation between pollution emission events and spatial diffusion characteristics, a refined reconstruction of the pollutant migration path in the industrial park is achieved, providing a reliable path basis for pollution tracing and prevention and control, and improving the spatiotemporal accuracy of pollution diffusion analysis.

[0131] To further improve the accuracy of identifying pollution diffusion areas in industrial parks, in some embodiments, step 304: calculating, based on the emission duration, the duration ratio of the concentration increasing trend in the adjacent areas pointed by the initial diffusion direction, and selecting adjacent areas whose duration ratio exceeds a preset ratio threshold as effective diffusion areas, includes:

[0132] Step 401: Generate a pollution emission time interval according to the emission start time point and emission end time point of the emission duration.

[0133] In step 401 , the pollution emission time interval represents a continuous time period defined by a pollution emission start time point and an end time point.

[0134] In an embodiment of the present application, the specific start and end times of pollution source emissions are extracted from the target event set, the emission start time is used as the starting point of the interval, and the emission end time is used as the end point of the interval to generate a complete pollution emission time period record for subsequent time matching analysis.

[0135] Step 402: Extract the starting monitoring time point corresponding to the concentration increase in the adjacent area pointed by the initial diffusion direction and the ending monitoring time point corresponding to the end of the concentration increase from the soil heavy metal concentration dynamic heat map to generate a concentration change time interval.

[0136] In step 402, the concentration change time interval represents a continuous time period from the beginning to the end of the increase in the heavy metal concentration in the monitoring area.

[0137] In an embodiment of the present application, a monitoring area within the initial diffusion direction is selected in the dynamic thermal map, the concentration data curve of each area is extracted, the starting monitoring time point when the concentration begins to rise continuously and the ending monitoring time point when the concentration tends to stabilize are identified, and a concentration change time period record of each area is formed.

[0138] Step 403: Calculate the length of the overlapping time interval between the pollution emission time interval and the concentration change time interval, and define the ratio of the overlapping time interval length to the total pollution emission time interval length as the duration ratio.

[0139] In step 403 , the length of the overlapping time interval represents the length of the overlapping portion between the pollution emission time period and the concentration change time period.

[0140] In an embodiment of the present application, the concentration change time period of each monitoring area is compared with the pollution emission time period, the duration of the overlapping part of the two time periods is calculated, and then the overlapping time is divided by the total pollution emission time to obtain a specific duration ratio value.

[0141] Step 404: Among all adjacent areas pointed by the initial diffusion direction, the adjacent areas whose duration ratio is greater than the first preset ratio threshold are marked as primary diffusion areas, and the adjacent areas whose duration ratio is greater than the second preset ratio threshold and less than or equal to the first preset ratio threshold are marked as secondary diffusion areas.

[0142] In step 404, the primary diffusion area represents a key impact area that is highly correlated with the pollution emission, and the secondary diffusion area represents a general impact area that is moderately correlated with the pollution emission.

[0143] In the embodiment of the present application, the first preset proportion threshold is set to 70%, and the second preset proportion threshold is set to 50%. Each monitoring area is classified and marked according to the calculation results to establish a grading system for the degree of pollution diffusion impact.

[0144] Step 405: Merge the areas in which the monitoring time points of the concentration increasing trend in the primary diffusion area and the secondary diffusion area continuously cover the pollution emission time interval into an effective diffusion area.

[0145] In an embodiment of the present application, the time continuity of the graded marked areas is verified, and areas where the concentration changes completely cover the pollution emission time period are screened out, and the first and second level areas that meet the conditions are merged into the final effective diffusion area set.

[0146] Here's a specific example:

[0147] For the chromium pollution emission event at the electroplating park between 9:00 AM and 2:00 PM on March 5th (emission duration 5 hours), concentration data for three monitoring points, A, B, and C, within a 35° northeast angle were extracted from the dynamic heat map. At point A, concentration began to rise 6.5 hours after the emission (3:30 PM) and continued until 7:30 PM (4 hours of increase); at point B, concentrations began to rise from 5:00 PM to 8:30 PM (3.5 hours); and at point C, concentrations rose from 7:00 PM to 10:00 PM (3 hours). The overlapping time intervals for each point were calculated: 3:30 PM to 7:00 PM at point A (3.5 hours, 70% of the time); 5:00 PM to 7:00 PM at point B (2 hours, 40% of the time); and 7:00 PM to 7:00 PM at point C (0 hours). Based on the preset thresholds (70% for level 1 and 50% for level 2), Point A was classified as a level 1 diffusion zone (70% ≥ 70%), Point B as a level 2 diffusion zone (50% > 40%), and Point C as non-compliant. Verification revealed that the concentration increase at Point A completely covered the emission period (3:30 PM to 7:00 PM, inclusive), while Point B only partially covered it. Ultimately, Point A was determined to be an effective diffusion zone. The 70% threshold was derived from a statistical analysis of 10 historical pollution incidents in the park (with an average effective zone percentage of 72 ± 5%).

