Soil heavy metal pollution intelligent detection method and system

Abstract

The invention relates to the technical field of soil pollution detection, in particular to a soil heavy metal pollution intelligent detection method and system.The method comprises the steps that soil multi-source information and regional environment parameters of to-be-detected soil are collected, and soil pollution characteristics are recognized according to the soil multi-source information; establishing a pollution identification analysis model according to the soil pollution characteristics and the regional environment parameters, and analyzing whether the to-be-detected soil contains heavy metal pollutants or not; if the heavy metal pollutants are contained, pollution diffusion paths of the heavy metal pollutants in time and space are predicted according to a pollution identification analysis model; and if the soil does not contain the heavy metal pollutants, performing time sequence analysis on soil pollution characteristics, monitoring and analyzing future concentration distribution of the heavy metal pollutants, and establishing pollution risk early warning. According to the invention, the problems of long sampling analysis time consumption, incapability of dynamically monitoring pollutant concentration change in real time, insufficient diffusion prediction accuracy and difficulty in comprehensively evaluating high-concentration and potential risk areas in a traditional soil heavy metal detection method are effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of soil pollution detection, and in particular to an intelligent detection method and system for soil heavy metal pollution. Background Art

[0002] Heavy metal pollution in soil has become a major challenge for environmental governance due to its high toxicity, difficulty in degradation and persistence. Traditional detection methods mainly rely on laboratory chemical analysis technology. Although it has high detection accuracy, it is inefficient due to the need for manual sampling and complex experimental operations, and it is difficult to meet the needs of large-scale rapid monitoring.

[0003] In addition, most existing technologies remain at the static monitoring stage and lack the ability to dynamically monitor changes in pollutant concentrations over time and space. At the same time, diffusion predictions are limited by static assumptions and fail to fully consider dynamic environmental factors such as groundwater flow rate, topography and meteorological conditions, resulting in insufficient prediction accuracy and risk assessment capabilities.

[0004] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present disclosure, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art known to those skilled in the art. Summary of the invention

[0005] The present invention provides a soil heavy metal pollution intelligent detection method and system, which can effectively solve the problems in the background technology.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is: A method for intelligent detection of soil heavy metal pollution, the method comprising: Collecting soil multi-source information and regional environmental parameters of the soil to be tested, and identifying soil pollution characteristics based on the soil multi-source information; Establishing a pollution identification and analysis model according to the soil pollution characteristics and the regional environmental parameters to analyze whether the soil to be tested contains heavy metal pollutants; If the heavy metal pollutants are present, predicting the pollution diffusion path of the heavy metal pollutants in time and space according to the pollution identification analysis model; If the soil does not contain the heavy metal pollutants, a time series analysis is performed on the soil pollution characteristics, the future concentration distribution of the heavy metal pollutants is monitored and analyzed, and a pollution risk warning is established.

[0007] Further, analyzing whether the soil to be tested contains heavy metal pollutants includes: Analyze the soil multi-source information and extract the soil pollution characteristics including soil physical parameters, chemical composition and trace heavy metal characteristics; Pulling a time period sequence, performing a fusion analysis based on the soil pollution characteristics obtained in the time period sequence, and setting a heavy metal pollution threshold based on the fusion analysis results; In combination with the regional environmental parameters, the heavy metal pollution threshold is modified and fed back to the pollution identification and analysis model; The soil pollution characteristics are input into the pollution identification analysis model, the distribution of the heavy metal pollutants and the concentration of the heavy metal pollutants are calculated, and whether the soil to be tested contains the heavy metal pollutants is determined based on the heavy metal pollution threshold.

[0008] Furthermore, the distribution of the heavy metal pollutants and the concentration of the heavy metal pollutants are calculated, including: Dividing the area of ​​the soil to be tested into a plurality of spatial units, each of the spatial units corresponding to the soil multi-source information and the regional environmental parameters; Inputting the soil pollution characteristics of each of the spatial units into the pollution identification analysis model to calculate the concentration value of the heavy metal pollutants in each of the spatial units; Performing interpolation processing on the calculated concentration values ​​of each of the spatial units to generate the pollution concentration distribution of the heavy metal pollutants in the area of ​​the soil to be tested; The distribution and pollution degree of the heavy metal pollutants are extracted based on the pollution concentration distribution.

[0009] Furthermore, interpolation processing is performed on the calculated concentration values ​​of each of the spatial units, including: Analyze the spatial correlation between each spatial unit, and construct a semivariogram based on the spatial correlation to describe the spatial variation law of the concentration value; Setting a target interpolation point, and calculating the weight of each of the spatial units around the target interpolation point according to the semivariogram, wherein the weight is dynamically adjusted according to the spatial correlation; According to the weight, weighted calculation is performed on the concentration value of the heavy metal pollutant corresponding to the spatial unit to the target interpolation point to generate the interpolation concentration of the heavy metal pollutant in the target area; The interpolation concentrations of the target interpolation points are integrated to generate the concentration distribution of heavy metal pollutants, and the spatial distribution range of heavy metal pollutants and high pollution risk areas are marked.

