Soil environment damage and risk assessment big data analysis system

Abstract

The invention relates to the technical field of data processing, and further relates to a soil environment damage and risk assessment big data analysis system. The system comprises a data acquisition module, a data processing and fusion module, a spatial correlation analysis module and a risk assessment module. The data acquisition module is used for setting a plurality of sampling points in a target soil area and sending the acquired data to the cloud big database; the data processing and fusion module is used for extracting sparse features of the preprocessed data; the spatial correlation analysis module is used for obtaining spatial correlation indexes; the risk assessment module is used for constructing a risk prediction model; and obtaining a current soil environment risk value corresponding to each sampling point. According to the method, the comprehensiveness, the real-time performance and the precision of evaluation are remarkably improved, and meanwhile, the method has the functions of dynamic response, multi-dimensional data integration and automatic early warning.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a big data analysis system for soil environmental damage and risk assessment. Background Art

[0002] The assessment and treatment of soil environmental damage has become a key area of ​​environmental protection that has attracted global attention. However, due to the complex spatial distribution of soil pollution, the variety of pollutants, and the dynamic characteristics of migration and diffusion, existing soil risk assessment technologies still have many limitations in practical applications. At present, a variety of methods and technologies have been developed in the field of soil pollution assessment and risk management, including pollutant concentration monitoring, soil physical and chemical properties analysis, and pollution diffusion simulation.

[0003] Traditional soil pollution monitoring usually relies on manual sampling and laboratory analysis to measure the concentration of heavy metals or organic pollutants at specific sampling points. This method has high accuracy in the quantitative detection of pollutants, but its monitoring range is limited and cannot fully reflect the spatial distribution characteristics of pollutants. In addition, due to the limited number of sampling points, the results are easily affected by abnormal data at individual points, resulting in deviations in the evaluation results. In recent years, with the advancement of data processing technology, multidimensional pollutant data integration analysis has gradually become a research hotspot. For example, researchers have tried to comprehensively analyze the concentrations of multiple pollutants in the soil, soil physical and chemical parameters (such as pH, cation exchange capacity, etc.) and terrain characteristics to reveal the correlation between pollutants and their diffusion laws. This type of method has improved the comprehensiveness of the assessment to a certain extent, but due to the lack of a dynamic update mechanism, it cannot reflect the diffusion process of pollutants and their changing trends in real time. Methods based on machine learning and statistical modeling have begun to be applied to soil pollution risk prediction. Random forest, support vector machine and Lasso regression models are widely used to predict the concentration or risk level of pollutants in soil. This type of method can improve the accuracy of prediction to a certain extent, but the construction of the model usually relies on a large amount of historical data and lacks the ability to respond to real-time data. In addition, most traditional prediction models only consider a single pollutant or environmental factor, and lack analysis of the complex relationship between multiple pollutants and their environmental sensitivity. Summary of the invention

[0004] The main purpose of the present invention is to provide a soil environmental damage and risk assessment big data analysis system, which realizes efficient collection, standardized processing, dynamic analysis and accurate risk prediction of various pollutant concentrations and soil environmental parameters through the collaborative work of data acquisition, processing and fusion, spatial correlation analysis and risk assessment modules. The system is based on enhanced Lasso regression modeling, combined with environmental sensitivity, spatial distribution characteristics and sparse characteristics, to construct an intelligent risk assessment and early warning mechanism. Compared with the existing technology, the present invention significantly improves the comprehensiveness, real-time and accuracy of the assessment, and at the same time has dynamic response, multi-dimensional data integration and automatic early warning functions, providing efficient, intelligent and reliable technical support for soil pollution control and environmental protection.

[0005] In order to solve the above problems, the technical solution of the present invention is achieved as follows: A soil environmental damage and risk assessment big data analysis system, the system comprising: a data acquisition module, a data processing and fusion module, a spatial correlation analysis module and a risk assessment module; the data acquisition module is used to set up multiple sampling points in a target soil area, and to deploy the same sensor group at each sampling point, wherein the sensor group includes multiple sensors, and each sensor respectively acquires data of a type of pollutant at the sampling point, and sends the acquired data to a cloud big data database; the data processing and fusion module is used to acquire historical data acquired at sampling times before the current sampling time from the cloud big data database, perform standardization and fusion processing on the historical data, obtain pre-processed data of each sampling point, perform high-dimensional sparse feature extraction on the pre-processed data, and construct a two-layer feature dictionary to hierarchically analyze the data. Redundant information is removed and sparse features of pre-processed data are extracted; the spatial correlation analysis module is used to analyze the variation pattern of pollutant concentration over time and space based on the pre-processed data of each sampling point, and to reveal the spatial diffusion characteristics of pollutants between sampling points by constructing a spatial weight matrix and a time variation model, and to obtain spatial correlation indicators; the risk assessment module is used to calculate the environmental sensitivity of the target soil area according to the environmental parameters of the target soil area, and to associate the spatial correlation indicators, environmental sensitivity and sparse features with enhanced Lasso regression modeling to construct a risk prediction model; and the data vector composed of the pollutant data obtained at the sampling point at the current time is used as input and input into the risk prediction model to obtain the current soil environmental risk value corresponding to each sampling point.

[0006] Furthermore, the area of ​​the target soil area ranges from 50 to 500 square kilometers; in the target soil area, sampling points are set using a uniform grid, and the grid side length ranges from 10 to 50 meters; the sensor group in each sampling point is sampled once a day to obtain pollutant data.

[0007] Furthermore, the pollutant data include: cadmium concentration, lead concentration, arsenic concentration, mercury concentration, copper concentration, zinc concentration, nickel concentration, chromium concentration, polycyclic aromatic hydrocarbons concentration, polychlorinated biphenyls concentration, nitrate concentration, sulfate concentration, chloride concentration, ammonium nitrogen concentration and total petroleum hydrocarbon concentration; the environmental parameters are average values, including: average organic matter content, average cation exchange capacity, average pH value, average soil bulk density, average soil permeability coefficient, average soil electrical conductivity, average clay content, average silt content and the average value of the terrain slope of the target soil area.

[0008] Furthermore, the historical data is standardized and fused through the following formula: ; in, For the Preprocessed data of sampling points; is the number of pollutant types; For the The sampling point is obtained at the previous sampling time before the current sampling time. The original concentration of the pollutant; For the The historical average concentration of the pollutant; For the The historical standard deviation of each pollutant; For the The first sampling point obtained The highest historical concentration of pollutants; For the The first sampling point obtained The lowest concentration of pollutants in history.