[0148] In the embodiment of the present application, by establishing a precise time correlation model of pollution emissions and concentration changes, the scientific delineation of the pollution impact range of the industrial park is achieved, providing a reliable spatial basis for precise prevention and control, and improving the objectivity and accuracy of pollution area identification.

[0149] To further improve the accuracy of causal analysis of pollution events in industrial parks, in some embodiments, step 202: performing event-triggered matching on the time-stamp sequence and the concentration distribution state to screen out a target event set, includes:

[0150] Step 501: extracting the starting monitoring time point corresponding to the concentration increase in each spatial region from the concentration distribution state.

[0151] In step 501, the starting monitoring time point represents the specific time point when the heavy metal concentration in the monitoring area begins to rise continuously.

[0152] In an embodiment of the present application, a slope analysis is performed on the concentration time series curve of each monitoring area in the dynamic heat map to identify the inflection point time when the concentration change rate changes from a stable state to a continuous increase, which is recorded as the starting time of the pollution response in the area.

[0153] Step 502: Calculate the time difference between the emission start time point in the time mark sequence and the corresponding start monitoring time point when the concentration of each spatial region increases.

[0154] In step 502, the time difference calculation represents the calculation of the interval between the pollution emission start time and the concentration rise start time.

[0155] In an embodiment of the present application, the difference between the start time of each pollution source emission event and the start time of the concentration rise in each surrounding monitoring area is calculated to obtain a series of time interval data for evaluating the lag characteristics of pollution propagation.

[0156] Step 503: Filter out emission events whose time difference is less than a preset time window and whose spatial location is downwind of the pollution source enterprise or in the direction of groundwater flow from the time difference calculation results.

[0157] In step 503, the preset time window represents the maximum reasonable response time range set according to the migration characteristics of pollutants. An emission event refers to a pollutant emission activity with a clear start and end time occurring within a specific time period by a pollution source enterprise.

[0158] In the embodiment of the present application, combined with the soil characteristics and historical data of the park, 8 hours is set as the time window threshold, and monitoring areas with a time difference within the range of 0-8 hours and located downwind of the pollution source or in the direction of groundwater flow are screened out to ensure the rationality of the spatial and temporal correlation.

[0159] Step 504: Based on the emission event, determine a trigger correlation relationship between the pollution source emission event and the degree of change in soil heavy metal concentration.

[0160] In step 504 , the trigger association relationship represents a causal relationship determination between the pollution emission and the concentration change.

[0161] In an embodiment of the present application, the concentration variation range of the screened emission events is analyzed. When the concentration increase range exceeds the baseline fluctuation range by more than 3 times, it is determined that there is a clear trigger correlation relationship, and a corresponding relationship table of pollution source-receptor area is established.

[0162] Step 505: All pollution source emission events having the trigger association relationship are combined according to corresponding spatial regions to generate a target event set.

[0163] In an embodiment of the present application, all emission events that meet the association conditions are grouped and integrated according to the spatial areas they affect to form a structured data set that contains complete information such as event time, spatial location, and concentration changes.