[0010] Further, predicting the pollution diffusion path of the heavy metal pollutants in time and space according to the pollution identification analysis model includes: Based on the soil pollution characteristics and the regional environmental parameters, setting initial regional boundary conditions for pollution diffusion; Delineating the pollution diffusion initial area according to the boundary conditions of the initial area, and identifying the location of the heavy metal pollution diffusion source in the pollution diffusion initial area; According to the initial area of ​​pollution diffusion, collecting environmental driving factors related to pollution diffusion; Combining the initial pollution diffusion area and the environmental driving factors, taking the location of the heavy metal pollution diffusion source as the starting point and the time series as the auxiliary condition, the pollution diffusion path of the heavy metal pollutants is predicted.

[0011] Furthermore, the initial regional boundary conditions for pollution diffusion are set, including: Based on the sampling location of the soil to be tested and its surrounding geographical information, the spatial scope of the initial area of ​​pollution diffusion is delineated; According to the soil pollution characteristics within the spatial range of the initial pollution diffusion area, setting the boundary value and distribution gradient of the heavy metal pollutant concentration; According to the regional environmental parameters and the distribution gradient, setting key environmental boundary conditions in the initial pollution diffusion area; The initial area boundary conditions are generated based on the key environmental boundary conditions and the boundary values ​​and distribution gradients of the heavy metal pollutant concentrations.

[0012] Furthermore, monitoring and analyzing the future concentration distribution of the heavy metal pollutants includes: Based on historical monitoring data and real-time sampling data, a pollution time series concentration database is constructed, wherein the pollution time series concentration database includes pollutant concentration values, sampling time, sampling location and environmental parameters of the region; Extracting the time series variation characteristics of the concentration of the heavy metal pollutants from the pollution time series concentration database; According to the time series variation characteristics and in combination with the pollution diffusion path, a future concentration distribution prediction model is established; Inputting the historical monitoring data and the real-time sampling data contained in the pollution time series concentration database into the future concentration distribution prediction model to generate the future concentration distribution of the heavy metal pollutants at different time points; Based on the future concentration distribution, high concentration areas and potential risk areas are evaluated and stored in the pollution time series concentration database.

[0013] Furthermore, high concentration areas and potential risk areas are assessed, including: Performing a fusion analysis on the soil pollution characteristics, and setting a heavy metal pollution threshold according to the fusion analysis results; Comparing the heavy metal pollutant concentration value generated by the future concentration distribution prediction model with the heavy metal pollution threshold, and calibrating the high concentration area exceeding the heavy metal pollution threshold; In combination with the regional environmental parameters and the pollution diffusion path, the surrounding geological, hydrological and meteorological conditions of the high-concentration area are analyzed to generate a high-concentration area distribution map; Based on the high-concentration area distribution map and the soil pollution characteristics, potential risk areas affected by pollution are delineated, and a pollution diffusion risk area map is generated.

[0014] A soil heavy metal pollution intelligent detection system, the system comprising: The information collection module collects soil multi-source information and regional environmental parameters of the soil to be tested, and identifies soil pollution characteristics based on the soil multi-source information; The pollution analysis module establishes a pollution identification and analysis model based on soil pollution characteristics and regional environmental parameters to analyze whether the soil to be tested contains heavy metal pollutants; Path identification module, if there are heavy metal pollutants, the pollution diffusion path of heavy metal pollutants in time and space is predicted according to the pollution identification analysis model; The time series monitoring module conducts a time series analysis of soil pollution characteristics if there are no heavy metal pollutants, monitors and analyzes the future concentration distribution of heavy metal pollutants, and establishes a pollution risk warning.

[0015] Furthermore, the pollution analysis module includes: The feature analysis unit analyzes soil multi-source information and extracts soil pollution characteristics including soil physical parameters, chemical composition and trace heavy metal characteristics; The time series fusion unit extracts the time period sequence, performs fusion analysis based on the soil pollution characteristics obtained in the time period sequence, and sets the heavy metal pollution threshold based on the fusion analysis results; The threshold correction unit, combined with regional environmental parameters, corrects the heavy metal pollution threshold and feeds it back to the pollution identification and analysis model; The pollution judgment unit inputs the soil pollution characteristics into the pollution identification analysis model, calculates the distribution of heavy metal pollutants and the concentration of heavy metal pollutants, and judges whether the soil to be tested contains heavy metal pollutants based on the heavy metal pollution threshold.

[0016] The technical solution of the present invention can achieve the following technical effects: By integrating multi-source information, dynamic monitoring and diffusion prediction technology, the problems of low detection efficiency, lack of dynamic monitoring, accurate diffusion prediction and risk assessment capabilities of traditional methods have been solved, effectively improving the efficiency and intelligence level of soil heavy metal pollution detection.

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of an intelligent detection method for heavy metal pollution in soil; Figure 2 A schematic diagram of the process for analyzing whether the soil to be tested contains heavy metal pollutants; Figure 3 To generate a schematic diagram of the pollution diffusion path; Figure 4 Schematic diagram of the structure for monitoring future concentration distribution. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0022] Embodiment 1; like Figure 1 As shown, the present application provides an intelligent detection method for heavy metal pollution in soil, the method comprising: S10: Collect soil multi-source information and regional environmental parameters of the soil to be tested, and identify soil pollution characteristics based on the soil multi-source information; S20: Establish a pollution identification analysis model based on soil pollution characteristics and regional environmental parameters to analyze whether the soil to be tested contains heavy metal pollutants; S30: If heavy metal pollutants are present, the pollution diffusion path of the heavy metal pollutants in time and space is predicted according to the pollution identification analysis model; S40: If there are no heavy metal pollutants, conduct a time series analysis of the soil pollution characteristics, monitor and analyze the future concentration distribution of heavy metal pollutants, and establish a pollution risk warning.