[0009] Furthermore, the following formula is used to construct a two-layer feature dictionary, remove redundant information layer by layer, and extract sparse features of the preprocessed data: ; By solving the minimum optimization problem expressed by this formula, we can obtain , and , in order to calculate the sparse features of the preprocessed data for: ;in, is the pre-processed vector composed of the pre-processed data of all sampling points; is the number of sampling points; The first layer feature dictionary; is the second-layer feature dictionary; is a sparse coefficient matrix, which is a preset diagonal matrix; represents the L2 norm; represents the L1 norm; is the Laplace operator; is the absolute value operator; is the F-norm.

[0010] Furthermore, the spatial correlation index is calculated by the following formula: : ; in, Indicates The sampling point and The Euclidean distance of the sampling points; Indicates The preprocessed data of the sampling points.

[0011] Furthermore, the environmental sensitivity of the target soil area is calculated according to the environmental parameters of the target soil area through the following formula: : ; in, is the average organic matter content; is the average cation exchange capacity; is the average pH value; is the average soil bulk density; is the average soil permeability coefficient; is the average soil conductivity; and are the average clay content and average silt content of the soil, respectively; is the average value of terrain slope; is the gamma function.

[0012] Furthermore, the following formula is used to combine the enhanced Lasso regression modeling to associate the spatial correlation index, environmental sensitivity and sparse features to construct a risk prediction model: ; in, The current time The data vector is composed of the pollutant data obtained from the sampling points; the risk prediction model is a minimum optimization problem. By solving the risk prediction model, the risk prediction value is obtained. ; To calculate the determinant of the matrix; Indicates the magnitude of the vector to be calculated.

[0013] Furthermore, the risk assessment module converts the risk prediction value It is compared with the preset threshold. If it exceeds the set threshold, the target soil area is judged to be at risk and an early warning is issued.

[0014] The soil environmental damage and risk assessment big data analysis system of the present invention has the following beneficial effects: The system of the present invention achieves high-precision monitoring of the concentrations of various pollutants (such as heavy metals, organic pollutants, volatile organic compounds, salts, etc.) by setting up multiple sampling points in the target soil area and deploying a multifunctional sensor group at each sampling point. By introducing a dynamic sampling mechanism, the system can capture the temporal and spatial changes in pollutant concentrations in real time. Compared with traditional single-point sampling or intermittent monitoring methods, the present invention significantly improves the comprehensiveness and continuity of data.

[0015] In addition, through the data processing and fusion module, the system standardizes and fuses the collected multi-dimensional pollutant data, solves the problem of different dimensions of different pollutant concentrations, and removes redundant information and extracts core features through sparse feature extraction technology. This processing method ensures the quality of data integration and provides high-quality input for subsequent analysis. Especially in the case of complex interactions between multiple pollutants, the fusion processing method of the present invention can accurately reveal the coupling effects between pollutants, making up for the shortcomings of insufficient multi-pollutant analysis in the prior art.

[0016] The present invention fully integrates the environmental sensitivity factors of the target area in the risk assessment process, including key parameters such as soil pH, organic matter content, cation exchange capacity, permeability coefficient, bulk density, and terrain slope. Through the environmental sensitivity calculation formula, the system performs nonlinear modeling on these parameters and quantifies the soil's ability to adsorb, diffuse, and accumulate pollutants. Compared with the prior art, the present invention more comprehensively considers the regulatory effect of soil physical and chemical properties on the behavior of pollutants, thereby improving the scientific nature of risk assessment. Especially in a complex environment where multiple pollutants coexist, the impact of soil environmental sensitivity on risk assessment is particularly important. The present invention constructs a multi-dimensional, multi-factor risk assessment framework by combining environmental sensitivity with pollutant concentration, spatial distribution characteristics, and sparse feature matrices. This comprehensive analysis method can not only accurately assess the pollution risk of the target area, but also identify the key factors that have the greatest impact on environmental sensitivity, providing a basis for the prioritization of treatment plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of the system structure of a soil environmental damage and risk assessment big data analysis system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described 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, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0019] Example 1, reference Figure 1 : A big data analysis system for soil environmental damage and risk assessment, the system comprising: a data acquisition module, a data processing and fusion module, a spatial correlation analysis module and a risk assessment module; the data acquisition module is used to set up multiple sampling points in the target soil area, and the same sensor group is deployed at each sampling point. The sensor group includes multiple sensors, each sensor respectively obtains data of a type of pollutant in the sampling point, and sends the obtained data to a cloud big database; the data processing and fusion module is used to obtain historical data obtained at the sampling time before the current sampling time from the cloud big database, standardize and fuse the historical data, obtain pre-processed data of each sampling point, perform high-dimensional sparse feature extraction on the pre-processed data, and construct a two-layer feature dictionary to hierarchically analyze the data. Redundant information is removed and sparse features of pre-processed data are extracted; the spatial correlation analysis module is used to analyze the variation pattern of pollutant concentration over time and space based on the pre-processed data of each sampling point, and to reveal the spatial diffusion characteristics of pollutants between sampling points by constructing a spatial weight matrix and a time variation model, and to obtain spatial correlation indicators; the risk assessment module is used to calculate the environmental sensitivity of the target soil area according to the environmental parameters of the target soil area, and to associate the spatial correlation indicators, environmental sensitivity and sparse features with enhanced Lasso regression modeling to construct a risk prediction model; and the data vector composed of the pollutant data obtained at the sampling point at the current time is used as input and input into the risk prediction model to obtain the current soil environmental risk value corresponding to each sampling point.

[0020] Specifically, the data acquisition module is the foundation and starting point of the entire system. Its core principle is to provide accurate and comprehensive raw data support for subsequent data processing, spatial analysis and risk assessment through efficient multi-dimensional sampling and real-time monitoring. To achieve this goal, this module deploys multiple sampling points in the target soil area and installs a sensor group at each sampling point. The design concept of the sensor group is to combine diversity and precision. Each sensor is used to monitor a specific type of pollutant, such as heavy metals, organic pollutants, volatile organic compounds, salts or inorganic substances. Through this multi-sensor collaborative work, the system can achieve high coverage and high-precision monitoring of pollutants in the target area. Specifically, the module combines the Internet of Things technology with the cloud computing architecture. Each sensor group is connected to the regional gateway device through wireless transmission or wired connection, and the data is uploaded to the cloud database through the gateway. In the selection and layout of sensors, the present invention focuses on the diversity of pollutant characteristics and the complexity of the soil environment. For example, for monitoring heavy metal pollution, inductively coupled plasma mass spectrometry (ICP-MS) or spectral sensors are used to capture trace changes in heavy metals such as cadmium and lead in the soil with high sensitivity; for organic pollutants, portable gas chromatographs or gas sensors are used to monitor the concentration of polycyclic aromatic hydrocarbons or organochlorine pesticides; for salts and inorganic pollutants, ion selective electrode sensors are used to quickly detect key indicators such as nitrate and ammonium nitrogen. In addition, in order to capture the dynamic changes of pollutants, the data acquisition module is designed with two modes: timed sampling and continuous monitoring. Timed sampling is suitable for pollutants that change slowly, while continuous monitoring is used to capture transient concentration changes such as volatile organic compounds.