[0164] Here's a specific example:

[0165] In the case of the electroplating park, for the chromium wastewater discharge event between 9:00 and 14:00 on a certain day of a certain month, the concentration data of 12 surrounding monitoring points were first extracted from the dynamic heat map. Among them, the concentrations of point A (150 meters from the discharge port), point B (320 meters), and point C (500 meters) in the northeast direction increased 6.5 hours (15:30), 8 hours (17:00), and 10 hours (19:00) after the discharge, respectively. The time difference between each point and the start time of the discharge was calculated (6.5 hours, 8 hours, and 10 hours). Combined with the dominant wind direction (northeast) and groundwater flow direction (30°east-northeast) of the park, points A and B (with a time difference less than the preset 8-hour window and located in the northeast) were selected. downwind); analysis showed that the chromium concentration at point A continued to rise from 5.2 mg / kg at 15:30 to 9.6 mg / kg at 19:30 (an increase of 4.4 mg / kg), and that at point B increased from 3.8 mg / kg at 17:00 to 7.2 mg / kg at 20:30 (an increase of 3.4 mg / kg), both exceeding the baseline fluctuation range (±0.5 mg / kg) by more than 6 times; ultimately, a trigger association relationship was established between this emission event and points A and B and included them in the target event set. The 8-hour time window was calculated based on the historical migration speed of chromium pollutants in the area of ​​50 meters / hour and the maximum spacing of the monitoring network of 400 meters (400÷50=8).

[0166] In the embodiments of the present application, by establishing a precise spatiotemporal correlation model between pollution emissions and soil responses, scientific tracing of pollution incidents in industrial parks is achieved, providing a reliable technical basis for pollution responsibility identification and precise governance, and improving the pertinence and effectiveness of environmental supervision.

[0167] To further improve the accuracy of the spatial distribution analysis of heavy metal pollution in industrial parks, in some embodiments, step 103: performing spatial concentration gradient calculation of heavy metal element concentration distribution on the optical sensing data based on the dynamic characteristic factor library to generate a soil heavy metal migration heat map includes:

[0168] Step 601: Obtain the measured value of the heavy metal element concentration at each monitoring point in the optical sensing data.

[0169] In step 601 , the heavy metal element concentration measurement value represents the quantitative data of the specific heavy metal content in the soil obtained by the optical sensor.

[0170] In an embodiment of the present application, the original spectral data collected by the optical sensor is analyzed, and the actual concentration values ​​of heavy metals such as chromium and lead at each monitoring point are calculated based on the intensity of the characteristic absorption peaks of heavy metals, and a corresponding relationship table between the monitoring point coordinates and the concentration values ​​is established.

[0171] Step 602: Extracting the heavy metal spatial distribution pattern corresponding to the historical pollution event from the dynamic characteristic factor library.

[0172] In step 602, the spatial distribution pattern of heavy metals represents the typical diffusion morphological characteristics of pollutants formed in historical pollution events.

[0173] In an embodiment of the present application, diffusion records of chromium pollution under similar meteorological conditions in the past three years are retrieved from the dynamic characteristic factor library, and their spatial distribution morphological characteristic parameters are extracted, including key pattern indicators such as the direction of the main diffusion axis and the concentration attenuation gradient.

[0174] Step 603: Establish a spatial grid model including all monitoring points according to the geographic coordinate positions of the monitoring points.

[0175] In step 603 , the spatial grid model represents a regularized spatial analysis unit network covering the entire industrial park.

[0176] In the embodiment of the present application, a 50m x 50m square grid system is established based on the base map of the park geographic information system, and the measured concentration value of each monitoring point is assigned to the corresponding grid node through coordinate matching.

[0177] Step 604: In the spatial grid model, for each grid node, compare the difference between the heavy metal element concentration measurement value of the current grid node and the heavy metal element concentration measurement value of the adjacent grid node.

[0178] In step 604, the relationship between the monitoring point and the grid node is that the geographical location of each monitoring point is directly mapped to a grid node in the spatial grid model, that is, one monitoring point corresponds to one grid node. The heavy metal element concentration measurement value of the grid node is directly derived from the optical sensing data of the corresponding monitoring point. The monitoring point is the physical location of the actual deployed sensor, which is responsible for data collection; the grid node is the calculation unit in the spatial grid model, which is used for concentration gradient analysis. Adjacent grid nodes refer to: for surface monitoring points: in the grid divided according to the preset spacing (such as 50 meters) with the monitoring point location as the center, the grid cells that share edges or corners are considered adjacent. For underground monitoring points: according to the direction of groundwater flow, the grids where the monitoring wells are located in the same aquifer and are closely hydraulically connected are considered adjacent. The difference in concentration measurement values ​​represents the variation range of heavy metal content in adjacent spatial locations.

[0179] In the embodiment of the present application, for each grid node, the absolute difference in chromium concentration between it and the surrounding eight adjacent nodes is calculated, and three characteristic indicators, namely the maximum difference, the minimum difference and the average difference, are recorded.