[0023] Specifically, the multi-source information of the soil samples to be tested includes the physical properties of the soil (such as permeability, porosity, and water content) and chemical composition (such as organic matter content, pH value, and heavy metal concentration). Regional environmental parameters include meteorological data related to pollution diffusion (such as precipitation, wind speed, and wind direction), hydrological conditions (such as groundwater flow rate, flow direction, and water level), and topographic characteristics (such as slope and surface undulation), which can be collected in real time through sensor networks, remote sensing technology, monitoring stations, and other equipment. Some historical data can be obtained from environmental monitoring databases. By analyzing the collected multi-source soil information, key features related to heavy metal pollution are extracted, including heavy metal concentration values, spatial distribution characteristics, and change trends. Data preprocessing methods (such as denoising and normalization) are used to ensure the validity and consistency of the data. Based on the extracted soil pollution characteristics, a preliminary judgment is made as to whether there are abnormal phenomena in soil pollution, providing support for subsequent modeling. Based on soil pollution characteristics and regional environmental parameters, machine learning algorithms (such as random forests and support vector machines) or statistical analysis methods are used to establish The pollution identification analysis model is used to analyze whether the soil to be tested contains heavy metal pollutants and to determine the type, concentration and distribution characteristics of the pollutants. For soils identified to contain heavy metal pollutants, the pollution diffusion path prediction step is entered; for soils without pollutants, the time series analysis and risk warning step is entered. After confirming that the soil to be tested contains heavy metal pollutants, the diffusion path of the pollutants is predicted according to the pollution identification analysis model. First, the initial regional boundary conditions for pollution diffusion are set, including the location of the pollution source, the initial concentration value and the regional environmental characteristics. Secondly, in combination with regional environmental parameters (such as groundwater flow rate, terrain slope) and dynamic time series, the diffusion path of heavy metal pollutants in time and space is predicted through a pollution diffusion model (such as a numerical simulation model based on Kriging interpolation or the finite element method), and a pollution distribution map and a diffusion trend map are generated.

[0024] The technical solution of the present invention solves the problems of low detection efficiency, lack of dynamic monitoring, accurate diffusion prediction and risk assessment capabilities of traditional methods, and effectively improves the efficiency and intelligence level of soil heavy metal pollution detection.

[0025] Further, if Figure 2 As shown, the soil to be tested is analyzed to see if it contains heavy metal pollutants, including: Analyze multi-source soil information and extract soil pollution characteristics including soil physical parameters, chemical composition and trace heavy metal characteristics; Pull the time period sequence, perform fusion analysis based on the soil pollution characteristics obtained in the time period sequence, and set the heavy metal pollution threshold based on the fusion analysis results; Combined with regional environmental parameters, the heavy metal pollution threshold is revised and fed back to the pollution identification and analysis model; The soil pollution characteristics are input into the pollution identification analysis model to calculate the distribution and concentration of heavy metal pollutants, and then determine whether the soil to be tested contains heavy metal pollutants based on the heavy metal pollution threshold.

[0026] As a preferred embodiment of the above, multi-source soil information of the soil to be tested is collected to extract soil pollution characteristics including soil physical parameters, chemical composition and trace heavy metal characteristics. The soil physical parameters include soil permeability, porosity and water content, the chemical composition includes soil pH value and organic matter content, and the trace heavy metal characteristics include the concentration values ​​of heavy metal pollutants (such as cadmium, lead, mercury, etc.) in the soil. After the collection is completed, the above soil pollution characteristics are analyzed to extract key indicators that can characterize the pollution characteristics, such as the concentration distribution of heavy metal pollutants and the chemical structure of the soil; the time period series data of the soil to be tested are pulled to obtain soil pollution characteristics containing different time points. The time period series data includes historical monitoring data and real-time sampling data, wherein the historical data is extracted through a database, and the real-time data is collected through on-site sensors. The changes in the soil pollution characteristics in the time period series in the time dimension are fused and analyzed to extract the change law of heavy metal concentration. According to the results of the fusion analysis, combined with the national or regional soil heavy metal pollution limit standards, a heavy metal pollution threshold is set to distinguish between contaminated soil and non-contaminated soil; combined The regional environmental parameters of the area where the soil to be tested is located are used to correct the set heavy metal pollution threshold. The regional environmental parameters include the meteorological conditions (such as precipitation and wind speed), hydrological conditions (such as groundwater flow velocity and flow direction) and topographic features (such as slope) of the area. The above regional environmental parameters are input into the correction model, and the heavy metal pollution threshold is corrected based on the regional environmental parameters to generate a corrected heavy metal pollution threshold suitable for the area, and the corrected heavy metal pollution threshold is fed back to the pollution identification analysis model to improve the model's adaptability to complex environments; the extracted soil pollution characteristics are input into the pollution identification analysis model, and combined with the corrected heavy metal pollution threshold, it is analyzed whether the soil to be tested contains heavy metal pollutants. The pollution identification analysis model calculates the distribution and concentration values ​​of pollutants based on the input soil pollution characteristics, and compares the calculation results with the corrected heavy metal pollution threshold. If the concentration value of a heavy metal pollutant in the soil sample exceeds the corrected pollution threshold, it is determined that the soil contains heavy metal pollutants; if the concentration values ​​of all heavy metal pollutants are lower than the threshold, it is determined that the soil does not contain heavy metal pollutants.