[0021] The data acquisition module not only focuses on the collection of single-point data, but also optimizes the layout of sampling points to achieve the scientificity and representativeness of spatial distribution. Specifically, the module adopts a variety of layout strategies, such as regular grid layout, random layout or hot spot layout, based on the topography of the target area, historical pollution distribution data and the location of potential pollution sources, to ensure that the distribution of sampling points can fully reflect the distribution characteristics of pollutants in the area. For areas with large pollutant concentration gradients, such as those around industrial pollution sources or areas with intensive agricultural fertilization, the spacing between sampling points will be relatively small to capture the detailed distribution of pollution. For areas with small changes in concentration gradients, the spacing between sampling points can be appropriately increased to improve monitoring efficiency while reducing costs. In addition, by dynamically adjusting the location and density of sampling points, the module can respond quickly to sudden pollution events, flexibly increase the number of sampling points in high-risk areas, and improve the timeliness and accuracy of data. In order to achieve efficient data transmission and storage, the data acquisition module constructs a distributed data transmission and cloud storage mechanism. After the sensor completes data collection, the raw data is transmitted to the cloud platform in real time through the regional gateway, and preliminary processing is completed during the transmission process, such as noise filtering, outlier detection and data compression. These processing steps are based on preset algorithm models. For example, the filtering algorithm for heavy metal data can effectively remove occasional measurement errors of sensors, and the abnormal detection of organic pollutant concentrations marks suspicious values ​​through statistical models. The processed data is uniformly stored in a large cloud database. The database design supports efficient indexing and rapid retrieval of multidimensional data, thereby providing high-quality data support for subsequent analysis modules. In addition, the data acquisition module also realizes the synchronous collection of pollutant concentrations and environmental factors by introducing environmental parameter monitoring. These environmental parameters include soil pH, organic matter content, temperature and humidity, etc., which are closely related to the mobility and bioavailability of pollutants. In the actual sampling process, the monitoring of environmental parameters is completed by dedicated sensors and recorded synchronously with the pollutant concentration data to ensure that the time and space dimensions of the two are fully matched. This multidimensional data collection method enables the system to fully consider the dynamic characteristics of pollutant behavior in subsequent analysis and improve the scientific nature of risk assessment.

[0022] The first step of data processing is to standardize the raw pollutant concentration data from the data acquisition module. Different types of pollutants, such as heavy metals, organic pollutants, salts, etc., have significant differences in their concentration ranges, physical units, and distribution characteristics, which directly affect the accuracy of subsequent analysis. The goal of standardization is to eliminate these differences so that the data of different pollutants can be compared and analyzed under a unified dimension. During the standardization process, the system uses interval scaling and distribution adjustment methods to map the concentration values ​​of each pollutant to the same normalized interval while retaining its original distribution characteristics to avoid losing important information due to data transformation. In addition, the time variation factor is introduced in the standardization process to quantify the dynamic changes of pollutant concentrations. This process fully takes into account the influence of seasonal factors and changes in environmental conditions on the concentration of some pollutants, and ensures that the processed data can truly reflect the spatial characteristics of pollutants by dynamically adjusting the weights. After completing the standardization, the system enters the data fusion stage. The fusion of pollutant data is one of the core tasks of this module, and its purpose is to integrate the concentration data of different sampling points, different time periods, and multiple pollutants into a multidimensional feature matrix. During the fusion process, the system associates the spatial location of the sampling point, the characteristic weight of the pollutant and the time dynamics based on the multi-source data weighting model. Specifically, the system assigns different weights to the data points in space according to the migration and diffusion characteristics of the pollutants. For example, in the analysis of heavy metal pollution, considering its slow migration speed, the system assigns a lower weight to the data of the long-distance sampling points in space, and a higher weight to the data of the close-distance points. Similarly, for pollutants with strong diffusion such as volatile organic compounds, the system adopts different weight distribution strategies. This weighted fusion method can effectively balance the characteristic differences of different pollutants, so that the fused data matrix can not only reflect the overall distribution law of pollutants, but also retain the local dynamic change characteristics. On the basis of data fusion, the module further performs high-dimensional sparse feature extraction. Since pollutant data usually has high dimensions and redundancy, directly using the original fused data for analysis may lead to high computational complexity and the risk of information redundancy. To this end, the system uses sparse feature extraction technology to construct a two-layer feature dictionary to achieve hierarchical dimensionality reduction of data and extraction of key features. The first-layer feature dictionary is used to extract the basic features of each pollutant, such as its average concentration, spatial distribution trend, etc. The second-layer feature dictionary extracts the coupling features and correlation patterns between multiple pollutants through cross-pollutant association analysis. This two-layer feature extraction mechanism can not only reduce data dimensions and improve computational efficiency, but also retain the potential connections between pollutants, providing more accurate feature input for subsequent spatial analysis and risk modeling.

[0023] The principle of the spatial association analysis module is first based on the spatial weight modeling of pollutant concentration data at multiple sampling points in the target area. In this process, the system constructs a spatial weight matrix based on the geographical location of the sampling points to measure the degree of correlation between different sampling points. In specific operations, the setting of spatial weights is usually based on the distance decay principle, that is, the spatial correlation between two sampling points decreases with the increase of distance. The system uses a Gaussian function or an inverse distance weight model to assign weights to the geographical distances between sampling points, thereby constructing an association network that reflects the spatial diffusion characteristics. For example, if the spatial distance between two sampling points is close and the pollutant concentration trends are similar, their spatial weights are higher, indicating that there may be a diffusion or transmission relationship between them; conversely, a lower weight indicates a weaker correlation. After constructing the spatial weight matrix, the module further calculates the spatial gradient changes in pollutant concentrations to characterize the diffusion direction and intensity of pollutants in the target area. The spatial gradient is an important indicator reflecting the change in pollutant concentration. It reveals the trend of pollutants diffusing from high-concentration areas to low-concentration areas by calculating the rate of change of concentration with spatial coordinates. In order to describe this change more accurately, the module introduces the Laplace operator to analyze the diffusion field characteristics of pollutants in the region. The results of the Laplace operator can intuitively reflect the diffusion intensity of pollutants. For example, when the Laplace value of a certain area is large, it means that the pollutant diffusion in the area is more intense; while the Laplace value is small or close to zero, it indicates that the pollutant concentration in the area is relatively uniform and the diffusion trend is not obvious. In addition, in order to quantify the spatial diffusion law more comprehensively, the spatial correlation analysis module also integrates the potential field model. The potential field is used to describe the diffusion potential and accumulation trend of pollutants in the soil, especially in the case of complex terrain or uneven distribution of pollution sources. In practical applications, the module generates a pollution potential field based on the pollutant concentration data of the sampling point, and determines the main diffusion path and boundary effect of the pollutant by calculating the gradient and divergence of the potential field. For example, when the gradient value of a potential field is large, it indicates that the pollutant has a strong diffusion ability; while in the area with a small gradient, the accumulation effect of pollutants may occur. Potential field analysis can not only reveal the overall diffusion trend of pollutants in the region, but also help identify the source or convergence point of diffusion, providing specific guidance for subsequent pollution control.