[0180] Step 605: Adjust the weight coefficients of adjacent grid nodes according to the heavy metal spatial distribution pattern.

[0181] In step 605 , the weight coefficient represents an adjustment parameter reflecting the degree of influence of the adjacent node on the current node.

[0182] In the embodiment of the present application, according to the main diffusion direction of chromium pollution in the historical distribution pattern, the adjacent nodes located in this direction are given a higher weight (0.5), and the nodes in other directions are given a lower weight (0.2), reflecting the directional characteristics of pollutant migration.

[0183] Step 606: Calculate the concentration change rate from the current grid node to each adjacent grid node based on the heavy metal element concentration difference and the weight coefficient.

[0184] In step 606 , the concentration change rate represents the rate of change of the heavy metal concentration per unit distance.

[0185] In the embodiment of the present application, the weighted average method is used to calculate the concentration change rate in each direction. The formula is: change rate = (concentration difference between adjacent nodes × weight coefficient) / node spacing, and finally a concentration change rate data set in 8 directions is obtained.

[0186] Step 607: Determine the migration direction of the heavy metal elements in the spatial grid based on all concentration change rates directed toward adjacent grid nodes.

[0187] In step 607 , the migration direction represents the main movement direction of the pollutants in space.

[0188] In the embodiment of the present application, the three directions with the largest concentration change rate are selected to calculate the vector sum, and the direction of the composite vector is determined as the main migration direction of the grid node, and the relative contribution ratio of each direction is recorded.

[0189] Step 608: Combine the heavy metal element concentration measurement value of each grid node with the corresponding migration direction to generate a soil heavy metal migration heat map.

[0190] In an embodiment of the present application, the chromium concentration value of each grid node is represented by color depth, and an arrow symbol is superimposed to indicate the migration direction. The length of the arrow reflects the rate of change, thereby generating a heat map that can intuitively display the pollution distribution and migration trend.

[0191] Here's a specific example:

[0192] In the case of the electroplating park, chromium concentration data were first obtained from 45 monitoring points (30 surface + 15 underground) (e.g., the concentration at monitoring point No. 3 was 15.6 mg / kg, calculated by comparing the intensity of the characteristic peak of the laser-induced spectrum with the standard curve); the spatial distribution patterns of five typical chromium pollution events in the past three years were extracted from the dynamic characteristic factor library, and it was found that they mainly spread along the northeast 30-45° direction; a 50m x 50m spatial grid was established to cover the entire park, and the monitoring point data were interpolated to the grid nodes (e.g., the chromium concentration at grid G-07 node was 16.2 mg / kg, calculated using the inverse distance square weighting method based on the data from the three surrounding monitoring points, with the weight being inversely proportional to the square of the distance); for each grid node (e.g., G-07), the concentration difference between it and the eight adjacent nodes was compared. The maximum difference with the G-08 node in the northeast direction is 3.8 mg / kg; according to the historical pattern, the adjacent nodes in the northeast direction are given a weight of 0.6 (0.3 in other directions), and the concentration change rate in the northeast direction is calculated to be 0.0256 (mg / kg) / m (formula: change rate = concentration difference × weight / node spacing = 3.8 × 0.6 / 50); the main migration direction of the G-07 node is determined to be 38° northeast (calculated by vector synthesis) based on the change rates in 8 directions; the final heat map shows that the area around the electroplating workshop (concentration>15 mg / kg) is red with an arrow pointing to the northeast, which is consistent with the actual pollution diffusion direction monitored subsequently. The deviation between the 38° direction and the groundwater flow direction in the park (35°) is within the allowable error range.

[0193] In the embodiments of the present application, by integrating real-time monitoring data with historical pollution patterns, accurate visualization of the spatial distribution and migration trends of heavy metal pollution in industrial parks is achieved, providing an intuitive and reliable spatial decision-making basis for pollution prevention and control, and improving the accuracy and predictability of pollution situation analysis.

[0194] To further improve the accuracy of identifying pollution source characteristics in industrial parks, in some embodiments, step 102: extracting pollution source characteristics from the production raw material composition data and the waste emission composition data, and generating a dynamic characteristic factor library based on the extracted pollution source characteristics and the monitoring data, includes:

[0195] Step 701: Identify the types of heavy metal elements in the raw materials used by each pollution source enterprise from the production raw material composition data.