[0027] Furthermore, the distribution and concentration of heavy metal pollutants are calculated, including: The area of ​​the soil to be tested is divided into several spatial units, each of which corresponds to soil multi-source information and regional environmental parameters; The soil pollution characteristics of each spatial unit are input into the pollution identification analysis model to calculate the concentration value of heavy metal pollutants in each spatial unit; Perform interpolation processing on the calculated concentration values ​​of each spatial unit to generate the pollution concentration distribution of heavy metal pollutants in the area of ​​the soil to be tested; The distribution and pollution degree of heavy metal pollutants are extracted based on the pollution concentration distribution.

[0028] As a preferred embodiment of the above, the area of ​​the soil to be tested is divided into several spatial units to ensure that each spatial unit has sufficient data support. The division of the spatial units can be based on the geographical information of the region, for example, a regular grid division method (such as an equidistant grid) or an adaptive grid division according to the distribution of terrain features is adopted. For each spatial unit, the corresponding soil multi-source information (such as permeability, porosity, water content, etc.) and regional environmental parameters (such as groundwater flow rate, meteorological data, terrain slope, etc.) are extracted to ensure the data integrity and accuracy of each unit; the soil pollution characteristics (such as heavy metal concentration value, distribution gradient) extracted in each spatial unit are The pollution identification analysis model is input, and combined with the corrected heavy metal pollution threshold, the concentration value of heavy metal pollutants in each unit is calculated. The pollution identification analysis model can process the input feature data based on multivariate regression analysis or machine learning algorithms (such as random forest model or support vector machine model), and output the concentration value and distribution characteristics of heavy metal pollutants in each spatial unit; the calculated heavy metal pollutant concentration values ​​of each spatial unit are interpolated to generate a pollution concentration distribution map of the entire area to be tested. The interpolation processing can use the Kriging interpolation method spatial interpolation algorithm to generate more accurate pollution concentration distribution results by analyzing the variability between spatial units. The specific steps of interpolation include constructing a variation function based on known unit concentration values, determining the correlation between spatial units, calculating the concentration values ​​of interpolation points through weight distribution, and generating a complete pollution concentration distribution to show the concentration distribution of heavy metal pollutants in the entire area; based on the generated pollution concentration distribution, extracting the distribution and degree of pollution of heavy metal pollutants. The distribution includes the spatial range and diffusion path of pollutants, and the degree of pollution includes the maximum and average concentration values ​​and the distribution characteristics of the exceeding areas. Combined with environmental standards and heavy metal pollution thresholds, high pollution risk areas are marked, and corresponding pollution distribution maps and pollution degree reports are generated to provide a scientific basis for pollution control.

[0029] Furthermore, the calculated concentration values ​​of each spatial unit are interpolated, including: Analyze the spatial correlation between each spatial unit, and construct the semivariogram based on the spatial correlation to describe the spatial variation law of concentration value; Set the target interpolation point, calculate the weight of each spatial unit around the target interpolation point according to the semivariogram, and adjust the weight dynamically with the spatial correlation; According to the weights, the heavy metal pollutant concentration values ​​corresponding to the spatial units are weighted and calculated to the target interpolation points to generate the interpolation concentrations of heavy metal pollutants in the target area; The interpolation concentrations of the target interpolation points are integrated to generate the concentration distribution of heavy metal pollutants, marking the spatial distribution range of heavy metal pollutants and high pollution risk areas.

[0030] As a preferred embodiment of the above embodiment, the calculated heavy metal pollutant concentration values ​​of each spatial unit and the corresponding spatial unit are used as basic data for interpolation processing. The changes in the heavy metal pollution concentration values ​​of each spatial unit are statistically analyzed, and the correlation with the change of distance is studied, so as to identify the spatial distribution law of the heavy metal pollution concentration value. According to the results of spatial correlation analysis, a semivariogram function describing the change of concentration values ​​between spatial units is constructed. The semivariogram function is used to quantify the concentration difference between spatial units and its change law with increasing distance. Specifically, as the distance between spatial units increases, the correlation between concentration values ​​gradually weakens until it reaches an irrelevant state. According to the boundary of the area to be measured and the distribution of spatial units, unmeasured points are selected as target interpolation points to ensure that the interpolation points evenly cover the area to be measured. According to the semivariogram function, the weight value of each spatial unit around the target interpolation point is calculated. The weight value is directly related to the distance and correlation between the spatial unit and the target interpolation point. The closer the distance is, the smaller the weight value is. Units with strong spatial correlation have higher weights, while units with farther distances or weaker correlations have lower weights. The weight values ​​will be dynamically adjusted to adapt to changes in correlation between different spatial positions and units; the concentration values ​​of heavy metal pollutants in the spatial units around the target interpolation point are weighted and summed according to their weight values, and finally the concentration value of the target interpolation point is obtained. The logic of weighted calculation is that the concentration value of the target interpolation point is determined by the concentration values ​​of the surrounding spatial units and their corresponding weights. Units with higher weights have greater impact on the results, and units with lower weights have less impact; the concentration values ​​of all target interpolation points are integrated to generate the concentration distribution of heavy metal pollutants, which is used to display the pollution concentration situation in the entire area to be tested and provide complete spatial distribution information. According to the generated concentration distribution, combined with the pre-set heavy metal pollution threshold, high pollution risk areas are marked. All areas where the concentration value of the target interpolation point exceeds the threshold will be marked as high pollution risk areas and highlighted in the pollution distribution map.