[0024] The core of the risk assessment module is to integrate the various data output by the system front-end module into a unified risk prediction model. In this process, the environmental sensitivity needs to be calculated first, which is an important basis for assessing regional risks. The calculation of environmental sensitivity depends on the physical and chemical properties of the soil (such as pH, organic matter content, cation exchange capacity, etc.) and regional ecological factors (such as vegetation coverage, biodiversity, etc.). Soil pH has a significant impact on the bioavailability and toxicity of heavy metals. For example, under acidic conditions, the solubility of cadmium and lead will increase significantly, resulting in higher mobility and biotoxicity. The organic matter content determines the soil's ability to adsorb pollutants. High organic matter content can usually fix more heavy metals or organic pollutants and reduce their migration risk. By weighted combination of these physical and chemical parameters, the system can generate a sensitivity index that comprehensively reflects the regional soil environmental status, indicating the region's carrying capacity for pollutants and potential ecological threats. Based on environmental sensitivity, the risk assessment module further incorporates the spatial correlation indicators provided by the spatial association analysis module into the model to reveal the diffusion range and dynamic characteristics of pollutants. Spatial correlation indicators not only reflect the strength of association between pollutants at different sampling points, but also quantify the pollution diffusion paths and the concentration of high-risk areas. For example, through the spatial weight matrix and gradient analysis results, the system can identify the main diffusion trend of pollutants from high-concentration areas to low-concentration areas. Combined with this information, the system can assess whether the concentration of pollutants in the target area is likely to exceed the environmental threshold, or whether there is a cumulative effect that will cause long-term pressure on the ecosystem.

[0025] Embodiment 2: The area of ​​the target soil region ranges from 50 to 500 square kilometers; in the target soil region, sampling points are set using a uniform grid with a grid side length ranging from 10 to 50 meters; the sensor group in each sampling point is sampled once a day to obtain pollutant data.

[0026] The target area has a large area, covering different types of soil environments and potential pollution sources. In order to achieve uniformity and representativeness of data collection, the monitoring scheme adopts a uniform grid layout method. Specifically, according to the complexity of the target area and the evaluation accuracy requirements, a uniform grid with a grid side length ranging from 10 to 50 meters is selected. The setting of this range mainly considers the following factors: when the pollutant concentration gradient in the area is large or the pollution sources are densely distributed, a smaller grid side length (such as 10 meters) is used to capture the subtle distribution characteristics of pollutants; in areas where the pollutant concentration is relatively uniform, the grid side length (such as 50 meters) is appropriately increased to improve monitoring efficiency and reduce sampling costs. Through this flexible grid layout method, the accuracy and economy of data collection can be effectively balanced. At each sampling point, a group of multifunctional sensor groups are deployed to collect data on different types of pollutants in the soil. The design of the sensor group can simultaneously monitor the concentrations of multiple pollutants such as heavy metals, organic pollutants, volatile organic compounds and salts. Heavy metal sensors usually use inductively coupled plasma mass spectrometry (ICP-MS) or spectral sensors, which can detect elements such as cadmium, lead, and arsenic with high sensitivity; organic pollutant sensors are based on gas chromatography or electrochemical detection technology to accurately obtain indicators such as polycyclic aromatic hydrocarbons or organochlorine pesticides. The frequency of sampling once a day fully considers the time characteristics of pollutant concentration changes and can balance the timeliness of data with sensor durability. For pollutants with large transient changes such as volatile pollutants (such as benzene, toluene, etc.), this sampling frequency can meet the general environmental assessment needs; while for pollutants with slower concentration changes such as heavy metals, the daily sampling frequency is sufficient to cover their temporal variation patterns. After each sampling, the sensor group will transmit the collected pollutant data to the regional gateway via wireless or wired network, and then upload it to the cloud big database. During the transmission process, the system will perform preliminary processing on the data, such as noise removal, outlier detection and data compression, to ensure the quality of the uploaded data. The cloud database uniformly stores and manages the collected daily data, providing efficient data support for subsequent data processing, spatial analysis and risk assessment.

[0027] Example 3: The pollutant data include: cadmium concentration, lead concentration, arsenic concentration, mercury concentration, copper concentration, zinc concentration, nickel concentration, chromium concentration, polycyclic aromatic hydrocarbons concentration, polychlorinated biphenyls concentration, nitrate concentration, sulfate concentration, chloride concentration, ammonium nitrogen concentration and total petroleum hydrocarbon concentration; the environmental parameters are average values, including: average organic matter content, average cation exchange capacity, average pH value, average soil bulk density, average soil permeability coefficient, average soil electrical conductivity, average clay content, average silt content and the average value of the terrain slope of the target soil area.

[0028] Specifically, the composition of pollutant data covers a variety of key pollutant types, which are divided into three categories: heavy metals, organic pollutants, and inorganic pollutants. In the heavy metal data, the concentrations of cadmium (Cd), lead (Pb), arsenic (As), mercury (Hg), copper (Cu), zinc (Zn), nickel (Ni), and chromium (Cr) are included. These heavy metals are common soil pollutants, and their sources include industrial waste, mining emissions, pesticide residues, etc. Each heavy metal has different behavioral characteristics. For example, cadmium and lead have strong mobility in soil, while chromium has relatively weak mobility but significant toxicity. These differences need to be quantified through feature analysis and modeling processes in the system to reveal their distribution patterns and ecological risks in the target area. Among organic pollutants, the concentrations of polycyclic aromatic hydrocarbons (PAHs) and polychlorinated biphenyls (PCBs) are included. Both types of pollutants are persistent organic pollutants with high toxicity and long-term environmental residual characteristics. The main sources of PAHs are fossil fuel combustion and industrial emissions, while PCBs come from waste industrial materials and electronic waste. Their adsorption and degradation characteristics in soil are extremely important to the environmental impact, and their spatial distribution trends need to be quantified through the dynamic analysis module in the system.