[0196] In step 701, the heavy metal element type represents the category of heavy metal chemical elements with pollution risks contained in the raw material.

[0197] In an embodiment of the present application, the raw material safety data sheet reported by the enterprise is parsed, the heavy metal components such as cadmium, chromium, and lead are identified, the existence form (such as chromate, lead oxide, etc.) and content percentage of each element in the raw material are recorded, and an enterprise-raw material-heavy metal correspondence table is established.

[0198] Step 702: extracting the conversion characteristics of heavy metal components in waste discharged by each pollution source enterprise from the waste discharge component data.

[0199] In step 702, the heavy metal component transformation characteristics represent the form transformation and content change rules of heavy metal elements during the production process.

[0200] In the examples of the present application, the enterprise's wastewater and waste gas treatment records are analyzed, the differences in heavy metal forms in raw materials and waste are compared (such as the conversion of hexavalent chromium to trivalent chromium), the conversion rate of each element is calculated (the amount of heavy metals in the output waste / the amount of heavy metals in the input raw materials), and the characteristic conversion paths are identified.

[0201] Step 703: Match and associate the heavy metal element types of the same pollution source enterprise with the heavy metal component conversion characteristics to generate an enterprise-level pollution source characteristic label.

[0202] In step 703, the enterprise-level pollution source characteristic tag represents the digital identification of the enterprise's unique pollution characteristics.

[0203] In an embodiment of the present application, the types of heavy metals in the raw materials are associated with the waste conversion characteristics and coded. For example, the characteristic label of the electroplating enterprise is "Cr6+→Cr3+_high conversion rate", which includes three types of characteristic information: heavy metal type, morphological change, and conversion degree.

[0204] Step 704: Perform time series association between the enterprise-level pollution source characteristic labels and the monitoring data to generate a dynamic characteristic factor library.

[0205] In an embodiment of the present application, the enterprise feature labels are aligned with the timestamps of the real-time monitoring data, and the correspondence between the feature labels and the soil pollution responses under different production cycles is recorded to form a feature-effect association database that can be queried by time dimension.

[0206] Here's a specific example:

[0207] In the electroplating park case, for electroplating company B in the park, we first analyzed its production raw material data and found that sodium chromate (Na2CrO4) was used as the main raw material, with a chromium content of 38.5% (calculated based on the mass fraction of chromium in the sodium chromate molecular formula); extracted data from the wastewater treatment records of the company for the past six months, and calculated that the average conversion rate of chromium was 82% (calculated by dividing the total monthly wastewater chromium discharge by the total raw material chromium use, the calculation formula is: conversion rate = Σ (wastewater chromium amount) / Σ (raw material chromium amount) × 100%); in particular, we found that the conversion rate of hexavalent chromium (Cr6+) to trivalent chromium (Cr3+) in the wastewater was as high as 92% (calculated by measuring the content of chromium in different valence states by spectrophotometry); This characteristic association generates a pollution source label unique to the company, "Sodium Chromate_Cr6+→Cr3+_High Conversion Rate." This label was then correlated with monitoring data from 12 past soil pollution incidents, revealing that trivalent chromium concentrations at surrounding monitoring points increased 6-8 hours after the company's emissions (with an average peak of 8.7 mg / kg), while hexavalent chromium concentrations remained relatively low (average 1.2 mg / kg). These data validate the accuracy of the characteristic label. The resulting dynamic characteristic factor library includes feature-effect correspondence records for 36 emissions incidents from the company over the past three years, of which 82% of the conversion rate data comes from statistical analysis of the company's wastewater treatment reports for six consecutive months, providing a reliable basis for traceability for subsequent pollution warnings.

[0208] In the embodiment of the present application, by establishing a heavy metal feature tracking system for the entire process from raw materials to waste, an accurate portrait of the pollution source characteristics of the industrial park is achieved, providing a reliable pollution source feature library support for pollution tracing and early warning, and improving the accuracy and scientific nature of environmental supervision.

[0209] Figure 2 This is a schematic diagram of a structural diagram of an industrial park soil and groundwater pollution early warning level evaluation system provided in an embodiment of the present application, such as Figure 2 As shown, the system includes:

[0210] The acquisition module 21 is used to obtain production raw material composition data, waste emission composition data, monitoring data on the evolution of soil heavy metal concentration over time in historical pollution events, and optical sensing data of target monitoring points in the industrial park, including surface monitoring points and underground monitoring points.