[0031] Further, if Figure 3 As shown in the figure, the pollution diffusion path of heavy metal pollutants in time and space is predicted based on the pollution identification analysis model, including: Based on soil pollution characteristics and regional environmental parameters, set initial regional boundary conditions for pollution diffusion; Delineate the initial pollution diffusion area according to the initial area boundary conditions, and identify the location of the heavy metal pollution diffusion source in the initial pollution diffusion area; According to the initial area of ​​pollution spread, collect environmental driving factors related to pollution spread; Combining the initial area of ​​pollution diffusion and environmental driving factors, taking the location of the heavy metal pollution diffusion source as the starting point and the time series as the auxiliary condition, the pollution diffusion path of heavy metal pollutants is predicted.

[0032] As a preferred embodiment of the above, based on the soil pollution characteristics and regional environmental parameters of the soil to be tested, the initial concentration, distribution range and environmental impact factors of the pollutants are analyzed. The soil pollution characteristics include the concentration value and spatial distribution characteristics of heavy metal pollutants. The regional environmental parameters include groundwater flow velocity, terrain slope and meteorological conditions. According to the pollution characteristics and regional environmental parameters, the initial regional boundary conditions of pollution diffusion are determined. The initial regional boundary conditions specifically include the initial value of the pollutant concentration, the hydrodynamic conditions within the boundary range (such as groundwater flow velocity and flow direction) and the terrain and meteorological characteristics of the boundary range. The initial regional boundary conditions provide an initial data basis for the prediction of the pollution diffusion path; based on the set initial regional boundary conditions, combined with the spatial distribution characteristics and environmental parameters of the pollutants, the initial regional range of pollution diffusion is delineated. The initial regional range usually includes the key pollution area around the soil sample to be tested. In the initial pollution diffusion area, the diffusion source position of the heavy metal pollutants is located by the pollution identification analysis model. The identification of the diffusion source position is based on the pollution. The distribution law of pollutant concentration is selected, and the location with the highest concentration value is selected as the potential diffusion source to provide a starting point for diffusion path prediction; within the designated initial area, the environmental driving factors that affect pollution diffusion are collected, and the environmental driving factors are integrated with the boundary conditions of the initial area of ​​pollution diffusion to provide multi-dimensional data input for diffusion path prediction; combining the diffusion source location, initial area boundary conditions and environmental driving factors, a diffusion path model of heavy metal pollutants is established. The construction of the model can be based on numerical simulation methods (such as finite difference method or finite element method) or pollutant migration simulation algorithms (such as Darcy's law). By introducing time series analysis, the diffusion path model is combined with the time dimension to simulate the diffusion of heavy metal pollutants at different times. The time series data includes the change of pollutant concentration over time and the dynamic expansion of the diffusion range. Starting from the diffusion source location, the pollution diffusion path of pollutants in time and space is simulated, and a pollution diffusion trend graph is generated. The trend graph shows the diffusion range, concentration distribution and diffusion speed of pollutants in the region.

[0033] Furthermore, the initial regional boundary conditions for pollution diffusion are set, including: Based on the sampling location of the soil to be tested and its surrounding geographical information, the spatial scope of the initial area of ​​pollution spread is delineated; According to the soil pollution characteristics within the spatial range of the initial pollution diffusion area, the boundary value and distribution gradient of heavy metal pollutant concentration are set; According to regional environmental parameters and distribution gradients, key environmental boundary conditions are set within the initial area of ​​pollution diffusion; The initial regional boundary conditions are generated based on the key environmental boundary conditions and the boundary values ​​and distribution gradients of heavy metal pollutant concentrations.

[0034] As a preferred embodiment of the above, based on the sampling location of the soil sample to be tested, the precise location coordinates of the sampling point and the surrounding geographical environment characteristics are obtained in combination with geographic information. With the sampling location as the center, the spatial range of the initial area of ​​pollution diffusion is delineated according to the possible diffusion range and geographical characteristics of the pollutants in the area to be tested. The spatial range is delineated by combining the distribution characteristics of heavy metal concentrations, setting a certain diffusion radius, considering the restrictions of regional terrain conditions (such as mountains, rivers and other natural barriers) on the diffusion path, adjusting the shape of the spatial range, and integrating historical monitoring data and environmental parameters to optimize the initial area range to ensure that potential pollution diffusion paths are covered; within the delineated initial area, the boundary value of the pollutant concentration is set in combination with the sampling point data and the distribution characteristics of the heavy metal pollutant concentration in the area. The setting of the boundary value can refer to the national or regional soil environmental quality standards, and can also be dynamically adjusted according to the actual monitoring data. Based on the spatial distribution law of heavy metal concentrations in the initial area, the concentration value is analyzed from the pollution source location to the The gradient change of external diffusion forms the distribution gradient of pollutant concentration through the quantitative description of concentration gradient (such as the rate of change of concentration with distance) to reflect the diffusion intensity of pollutants in the initial area; regional environmental parameters related to pollution diffusion are collected in the initial area, and key environmental boundary conditions in the initial area are set in combination with regional environmental parameters. Key environmental boundary conditions describe the constraints affected by environmental factors in the pollution diffusion process, such as hydrodynamic boundary conditions, topographic boundary conditions, and meteorological boundary conditions; according to the boundary value and distribution gradient of heavy metal pollutant concentration, a comprehensive analysis is conducted with key environmental boundary conditions to form complete initial regional boundary conditions. Using the pollution identification analysis model, the above boundary values, gradients and environmental parameters are input into the model to uniformly generate boundary condition data for the initial area of ​​pollution diffusion. The generated initial regional boundary conditions include the initial area range, concentration boundary value, concentration gradient and numerical description of environmental influencing factors, which serve as the basic input for pollution diffusion path prediction.