[0029] For inorganic pollutants, the system monitors nitrate (NO 3 ⁻), sulfate (SO 4 ²⁻), chloride (Cl⁻), ammonium nitrogen (NH 4⁺) and total petroleum hydrocarbons (TPH). These indicators reflect the residual nutrients in the soil and the potential pollution caused by industrial emissions. In particular, the concentrations of nitrate and ammonium nitrogen can be used to assess the impact of agricultural activities on soil quality, while total petroleum hydrocarbons are the core indicators for measuring oil pollution, which are commonly found in oil fields, transportation leaks or industrial waste sites. In addition to pollutant data, the system also defines a series of average environmental parameters that help quantify the basic state of the soil environment and its impact on the behavior of pollutants. First, the average organic matter content reflects the adsorption capacity of the soil. High organic matter content generally enhances the soil's fixation of heavy metals and organic pollutants. The average cation exchange capacity (CEC) measures the soil's ability to fix metal ions. Soils with higher CEC have a stronger adsorption capacity for cations, which helps reduce the mobility of heavy metals. The average pH value is an important parameter in the physical and chemical properties of soil, which directly affects the solubility and bioavailability of pollutants. For example, in acidic soils, the solubility of cadmium and lead will increase significantly, thereby increasing their ecological risks, while in alkaline soils, the mobility of most heavy metals will decrease significantly. The bulk density and permeability coefficient of soil reflect the compactness and water penetration capacity of the soil, which affect the horizontal diffusion and vertical migration rate of pollutants. The average electrical conductivity (EC) is used to characterize the distribution of soil salt. Soil with higher conductivity may indicate higher salt concentration, which is closely related to the distribution of nitrate and chloride. In terms of physical properties, the average clay content and average silt content reflect the distribution characteristics of soil particle composition. Higher clay content is usually accompanied by higher adsorption capacity and lower permeability, while soil with higher silt content is more prone to pollutant migration. In addition, the average terrain slope of the target soil area is a key spatial parameter that determines the intensity of surface runoff and the possibility of pollutant loss. In areas with larger slopes, pollutants may more easily enter adjacent water bodies or downstream soil areas with surface runoff, increasing the spread range and the risk of secondary pollution.

[0030] Example 4: The historical data is standardized and fused using the following formula: ; in, For the Preprocessed data of sampling points; is the number of pollutant types; For the The sampling point is obtained at the previous sampling time before the current sampling time. The original concentration of the pollutant; For the The historical average concentration of the pollutant; For the The historical standard deviation of each pollutant; For the The first sampling point obtained The highest historical concentration of pollutants; For the The first sampling point obtained The lowest concentration of pollutants in history.

[0031] Specifically, the core of the formula is to normalize and weightedly fuse the concentration data of multiple pollutants at each sampling point, and finally generate a comprehensive pre-processed data , used to characterize the The pollutant status of each sampling point. In the specific implementation, the historical data is first normalized, that is, the concentration value of each pollutant is Converted to the highest historical value relative to the sampling point and the minimum value The purpose of this step is to eliminate the numerical bias caused by the difference in magnitude of different pollutants, so that the data of all pollutants can be compared and analyzed on a unified scale. , the concentration value of each pollutant is normalized to the interval , thus ensuring that the weight of each pollutant in the calculation will not be affected by the difference in dimensions. After completing the normalization, the system further weights the data based on the historical fluctuation characteristics of the pollutants. Specifically, the Gaussian distribution function is used to adjust the normalized concentration value of each pollutant and calculate its difference from the historical average concentration. The bias weight of . The system can highlight pollutants whose concentration values ​​are close to the historical average level, and attenuate the outliers with large dispersion. This processing method is based on the statistical characteristics of pollutant distribution and can effectively reduce the interference of outliers on comprehensive data while retaining the characteristic information of major pollutants. For each sampling point, the system performs a weighted summation of the data of all pollutants to generate comprehensive pre-processed data. In the weighted summation process, the contribution of each pollutant is determined by its normalized value and Gaussian weighted value, that is, by the formula and A comprehensive expression that takes into account both concentration levels and historical volatility is constructed. This determines the complexity and diversity of the comprehensive data, and can adapt to soil environmental analysis scenarios where multiple pollutants exist at the same time.

[0032] Example 5: By constructing a two-layer feature dictionary, redundant information is removed layer by layer and sparse features of preprocessed data are extracted using the following formula: ; By solving the minimum optimization problem expressed by this formula, we can obtain , and , in order to calculate the sparse features of the preprocessed data for: ;in, is the pre-processed vector composed of the pre-processed data of all sampling points; is the number of sampling points; The first layer feature dictionary; is the second-layer feature dictionary; is a sparse coefficient matrix, which is a preset diagonal matrix; represents the L2 norm; represents the L1 norm; is the Laplace operator; is the absolute value operator; is the F-norm.

[0033] Specifically, the first term of the formula It is the core part of the objective function, indicating the preprocessing data With two layers of feature dictionaries and the sparse coefficient matrix The error between the reconstructed data under the joint action of The error measurement is performed using the norm, which aims to minimize the Euclidean distance between the original data and the reconstructed data, ensuring that the reconstructed result can reflect the feature distribution of the original data as realistically as possible. Through this optimization, the system can dynamically adjust the content of the feature dictionary and the sparsity of the sparse coefficient matrix, so that the feature extraction result not only maintains the integrity of the data, but also effectively compresses the redundant information. The second term of the formula is the sparse regularization term in the objective function, and its main function is to constrain the sparse coefficient matrix The sparsity of ensures that each feature dictionary represents the data sparsely and efficiently. The norm constrains the sparse coefficients, which can effectively suppress unimportant feature variables and focus feature extraction on dimensions that are critical to data description. The introduction of sparse regularization is particularly suitable for multidimensional pollutant data analysis, because some pollutants have little impact on the overall soil risk. Sparse regularization can automatically filter out these minor information, thereby improving the system's computational efficiency and result interpretability. is the dictionary smoothing regularization term, which is unique in that it introduces the Laplace operator , which is used to measure the smoothness and consistency of the two-layer feature dictionary. The Laplace operator can suppress high-frequency noise or abnormal data in the feature dictionary to ensure the smoothness and stability of the feature extraction results. By calculating the first layer dictionary and the second-level dictionary By constraining the Laplace value difference of the two layers and dynamically balancing the complexity and detail retention of the two layers of features, the system can avoid excessive deviation in the feature representation of the two layers of dictionaries. This optimization ensures the multi-level effect of feature extraction and improves the adaptability of the model to complex pollution scenarios. It is the hierarchical weight constraint item of the feature dictionary. By performing ratio constraints on the Frobenius norms of the two-layer dictionaries, the system can dynamically adjust the weight distribution of the first and second-layer feature dictionaries. The Frobenius norm measures the overall size of the dictionary matrix, and its ratio reflects the relative importance of the two-layer feature dictionary in data representation. When the ratio is large, it indicates that the second-layer dictionary contributes more significantly to feature extraction, which is suitable for scenarios with strong correlation between complex pollutants; when the ratio is small, the first-layer dictionary will dominate the feature extraction, which is suitable for scenarios where pollutant characteristics are relatively independent. This design introduces an adaptive weight allocation mechanism for feature extraction to ensure that the model can optimize the feature extraction process according to the characteristics of different pollution environments. By solving the minimum value of the above objective function, the system can obtain a two-layer feature dictionary. and and the sparse coefficient matrix The optimal solution of . Further calculation of sparse features , the pollutant pretreatment data Mapped into a sparse feature space. Sparse features It can highly summarize the inherent patterns of pollutant data in the target area, including global distribution characteristics and local features. By introducing a hierarchical structure of two layers of dictionaries, the system can not only effectively reduce the dimension of the data, but also dig deeper into the complex coupling relationship between multiple pollutants, providing scientific support for pollutant behavior modeling and risk assessment.