[0211] The first generating module 22 is configured to extract pollution source characteristics from the production raw material composition data and the waste emission composition data, and generate a dynamic characteristic factor library based on the extracted pollution source characteristics and the monitoring data.

[0212] The calculation module 23 is used to calculate the spatial concentration gradient of the heavy metal element concentration distribution on the optical sensing data based on the dynamic characteristic factor library to generate a soil heavy metal migration heat map.

[0213] The second generation module 24 is used to perform a cross-modal spatiotemporal coupling analysis on the dynamic characteristic factor library and the soil heavy metal concentration dynamic heat map to generate a spatiotemporal evolution trajectory of the pollution source diffusion path in the industrial park.

[0214] The division module 25 is used to divide the industrial park into different sub-intervals based on the spatiotemporal evolution trajectory, where different sub-intervals correspond to different pollution risk warning intervals, and generate a graded prevention and control strategy for the soil and groundwater in the industrial park according to the pollution risk warning intervals and the prevention and control rules corresponding to the pollution risk warning intervals.

[0215] Figure 2 The industrial park soil and groundwater pollution early warning level evaluation system can be implemented Figure 1 The implementation principles and technical effects of the method for evaluating the early warning level of soil and groundwater pollution in an industrial park described in the illustrated embodiment are not further elaborated. The specific manner in which each module and unit performs operations in the aforementioned method for evaluating the early warning level of soil and groundwater pollution in an industrial park has been described in detail in the embodiments of the method and will not be further elaborated here.

[0216] In one possible design, Figure 2 The embodiment of the industrial park soil and groundwater pollution early warning level evaluation system can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0217] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0218] The processing component 32 is as follows Figure 1 The embodiment provides a method for evaluating early warning levels of soil and groundwater pollution in an industrial park.

[0219] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0220] The storage component 31 is configured to store various types of data to support operations on the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random-access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0221] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0222] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0223] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0224] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0225] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment provides a method for evaluating early warning levels of soil and groundwater pollution in an industrial park.

[0226] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0227] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0228] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0229] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for evaluating the early warning level of soil and groundwater pollution in industrial parks, characterized in that: include: Obtaining data on the composition of raw materials and waste emissions from pollution source enterprises within the industrial park, monitoring data on the temporal evolution of heavy metal concentrations in soil during historical pollution incidents, and optical sensing data from target monitoring points within the industrial park, including surface and underground monitoring points; Extracting pollution source characteristics from the production raw material composition data and the waste emission composition data, and generating a dynamic characteristic factor library based on the extracted pollution source characteristics and the monitoring data; Based on the dynamic characteristic factor library, calculating the spatial concentration gradient of heavy metal element concentration distribution on the optical sensing data to generate a soil heavy metal migration heat map; Performing a cross-modal spatiotemporal coupling analysis on the dynamic characteristic factor library and the soil heavy metal concentration dynamic heat map to generate a spatiotemporal evolution trajectory of the pollution source diffusion path within the industrial park; Based on the spatiotemporal evolution trajectory, the industrial park is divided into different sub-intervals, where different sub-intervals correspond to different pollution risk warning intervals. Based on the pollution risk warning intervals and the prevention and control rules corresponding to the pollution risk warning intervals, a graded prevention and control strategy for the soil and groundwater in the industrial park is generated; The cross-modal spatiotemporal coupling analysis of the dynamic characteristic factor library and the soil heavy metal concentration dynamic heat map is performed to generate the spatiotemporal evolution trajectory of the pollution source diffusion path in the industrial park, including: Extracting a time stamp sequence of pollution source emission events from the dynamic characteristic factor library, and extracting the concentration distribution state of heavy metal elements in different spatial regions from the soil heavy metal concentration dynamic heat map; Performing event trigger matching on the time mark sequence and the concentration distribution state to screen out a target event set; Combining the target event set with the concentration diffusion direction in the soil heavy metal concentration dynamic heat map to generate a diffusion path chain; Generating a spatiotemporal evolution trajectory of the pollution source diffusion path within the industrial park based on the diffusion path chain and the soil heavy metal concentration dynamic heat map; Combining the target event set with the concentration diffusion direction in the soil heavy metal concentration dynamic heat map to generate a diffusion path chain includes: Extracting the enterprise spatial location and emission duration corresponding to each pollution source emission event from the target event set; Extracting the concentration increasing trend of the adjacent areas around the spatial location of the enterprise from the soil heavy metal concentration dynamic heat map, wherein the concentration increasing trend includes the propagation order of the heavy metal concentration values ​​in each adjacent area as the monitoring time changes; Determining an initial diffusion direction corresponding to the pollution source emission event according to the propagation sequence; Based on the emission duration, the duration ratio of the concentration increasing trend in the adjacent area pointed by the initial diffusion direction is calculated, and the adjacent areas whose duration ratio exceeds a preset ratio threshold are selected as effective diffusion areas; Connecting the spatial location of the enterprise where the pollution source emission event occurs with the spatial location of the effective diffusion area to generate a one-way diffusion link, wherein the one-way diffusion link takes the spatial location of the enterprise as a starting point and the spatial location of the effective diffusion area as a next node; Repeatedly traverse the one-way diffusion links corresponding to all pollution source emission events in the target event set, connect the one-way diffusion links with the same nodes end to end, and generate a diffusion path chain.