[0035] Further, if Figure 4 As shown, monitoring and analysis of the future concentration distribution of heavy metal pollutants include: Based on historical monitoring data and real-time sampling data, a pollution time series concentration database is constructed, which includes pollutant concentration values, sampling time, sampling location and regional environmental parameters; Extracting the time series variation characteristics of the concentration of heavy metal pollutants from the pollution time series concentration database; According to the time series variation characteristics and combined with the pollution diffusion path, a future concentration distribution prediction model is established; The historical monitoring data and real-time sampling data contained in the pollution time series concentration database are input into the future concentration distribution prediction model to generate the future concentration distribution of heavy metal pollutants at different time points; Based on the future concentration distribution, high concentration areas and potential risk areas are evaluated and stored in the pollution time series concentration database.

[0036] As a preferred embodiment of the above, based on historical monitoring data and real-time sampling data, information related to heavy metal pollutants is collected, including pollutant concentration values: monitoring concentrations of heavy metal pollutants (such as cadmium, lead, mercury, etc.); sampling time: the specific time point of each monitoring or sampling; sampling location: the geographical coordinates of the soil sample collection point; regional environmental parameters: environmental factors that affect changes in pollutant concentrations, such as meteorological data (precipitation, wind speed, temperature) and hydrological data (groundwater flow rate, flow direction). The above data are collated, cleaned and stored in the pollution time series concentration database; the data in the pollution time series concentration database are denoised and normalized to eliminate outliers and data inconsistencies; the time variation characteristics of pollutant concentrations are extracted through time series analysis algorithms to identify the concentration variation trend, periodicity and mutation points, such as identifying the peak and trough of heavy metal concentrations at different time points, analyzing the growth or decrease rate of concentration over time, and determining the law of periodic changes in concentration (such as seasonal changes); based on the extracted time series characteristics and pollution diffusion path data, a future concentration distribution prediction model is established. The prediction model can use statistical methods or machine learning methods, combined with the input parameters of the pollution diffusion path (such as diffusion range, diffusion source location and environmental driving factors), to integrate the time series characteristics with the spatial diffusion characteristics; the historical monitoring data and real-time sampling data in the pollution time series concentration database are input into the future concentration distribution prediction model, and the future concentration distribution of heavy metal pollutants at different time points is predicted based on the input data and diffusion path. The generated concentration distribution includes the concentration values ​​of heavy metal pollutants at different times and the distribution of pollutants in the spatial range. The generated future concentration distribution is visualized in the form of dynamic graphics or concentration distribution maps to intuitively show the diffusion trend of heavy metal pollutants over time and space; the generated future concentration distribution is analyzed to identify high-concentration areas where pollutant concentrations exceed the set threshold, mark the area range that may be seriously affected, and analyze the potential risk areas where high-concentration areas may further spread in combination with regional environmental parameters (such as topography, groundwater flow direction), and store the results of the assessment of high-concentration areas and potential risk areas in the pollution time series concentration database as a basis for subsequent monitoring and dynamic updates.

[0037] Further, evaluate high concentration areas and potential risk areas, including: Conduct fusion analysis on soil pollution characteristics and set heavy metal pollution thresholds based on the fusion analysis results; Compare the heavy metal pollutant concentration values ​​generated by the future concentration distribution prediction model with the heavy metal pollution threshold, and calibrate the high-concentration areas that exceed the heavy metal pollution threshold; Combined with regional environmental parameters and pollution diffusion paths, the surrounding geological, hydrological and meteorological conditions of high-concentration areas are analyzed to generate a high-concentration area distribution map; Based on the high-concentration area distribution map and soil pollution characteristics, potential risk areas that may be affected by pollution are delineated and a pollution spread risk area map is generated.

[0038] As a preferred embodiment of the above, in combination with the historical monitoring data and real-time sampling data in the pollution time series concentration database, the data fusion technology is used to conduct a comprehensive analysis of the soil pollution characteristics. The analysis content includes the changes in the concentration of heavy metal pollutants in different time periods and the distribution characteristics of heavy metal concentrations in the spatial range, as well as the correlation between the concentration value and the regional environmental parameters (such as hydrological and meteorological conditions). According to the fusion analysis results, combined with the national or regional soil environmental quality standards, the threshold of heavy metal pollutants is set. The threshold represents the judgment standard for high-concentration pollution and can be dynamically adjusted based on actual data. For example, for heavy metals such as cadmium and lead, it can be set that when their concentration exceeds a certain value, they are judged as high pollution risks; the heavy metal pollutant concentration value generated by the future concentration distribution prediction model is compared point by point with the set heavy metal pollution threshold. The comparison results show whether the concentration value of each spatial position exceeds the threshold, calibrate the spatial area where the concentration value exceeds the threshold, identify the high-concentration pollution area, and the high-concentration area may be concentrated downstream of the diffusion path or near the pollution source. The calibrated high-concentration area data is recorded in the pollution time series concentration database; combined with the calibration results of the high-concentration area, a comprehensive analysis is conducted with the regional environmental parameters (such as geological, hydrological and meteorological conditions), and a high-concentration area distribution map is generated based on the analysis results, marking the scope, shape and pollutant concentration values ​​of the exceeded areas; based on the high-concentration area distribution map and the pollution diffusion path, combined with the soil pollution characteristics, the potential risk areas that may be affected by the pollution are delineated. The specific steps include determining the diffusion trend of the high-concentration area, comprehensively analyzing the environmental parameters (such as slope, water flow direction) and soil pollution characteristics of the potential risk area, and evaluating the risk of pollutant migration to the surrounding areas. Based on the above analysis results, a pollution diffusion risk area map is generated, marking the potential impact range and risk level of pollution diffusion.