[0034] Example 6: Calculate the spatial correlation index using the following formula: : ; in, Indicates The sampling point and The Euclidean distance of the sampling points; Indicates The preprocessed data of the sampling points.

[0035] Specifically, the calculation of spatial correlation index is based on the standardized data of pollutant concentration. The data are derived from the normalization of the historical concentrations of the sampling points in the previous module. The significance of standardization is to eliminate the comparison deviation caused by the difference in dimensions or concentrations of different pollutants, so that all pollutant data can be analyzed on the same scale during the calculation process. At the same time, the formula is calculated by comparing the concentration value with the historical average concentration. Subtracting the concentration of each sampling point from the historical average, focusing on the degree to which the concentration at each sampling point deviates from the historical average. This deviation analysis method can reveal concentration anomalies, such as areas above or below the average level, and thus quantify the distribution heterogeneity of pollutants. When analyzing the spatial correlation of pollutant concentrations between sampling points, distance is a crucial factor. The formula introduces the Euclidean distance between sampling points , the attenuation effect of distance on correlation is taken into account in the calculation. Generally speaking, the spatial correlation between two sampling points will weaken as the geographical distance increases. This is a natural law based on the diffusion characteristics of pollutants. Therefore, when the distance between two sampling points is close, their concentration correlation will contribute more to the overall spatial correlation index; when the distance is far, its impact on the overall index will be significantly weakened. This distance-based weight design enables the calculation results to more truly reflect the actual diffusion range and spatial connection of pollutants.

[0036] In addition to the concentration and distance relationships between sampling points, the sparse feature matrix The introduction of further enhances the global interpretation ability of spatial correlation indicators. The sparse feature matrix is ​​the result of the dimension reduction and feature representation of the preprocessed data by the previous feature extraction module. It contains the key patterns and internal structures of the pollutant data in the target area. By calculating the Frobenius norm of the sparse feature matrix , the system can globally normalize the spatial correlation index to ensure that the correlation indexes in different regions or different pollutant combinations are comparable. This normalization method also effectively balances the relationship between local concentration correlation and global characteristic characteristics, making the final spatial correlation index It is not only applicable to pollution analysis in a single area, but also can compare results across regions or pollutant types. In the calculation process, the covariance formula of the numerator is the key to revealing the correlation between concentrations at two sampling points. Covariance describes whether the concentration deviations at two sampling points show the same trend of change. For example, when and When the deviations of both sampling points are higher than the average concentration, the product is positive, indicating that the concentration changes of the two sampling points are consistent; on the contrary, when the concentration deviation of one point is higher than the average and the other point is lower than the average, the product is negative, indicating that the concentration changes between them are inversely correlated. By summing up the covariances of all sampling point pairs, the overall correlation pattern of pollutants in the entire target area can be quantified. The final calculated The index value can directly reflect the spatial characteristics of pollutant distribution in the target area. When the value is high, it indicates that the concentration distribution of pollutants in the area has a strong spatial aggregation, high concentration points tend to be close to each other, and low concentration points also show a similar trend; when When the value is low or even negative, it means that the distribution of pollutants in the region is significantly discrete or disordered. This indicator is important for identifying the diffusion center of pollutants, high-risk areas, and potential pollution sources. By combining the calculation results with geographic information, the system can generate intuitive spatial correlation distribution maps to provide visual support for pollution control decisions.

[0037] Example 7: Calculate the environmental sensitivity of the target soil area according to the environmental parameters of the target soil area using the following formula: : ; in, is the average organic matter content; is the average cation exchange capacity; is the average pH value; is the average soil bulk density; is the average soil permeability coefficient; is the average soil conductivity; and are the average clay content and average silt content of the soil, respectively; is the average value of terrain slope; is the gamma function.

[0038] Specifically, the first part of the formula It mainly describes the contribution of soil chemical properties to environmental sensitivity. The molecules in this part are ,in Indicates the organic matter content of the soil, which is a key indicator to measure the soil's ability to adsorb pollutants. Organic matter interacts physically or chemically with pollutant molecules through its surface charge and pore structure, thereby reducing the mobility of pollutants. Therefore, a higher organic matter content usually means lower environmental sensitivity. (Cation Exchange Capacity) is a measure of the soil's ability to retain and exchange cations. It reflects the soil's potential to fix heavy metal ions (such as lead, cadmium, etc.). Soils with high CEC values ​​have a stronger ability to fix pollutants, thereby reducing their bioavailability and mobility. The formula is calculated by and Multiplying them together captures the synergistic effect of organic matter and cation exchange capacity in enhancing the soil pollution buffering capacity. It has an inhibitory or amplifying effect on environmental sensitivity. The pH value of the soil is an important factor that affects the solubility and chemical form of pollutants. For example, under acidic conditions, many heavy metals (such as lead and cadmium) become more soluble and mobile, so low pH will significantly increase environmental sensitivity. When the pH is alkaline, pollutants are more likely to form insoluble compounds, thereby reducing sensitivity. The formula nonlinearly amplifies the pH value in square form, which means that extreme changes in pH (too high or too low) have a more significant effect on sensitivity. Permeability coefficient It is a measure of the water migration capacity in the soil, which has a direct impact on the vertical migration of pollutants. The formula uses logarithmic and square root functions to The nonlinear treatment reflects the important role of highly permeable soil in the diffusion of pollutants. When the permeability coefficient is high, pollutants are more likely to enter the groundwater layer, significantly increasing environmental sensitivity.