2. The method according to claim 1, characterized in that The step of calculating the duration ratio of the concentration increasing trend in the adjacent area pointed by the initial diffusion direction based on the emission duration, and selecting the adjacent area whose duration ratio exceeds a preset ratio threshold as the effective diffusion area, includes: Generate a pollution emission time interval according to the emission start time point and emission end time point of the emission duration; Extracting the starting monitoring time point corresponding to the concentration increase in the adjacent area pointed by the initial diffusion direction and the ending monitoring time point corresponding to the end of the concentration increase from the soil heavy metal concentration dynamic heat map to generate a concentration change time interval; Calculating the length of the overlapping time interval between the pollution emission time interval and the concentration change time interval, and defining the ratio of the overlapping time interval length to the total pollution emission time interval length as the duration ratio; Among all adjacent areas pointed by the initial diffusion direction, the adjacent areas whose duration ratio is greater than a first preset ratio threshold are marked as primary diffusion areas, and the adjacent areas whose duration ratio is greater than a second preset ratio threshold and less than or equal to the first preset ratio threshold are marked as secondary diffusion areas; The areas where the monitoring time points of the concentration increasing trend in the primary diffusion area and the secondary diffusion area continuously cover the pollution emission time interval are merged into the effective diffusion area.

3. The method according to claim 1, characterized in that The performing event-triggered matching on the time-stamp sequence and the concentration distribution state to screen out a target event set includes: Extracting the starting monitoring time point corresponding to the concentration increase in each spatial region from the concentration distribution state; Calculate the time difference between the emission start time point in the time mark sequence and the start monitoring time point corresponding to the concentration increase in each spatial region; From the time difference calculation results, filter out emission events whose time difference is less than the preset time window and whose spatial location is downwind of the pollution source enterprise or in the direction of groundwater flow; Based on the emission events, determining the triggering correlation between the pollution source emission events and the degree of change in soil heavy metal concentrations; All pollution source emission events having the trigger association relationship are combined according to corresponding spatial regions to generate a target event set.

4. The method according to claim 1, wherein The calculating of the spatial concentration gradient of the heavy metal element concentration distribution on the optical sensing data based on the dynamic characteristic factor library to generate a soil heavy metal migration heat map includes: Obtaining a measured value of heavy metal element concentration at each monitoring point in the optical sensing data; Extracting the heavy metal spatial distribution pattern corresponding to the historical pollution event from the dynamic characteristic factor library; According to the geographic coordinate positions of the monitoring points, a spatial grid model including all monitoring points is established; In the spatial grid model, for each grid node, comparing the difference between the heavy metal element concentration measurement value of the current grid node and the heavy metal element concentration measurement value of the adjacent grid node; adjusting weight coefficients of adjacent grid nodes according to the heavy metal spatial distribution pattern; Calculating the concentration change rate of each adjacent grid node from the current grid node according to the heavy metal element concentration difference and the weight coefficient; Determine the migration direction of heavy metal elements in the spatial grid based on the concentration change rate of all points to adjacent grid nodes; The heavy metal element concentration measurements at each grid node were combined with the corresponding migration direction to generate a soil heavy metal migration heat map.