[0039] Embodiment 2: Based on the same inventive concept as the soil heavy metal pollution intelligent detection method in the above embodiment, the present invention also provides a soil heavy metal pollution intelligent detection system, the system comprising: The information collection module collects soil multi-source information and regional environmental parameters of the soil to be tested, and identifies soil pollution characteristics based on the soil multi-source information; The pollution analysis module establishes a pollution identification and analysis model based on soil pollution characteristics and regional environmental parameters to analyze whether the soil to be tested contains heavy metal pollutants; Path identification module, if there are heavy metal pollutants, the pollution diffusion path of heavy metal pollutants in time and space is predicted according to the pollution identification analysis model; The time series monitoring module conducts a time series analysis of soil pollution characteristics if there are no heavy metal pollutants, monitors and analyzes the future concentration distribution of heavy metal pollutants, and establishes a pollution risk warning.

[0040] The above-mentioned adjustment system in the present invention can effectively realize an intelligent detection method for heavy metal pollution in soil, and the technical effects that can be achieved are as described in the above-mentioned embodiments, which will not be repeated here.

[0041] Specifically, the pollution analysis module includes: The feature analysis unit analyzes soil multi-source information and extracts soil pollution characteristics including soil physical parameters, chemical composition and trace heavy metal characteristics; The time series fusion unit extracts the time period sequence, performs fusion analysis based on the soil pollution characteristics obtained in the time period sequence, and sets the heavy metal pollution threshold based on the fusion analysis results; The threshold correction unit, combined with regional environmental parameters, corrects the heavy metal pollution threshold and feeds it back to the pollution identification and analysis model; The pollution judgment unit inputs the soil pollution characteristics into the pollution identification analysis model, calculates the distribution of heavy metal pollutants and the concentration of heavy metal pollutants, and judges whether the soil to be tested contains heavy metal pollutants based on the heavy metal pollution threshold.

[0042] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the method in Example 1, which will not be repeated here.

[0043] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined therein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. An intelligent detection method for heavy metal pollution in soil, characterized in that: The method comprises: Collecting soil multi-source information and regional environmental parameters of the soil to be tested, and identifying soil pollution characteristics based on the soil multi-source information; Establishing a pollution identification and analysis model according to the soil pollution characteristics and the regional environmental parameters to analyze whether the soil to be tested contains heavy metal pollutants; If the heavy metal pollutants are present, predicting the pollution diffusion path of the heavy metal pollutants in time and space according to the pollution identification analysis model; If the soil does not contain the heavy metal pollutants, a time series analysis is performed on the soil pollution characteristics, the future concentration distribution of the heavy metal pollutants is monitored and analyzed, and a pollution risk warning is established.

2. The intelligent detection method for heavy metal pollution in soil according to claim 1, characterized in that: Analyzing whether the soil to be tested contains heavy metal pollutants includes: Analyze the soil multi-source information and extract the soil pollution characteristics including soil physical parameters, chemical composition and trace heavy metal characteristics; Pulling a time period sequence, performing a fusion analysis based on the soil pollution characteristics obtained in the time period sequence, and setting a heavy metal pollution threshold based on the fusion analysis results; In combination with the regional environmental parameters, the heavy metal pollution threshold is modified and fed back to the pollution identification and analysis model; The soil pollution characteristics are input into the pollution identification analysis model, the distribution of the heavy metal pollutants and the concentration of the heavy metal pollutants are calculated, and whether the soil to be tested contains the heavy metal pollutants is determined based on the heavy metal pollution threshold.

3. The intelligent detection method for heavy metal pollution in soil according to claim 2, characterized in that: Calculate the distribution of the heavy metal pollutants and the concentration of the heavy metal pollutants, including: Dividing the area of ​​the soil to be tested into a plurality of spatial units, each of the spatial units corresponding to the soil multi-source information and the regional environmental parameters; Inputting the soil pollution characteristics of each of the spatial units into the pollution identification analysis model to calculate the concentration value of the heavy metal pollutants in each of the spatial units; Performing interpolation processing on the calculated concentration values ​​of each of the spatial units to generate the pollution concentration distribution of the heavy metal pollutants in the area of ​​the soil to be tested; The distribution and pollution degree of the heavy metal pollutants are extracted based on the pollution concentration distribution.