[0039] The second part of the formula Focuses on the effects of soil particle composition, slope and bulk density. Molecular Part Represents the clay content of the soil. Clay is the smallest particle size component in the soil and has a high specific surface area and adsorption capacity. A higher clay content usually means that the soil has a stronger fixation effect on pollutants and lower mobility of pollutants, thereby reducing environmental sensitivity. The denominator includes the slope , bulk density and conductivity The sine value of the slope is used to quantify the impact of terrain on surface runoff intensity. The steeper the slope, the stronger the surface runoff, which increases the risk of pollutant loss and improves sensitivity. At the same time, the nonlinear treatment of the slope smoothes the sensitivity change through the sine function, making the model better adapted to different terrain conditions. Soil bulk density It is an important parameter to measure the compactness of soil. Its restriction on the water infiltration path directly affects the migration behavior of pollutants. Higher bulk density usually reduces the diffusion range of pollutants, thereby reducing sensitivity. However, in the formula, the effect of bulk density is overshadowed by the gamma function. Correction, where (Electrical conductivity) is an indicator of soil salt concentration. High-salinity soils usually have lower permeability, but may weaken the soil's adsorption capacity for metal pollutants due to ion competition effects. The introduction of the gamma function can describe the nonlinear regulation of salt on bulk density, allowing the model to more accurately capture the combined effects of salt and bulk density. The third part of the formula The soil silt content is characterized and slope When the silt content is high, the soil structure is loose, the particle stability is poor, and the adsorption capacity of pollutants is relatively low, so the environmental sensitivity will increase significantly. Exponential function The square of the silt content is magnified to further highlight the sensitivity impact of high silt content. The hyperbolic cosine function is used to smooth the drastic changes in slope to avoid drastic fluctuations in sensitivity in the slope extreme value area. This design ensures the stability and continuity of sensitivity calculation and enhances the model's adaptability to complex terrain conditions.

[0040] Example 8: By combining the enhanced Lasso regression modeling, the spatial correlation index, environmental sensitivity and sparse features are associated to construct a risk prediction model: ; in, The current time The data vector is composed of the pollutant data obtained from the sampling points; the risk prediction model is a minimum optimization problem. By solving the risk prediction model, the risk prediction value is obtained. ; To calculate the determinant of the matrix; Indicates the magnitude of the vector to be calculated.

[0041] Specifically, the first part of the formula Describes environmental sensitivity and spatial correlation index Risk Prediction Value The core of this part is to quantify the relationship between environmental parameters and the current state of pollutants, and to reveal the spatial distribution characteristics of pollution risks in the target area by combining spatial correlation. Indicates the current time The pollutant concentration at each sampling point is calculated by its modulus operation. Calculate the amplitude characteristics of pollutants in multidimensional space. This amplitude calculation can comprehensively reflect the overall intensity of the current pollutant concentration, rather than the changes in a single dimension, thereby more comprehensively capturing the global characteristics of the current pollution state. Environmental sensitivity As a moderating factor, Multiplied together, it describes the soil's ability to respond to the current state of the pollutant. The introduction of environmental sensitivity takes into account the regulatory effects of soil physical and chemical properties (such as pH, organic matter content, and cation exchange capacity) on the behavior of pollutants. For example, in high-pH soils, the solubility and mobility of heavy metals are low, and the risk prediction value should be reduced accordingly; while in low-pH soils, the solubility of heavy metals increases, and the predicted risk value should be significantly increased.

[0042] On the other hand, the formula The spatial correlation index The influence of is incorporated into the risk prediction model. It is an important tool to measure the global characteristics of the matrix, and its value can reflect The strength of the pollutant association between the sampling points described. When the indicator shows that the pollutant concentration is highly aggregated (e.g., pollutants in high-concentration areas are closely related to each other), the determinant value is large, and the impact on the risk prediction value increases accordingly. This design reflects that high-aggregation areas are usually accompanied by higher environmental risks, because the local accumulation of high-concentration pollutants will put greater pressure on the carrying capacity of the soil system and the surrounding ecosystem. By minimizing , the system can adjust the predicted value To match the current environmental characteristics and spatial distribution patterns, the risk can be accurately quantified. The second part of the formula The sparse feature matrix is ​​further introduced Impact on risk prediction. Sparse feature matrix It is the result generated by the previous feature extraction module, which contains the deep feature patterns of pollutant data in the target area. By removing redundant information and mining key features, the sparse feature matrix can reflect the complex distribution relationship and dynamic evolution characteristics of pollutants in the target area. In this section, the formula is expressed by the quadratic difference term Capturing environmental sensitivity and risk prediction value When the soil environment shows a high sensitivity to pollutants (i.e. When the value is large, the system tends to predict the risk value Increased to reflect the low carrying capacity of the environment for pollutants. In the design of the formula, the quadratic operation further amplifies and The impact of deviations on risk prediction ensures that the risk values ​​in highly sensitive areas more realistically reflect the vulnerability of the soil system. Introducing sparse feature matrix The ratio of the current pollutant data adjusts the weight of sparse features for risk prediction. Frobenius norm It is the overall strength measure of the sparse feature matrix, which indicates the comprehensive influence of the important patterns contained in the sparse features. In comparison, the formula can dynamically adjust the contribution of sparse features and current data to risk prediction. For example, when the deep patterns in the sparse feature matrix are highly consistent with the current data, the impact of sparse features on risk prediction will be amplified; when the intensity of sparse features is low, the impact of current pollutant data will dominate. In addition, the determinant term of the formula and The sparse features are further related to the overall characteristics of the spatial correlation index. This design captures the intrinsic connections between features at different levels through multiple matrix operations, such as how sparse feature patterns work together with spatial distribution characteristics to affect risk prediction. Finally, by minimizing , the system can optimize the risk prediction value , making it closer to the actual pollutant distribution and environmental characteristics.

[0043] Example 9: The risk assessment module converts the risk prediction value It is compared with the preset threshold. If it exceeds the set threshold, the target soil area is judged to be at risk and an early warning is issued.

[0044] Specifically, the risk prediction value It is the core output of the previous model calculation. It integrates the current concentration data, spatial distribution characteristics, environmental sensitivity and sparse characteristics of pollutants in the target area. The size of this value directly reflects the comprehensive pollution risk level of the target area: higher The value indicates that the concentration, diffusion or environmental sensitivity of the pollutant in the area is at a high level, while the lower The value indicates that the regional pollution risk is low. In this embodiment, the system classifies and determines the predicted risk level by setting a scientific and reasonable risk threshold. The setting of the threshold is the key to the entire early warning mechanism. The size of the threshold depends on the specific environmental characteristics of the target soil area, the historical pollution level, and the risk tolerance of regional management. For example, in areas with high environmental sensitivity (such as areas with high groundwater levels or soil areas with sparse vegetation cover), the threshold can be set lower to detect potential risks earlier. For areas with high background values ​​of pollutants but strong ecosystem recovery capacity, the threshold can be appropriately increased to avoid too frequent false alarms. In addition, the system also supports setting different thresholds according to specific pollutant types. For example, for heavy metal pollution, a lower threshold may be used because its migration is slow but its long-term toxicity is significant; for volatile organic compounds, the threshold may be higher to cope with instantaneous fluctuations in its concentration.