5. The method according to claim 1, wherein The extraction of pollution source characteristics from the production raw material composition data and the waste emission composition data, and the generation of a dynamic characteristic factor library based on the extracted pollution source characteristics and the monitoring data, include: Identify the types of heavy metal elements in the raw materials used by each pollution source enterprise from the production raw material composition data; Extracting the transformation characteristics of heavy metal components in the waste discharged by each pollution source enterprise from the waste discharge composition data; Match and associate the heavy metal element types of the same pollution source enterprise with the heavy metal component conversion characteristics to generate an enterprise-level pollution source characteristic label; The enterprise-level pollution source characteristic labels are associated with the monitoring data in time series to generate a dynamic characteristic factor library.

6. An industrial park soil and groundwater pollution early warning level evaluation system, characterized by: include: An acquisition module is used to obtain production raw material composition data, waste discharge composition data, monitoring data on the temporal evolution of soil heavy metal concentrations in historical pollution incidents, and optical sensing data from target monitoring points within the industrial park, including surface and underground monitoring points. A first generating module is configured to extract pollution source characteristics from the production raw material composition data and the waste emission composition data, and generate a dynamic characteristic factor library based on the extracted pollution source characteristics and the monitoring data; a calculation module for calculating the spatial concentration gradient of the heavy metal element concentration distribution on the optical sensing data based on the dynamic characteristic factor library to generate a soil heavy metal migration heat map; A second generation module is used to perform a cross-modal spatiotemporal coupling analysis on the dynamic characteristic factor library and the soil heavy metal concentration dynamic heat map to generate a spatiotemporal evolution trajectory of the pollution source diffusion path within the industrial park; a partitioning module for dividing the industrial park into different sub-intervals based on the spatiotemporal evolution trajectory, wherein different sub-intervals correspond to different pollution risk warning intervals, and generating a graded prevention and control strategy for the soil and groundwater of the industrial park according to the pollution risk warning intervals and the prevention and control rules corresponding to the pollution risk warning intervals; The cross-modal spatiotemporal coupling analysis of the dynamic characteristic factor library and the soil heavy metal concentration dynamic heat map is performed to generate the spatiotemporal evolution trajectory of the pollution source diffusion path in the industrial park, including: Extracting a time stamp sequence of pollution source emission events from the dynamic characteristic factor library, and extracting the concentration distribution state of heavy metal elements in different spatial regions from the soil heavy metal concentration dynamic heat map; Performing event trigger matching on the time mark sequence and the concentration distribution state to screen out a target event set; Combining the target event set with the concentration diffusion direction in the soil heavy metal concentration dynamic heat map to generate a diffusion path chain; Generating a spatiotemporal evolution trajectory of the pollution source diffusion path within the industrial park based on the diffusion path chain and the soil heavy metal concentration dynamic heat map; Combining the target event set with the concentration diffusion direction in the soil heavy metal concentration dynamic heat map to generate a diffusion path chain includes: Extracting the enterprise spatial location and emission duration corresponding to each pollution source emission event from the target event set; Extracting the concentration increasing trend of the adjacent areas around the spatial location of the enterprise from the soil heavy metal concentration dynamic heat map, wherein the concentration increasing trend includes the propagation order of the heavy metal concentration values ​​in each adjacent area as the monitoring time changes; Determining an initial diffusion direction corresponding to the pollution source emission event according to the propagation sequence; Based on the emission duration, the duration ratio of the concentration increasing trend in the adjacent area pointed by the initial diffusion direction is calculated, and the adjacent areas whose duration ratio exceeds a preset ratio threshold are selected as effective diffusion areas; Connecting the spatial location of the enterprise where the pollution source emission event occurs with the spatial location of the effective diffusion area to generate a one-way diffusion link, wherein the one-way diffusion link takes the spatial location of the enterprise as a starting point and the spatial location of the effective diffusion area as a next node; Repeatedly traverse the one-way diffusion links corresponding to all pollution source emission events in the target event set, connect the one-way diffusion links with the same nodes end to end, and generate a diffusion path chain.

7. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an industrial park soil and groundwater pollution warning level evaluation method as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, the method for evaluating the early warning level of soil and groundwater pollution in an industrial park according to any one of claims 1 to 5 is implemented.

Images