4. The intelligent detection method for heavy metal pollution in soil according to claim 3, characterized in that: The calculated concentration values ​​of each of the spatial units are interpolated, including: Analyze the spatial correlation between each spatial unit, and construct a semivariogram based on the spatial correlation to describe the spatial variation law of the concentration value; Setting a target interpolation point, and calculating the weight of each of the spatial units around the target interpolation point according to the semivariogram, wherein the weight is dynamically adjusted according to the spatial correlation; According to the weight, weighted calculation is performed on the concentration value of the heavy metal pollutant corresponding to the spatial unit to the target interpolation point to generate the interpolation concentration of the heavy metal pollutant in the target area; The interpolation concentrations of the target interpolation points are integrated to generate the concentration distribution of heavy metal pollutants, and the spatial distribution range of heavy metal pollutants and high pollution risk areas are marked.

5. The intelligent detection method for soil heavy metal pollution according to claim 1, characterized in that: Predicting the pollution diffusion path of the heavy metal pollutants in time and space according to the pollution identification analysis model includes: Based on the soil pollution characteristics and the regional environmental parameters, setting initial regional boundary conditions for pollution diffusion; Delineating the pollution diffusion initial area according to the boundary conditions of the initial area, and identifying the location of the heavy metal pollution diffusion source in the pollution diffusion initial area; According to the initial area of ​​pollution diffusion, collecting environmental driving factors related to pollution diffusion; Combining the initial pollution diffusion area and the environmental driving factors, taking the location of the heavy metal pollution diffusion source as the starting point and the time series as the auxiliary condition, the pollution diffusion path of the heavy metal pollutants is predicted.

6. The intelligent detection method for heavy metal pollution in soil according to claim 5, characterized in that: Set the initial area boundary conditions for pollution diffusion, including: Based on the sampling location of the soil to be tested and its surrounding geographical information, the spatial scope of the initial area of ​​pollution diffusion is delineated; According to the soil pollution characteristics within the spatial range of the initial pollution diffusion area, setting the boundary value and distribution gradient of the heavy metal pollutant concentration; According to the regional environmental parameters and the distribution gradient, setting key environmental boundary conditions in the initial pollution diffusion area; The initial area boundary conditions are generated based on the key environmental boundary conditions and the boundary values ​​and distribution gradients of the heavy metal pollutant concentrations.

7. The intelligent detection method for heavy metal pollution in soil according to claim 1, characterized in that: Monitoring and analysis of the future concentration distribution of the heavy metal pollutants, including: Based on historical monitoring data and real-time sampling data, a pollution time series concentration database is constructed, wherein the pollution time series concentration database includes pollutant concentration values, sampling time, sampling location and environmental parameters of the region; Extracting the time series variation characteristics of the concentration of the heavy metal pollutants from the pollution time series concentration database; According to the time series variation characteristics and in combination with the pollution diffusion path, a future concentration distribution prediction model is established; Inputting the historical monitoring data and the real-time sampling data contained in the pollution time series concentration database into the future concentration distribution prediction model to generate the future concentration distribution of the heavy metal pollutants at different time points; Based on the future concentration distribution, high concentration areas and potential risk areas are evaluated and stored in the pollution time series concentration database.

8. The intelligent detection method for heavy metal pollution in soil according to claim 7, characterized in that: Assess areas of high concentration and potential risk, including: Performing a fusion analysis on the soil pollution characteristics, and setting a heavy metal pollution threshold according to the fusion analysis results; Comparing the heavy metal pollutant concentration value generated by the future concentration distribution prediction model with the heavy metal pollution threshold, and calibrating the high concentration area exceeding the heavy metal pollution threshold; In combination with the regional environmental parameters and the pollution diffusion path, the surrounding geological, hydrological and meteorological conditions of the high-concentration area are analyzed to generate a high-concentration area distribution map; Based on the high-concentration area distribution map and the soil pollution characteristics, potential risk areas affected by pollution are delineated, and a pollution diffusion risk area map is generated.

9. An intelligent detection system for soil heavy metal pollution, characterized in that: The system comprises: The information collection module collects soil multi-source information and regional environmental parameters of the soil to be tested, and identifies soil pollution characteristics based on the soil multi-source information; The pollution analysis module establishes a pollution identification and analysis model based on soil pollution characteristics and regional environmental parameters to analyze whether the soil to be tested contains heavy metal pollutants; Path identification module, if there are heavy metal pollutants, the pollution diffusion path of heavy metal pollutants in time and space is predicted according to the pollution identification analysis model; The time series monitoring module conducts a time series analysis of soil pollution characteristics if there are no heavy metal pollutants, monitors and analyzes the future concentration distribution of heavy metal pollutants, and establishes a pollution risk warning.

10. The intelligent soil heavy metal pollution detection system according to claim 9, characterized in that: The pollution analysis module comprises: The feature analysis unit analyzes soil multi-source information and extracts soil pollution characteristics including soil physical parameters, chemical composition and trace heavy metal characteristics; The time series fusion unit extracts the time period sequence, performs fusion analysis based on the soil pollution characteristics obtained in the time period sequence, and sets the heavy metal pollution threshold based on the fusion analysis results; The threshold correction unit, combined with regional environmental parameters, corrects the heavy metal pollution threshold and feeds it back to the pollution identification and analysis model; The pollution judgment unit inputs the soil pollution characteristics into the pollution identification analysis model, calculates the distribution of heavy metal pollutants and the concentration of heavy metal pollutants, and judges whether the soil to be tested contains heavy metal pollutants based on the heavy metal pollution threshold.

Images