[0045] When the risk prediction value When the preset threshold is exceeded, the system will automatically determine that there is a potential pollution risk in the target area and trigger the early warning function. The early warning signal can be transmitted in a variety of ways, such as displaying a risk alarm on the system interface, notifying managers via SMS or email, or directly triggering the operation of pollution control equipment. The early warning mechanism can not only provide qualitative risk warnings, but also The magnitude of the value further quantifies the risk level. When the risk is only slightly above the threshold, the system can determine it as "low risk" and recommend basic monitoring; When it is significantly higher than the threshold, the system will judge it as "high risk" or "extremely high risk" and recommend immediate emergency control measures. In order to improve the accuracy and applicability of the early warning, the system also supports dynamic adjustment of the threshold. The adjustment mechanism of the dynamic threshold is based on historical risk data, changes in environmental conditions, and fluctuations in pollutant concentrations. For example, in seasons with frequent rainfall, the system can automatically lower the threshold to cope with the risk of pollutant leaching and diffusion caused by rainwater; in dry seasons, the threshold can be appropriately increased to reduce unnecessary false alarms. In addition, the dynamic threshold can also be adjusted in combination with the rate of change of the risk prediction value. If When the value increases rapidly in a short period of time, it usually means that the pollutant is spreading or the concentration is surging. The system can actively lower the threshold and improve the sensitivity of the early warning to ensure that potential problems are discovered in time. Another important feature of the early warning mechanism is the visual display. When the threshold is exceeded, the system generates a detailed risk analysis report and presents it in an intuitive form. For example, the system can draw a risk distribution heat map to show the spatial distribution of high-risk points in the target area; or generate a time series graph to show These visualization results can help managers quickly understand the source, scope, and evolution of risks, so as to formulate more targeted governance plans.

[0046] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. 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 invention.

Claims

1. Soil environmental damage and risk assessment big data analysis system, characterized by: The system includes: a data acquisition module, a data processing and fusion module, a spatial correlation analysis module and a risk assessment module; the data acquisition module is used to set up multiple sampling points in the target soil area, and the same sensor group is arranged at each sampling point. The sensor group includes multiple sensors, and each sensor respectively obtains data of a type of pollutant in the sampling point, and sends the obtained data to a cloud big database; the data processing and fusion module is used to obtain historical data obtained at sampling times before the current sampling time from the cloud big database, standardize and fuse the historical data, obtain pre-processed data of each sampling point, perform high-dimensional sparse feature extraction on the pre-processed data, and extract pre-processed data by constructing a two-layer feature dictionary and removing redundant information in layers. The sparse characteristics of the processing data; the spatial correlation analysis module is used to analyze the variation pattern of pollutant concentration over time and space based on the pre-processed data of each sampling point, and to reveal the spatial diffusion characteristics of pollutants between sampling points by constructing a spatial weight matrix and a time variation model, and to obtain spatial correlation indicators; the risk assessment module is used to calculate the environmental sensitivity of the target soil area according to the environmental parameters of the target soil area, and to associate the spatial correlation indicators, environmental sensitivity and sparse characteristics with enhanced Lasso regression modeling to construct a risk prediction model; and the data vector composed of the pollutant data obtained at the sampling point at the current time is used as input and input into the risk prediction model to obtain the current soil environmental risk value corresponding to each sampling point.

2. The soil environmental damage and risk assessment big data analysis system according to claim 1, characterized in that: The target soil region has an area ranging from 50 to 500 square kilometers. In the target soil region, sampling points are set up using a uniform grid with a grid side length ranging from 10 to 50 meters. The sensor group in each sampling point performs sampling once a day to obtain pollutant data.

3. The soil environmental damage and risk assessment big data analysis system according to claim 2, characterized in that: The pollutant data include: cadmium concentration, lead concentration, arsenic concentration, mercury concentration, copper concentration, zinc concentration, nickel concentration, chromium concentration, polycyclic aromatic hydrocarbons concentration, polychlorinated biphenyls concentration, nitrate concentration, sulfate concentration, chloride concentration, ammonium nitrogen concentration and total petroleum hydrocarbon concentration; the environmental parameters are average values, including: average organic matter content, average cation exchange capacity, average pH value, average soil bulk density, average soil permeability coefficient, average soil electrical conductivity, average clay content, average silt content and the average value of the terrain slope of the target soil area.

4. The soil environmental damage and risk assessment big data analysis system according to claim 3, characterized in that: The historical data is standardized and fused through the following formula: ； in, For the Preprocessed data of sampling points; is the number of pollutant types; For the The sampling point is obtained at the previous sampling time before the current sampling time. The original concentration of the pollutant; For the The historical average concentration of the pollutant; For the The historical standard deviation of each pollutant; For the The first sampling point obtained The highest historical concentration of pollutants; For the The first sampling point obtained The lowest concentration of pollutants in history.

5. The soil environmental damage and risk assessment big data analysis system according to claim 4, characterized in that: The following formula is used to construct a two-layer feature dictionary, remove redundant information layer by layer, and extract sparse features of the preprocessed data: ； By solving the minimum optimization problem expressed by this formula, we can obtain , and , in order to calculate the sparse features of the preprocessed data for: ;in, is the pre-processed vector composed of the pre-processed data of all sampling points; is the number of sampling points; The first layer feature dictionary; is the second-layer feature dictionary; is a sparse coefficient matrix, which is a preset diagonal matrix; represents the L2 norm; represents the L1 norm; is the Laplace operator; is the absolute value operator; is the F-norm.

6. The soil environmental damage and risk assessment big data analysis system according to claim 5, characterized in that: The spatial correlation index is calculated by the following formula: : ； in, Indicates The sampling point and The Euclidean distance of the sampling points; Indicates The preprocessed data of the sampling points.

7. The soil environmental damage and risk assessment big data analysis system according to claim 6, characterized in that: The environmental sensitivity of the target soil area is calculated according to the environmental parameters of the target soil area through the following formula: : ； in, is the average organic matter content; is the average cation exchange capacity; is the average pH value; is the average soil bulk density; is the average soil permeability coefficient; is the average soil conductivity; and are the average clay content and average silt content of the soil, respectively; is the average value of terrain slope; is the gamma function.

8. The soil environmental damage and risk assessment big data analysis system according to claim 7, characterized in that: The following formula is combined with enhanced Lasso regression modeling to associate spatial correlation indicators, environmental sensitivity and sparse features to build a risk prediction model: ； in, The current time The data vector is composed of the pollutant data obtained from the sampling points; the risk prediction model is a minimum optimization problem. By solving the risk prediction model, the risk prediction value is obtained. ; To calculate the determinant of the matrix; Indicates the magnitude of the vector to be calculated.

9. The soil environmental damage and risk assessment big data analysis system according to claim 8, characterized in that: The risk assessment module converts the risk prediction value It is compared with the preset threshold. If it exceeds the set threshold, the target soil area is judged to be at risk and an early warning is issued.

Images