Method and system for evaluating remediation effect of heavy metal contaminated soil

Abstract

The invention provides a heavy metal contaminated soil remediation effect evaluation method and system.The method comprises the steps that firstly, the heavy metal effective state content, microbial index data, plant index data and heavy metal ion migration data of a monitoring area are collected; calculating a repair efficiency index by using the first three types of data, exciting a nano-catalyst by microwave energy to generate active oxygen to catalyze the form transformation of the heavy metal, and recording temperature rise curve data in the reaction process; calculating a current density value of each monitoring point based on the ion migration data and generating a spatial distribution diagram; and fusing the remediation efficiency index, the temperature rise curve and the current density distribution data, inputting the fused data into a convolutional neural network, and finally outputting a soil remediation effect grade evaluation result and a spatial difference analysis result. According to the method, the accuracy and comprehensiveness of heavy metal contaminated soil remediation effect evaluation are improved.

Description

Technical Field

[0001] This application relates to the field of soil pollution remediation technology, and in particular to a method and system for evaluating the remediation effect of heavy metal contaminated soil. Background Technology

[0002] In soil heavy metal pollution remediation projects, it is necessary to establish an evaluation system that can comprehensively reflect the remediation effect. This system needs to take into account key indicators such as the transformation of heavy metals and the restoration of soil ecological functions, while also meeting the requirements of large-scale monitoring and real-time feedback, so as to provide a scientific basis for the optimization and adjustment of remediation projects.

[0003] Currently, a more advanced evaluation method is based on an evaluation model that combines soil enzyme activity with heavy metal speciation analysis. This method quantifies remediation effectiveness by detecting soil urease, catalase, and other activity indicators, combined with the content ratios of different heavy metal speciations, and constructing a comprehensive evaluation function. Specifically, enzyme activity indicators reflect the restoration status of soil ecological functions, while heavy metal speciation analysis assesses changes in the environmental risk of pollutants.

[0004] This method requires the collection of a large number of soil samples for laboratory analysis, which is time-consuming and costly. The evaluation process mainly relies on static indicators, making it difficult to capture the dynamic changes during the remediation process. In practical applications, there is a lack of monitoring methods for the real-time response processes occurring in remediation projects, causing evaluation results to lag behind the project progress. Summary of the Invention

[0005] This application provides a method and system for evaluating the remediation effect of heavy metal contaminated soil, in order to solve the problems of low accuracy and poor comprehensiveness in the evaluation of the remediation effect of heavy metal contaminated soil in the prior art.

[0006] Firstly, this application provides a method for evaluating the remediation effect of heavy metal contaminated soil, comprising:

[0007] Acquire data on the available content of heavy metals, microbial index data, plant index data, and heavy metal ion migration data in the soil monitoring area;

[0008] Based on the available content of heavy metals, the microbial index data, and the plant index data, the soil remediation efficiency index is determined.

[0009] By applying microwave energy to generate active oxygen, heavy metals in the soil are catalyzed to undergo speciation transformation, and temperature rise curve data are obtained during the catalytic transformation process.

[0010] Based on the heavy metal ion migration data, current density distribution data is generated;

[0011] The remediation efficiency index, the temperature rise curve data, and the current density distribution data are fused using a multi-source data fusion algorithm. The fusion result is then input into a convolutional neural network to output the soil remediation effect level assessment result and spatial difference analysis result.

[0012] Optionally, the remediation efficiency index, the temperature rise curve data, and the current density distribution data are fused using a multi-source data fusion algorithm. The fusion result is then input into a convolutional neural network to output the soil remediation effect level assessment result and spatial difference analysis result, including:

[0013] Create a multi-source dataset, which includes the repair efficiency index, the temperature rise curve data, and the current density distribution data;

[0014] The multi-source data set is fused using a multi-source data fusion algorithm to generate a fused feature vector.

[0015] The fused feature vector is input into the processing layer of the convolutional neural network. Through the sequential operation of multiple modules in the processing layer, the repair effect level evaluation result and spatial difference analysis result are output.

[0016] Optionally, the step of inputting the fused feature vector into the processing layer of a convolutional neural network, and outputting the repair effect level evaluation result and spatial difference analysis result through the sequential operation of multiple modules in the convolutional neural network processing layer, includes:

[0017] The fused feature vector is transformed by the transformation module in the processing layer to generate intermediate features;

[0018] The intermediate features are matched with preset level labels by the matching module in the processing layer, and a repair effect level evaluation result is generated based on the matching result.

[0019] The spatial analysis module in the processing layer reconstructs a spatial distribution map that matches the soil monitoring area.

[0020] Based on the distribution characteristics of the spatial distribution map, spatial difference analysis results are generated.

[0021] Optionally, the step of matching the intermediate features with preset level labels through the matching module in the processing layer, and generating a repair effect level evaluation result based on the matching result, includes:

[0022] The intermediate features are matched with the level label features in the preset level label library;

[0023] Based on the matching results, calculate the quantitative difference value between the intermediate features and the label features at each level;

[0024] Select the grade label corresponding to the smallest quantitative difference value, and use the grade label as the evaluation result of the repair effect grade.

[0025] Optionally, determining the soil remediation efficiency index based on the available heavy metal content, the microbial index data, and the plant index data includes:

[0026] A first weighting factor is assigned to the available content of heavy metals, a second weighting factor is assigned to the microbial index data, and a third weighting factor is assigned to the plant index data.

[0027] The available heavy metal content, the microbial index data, and the plant index data are multiplied by the corresponding first weighting factor, second weighting factor, and third weighting factor, respectively, to obtain the weighted available heavy metal content, the weighted microbial index data, and the weighted plant index data.

[0028] The remediation efficacy index is obtained by adding the weighted heavy metal bioavailability content, the weighted microbial index data, and the weighted plant index data.

[0029] Optionally, the step of generating reactive oxygen species by applying microwave energy to catalyze the speciation of heavy metals in the soil, and obtaining temperature rise curve data during the catalytic transformation process, includes:

[0030] Microwave energy is applied to the soil, and the microwave energy is used to excite the nanocatalyst to generate active oxygen;

[0031] The active oxygen triggers the redox reaction of heavy metals, catalyzes the transformation of heavy metal forms, and the temperature of the soil at each moment during the redox reaction is monitored simultaneously.

[0032] Based on the temperature of the soil at various points during the redox reaction, temperature rise curve data are generated.

[0033] Optionally, generating current density distribution data based on the heavy metal ion migration data includes:

[0034] Extract migration current values ​​and corresponding spatial location information from the heavy metal ion migration data;

[0035] The migration current value corresponding to each spatial location point in the spatial location information is correlated with the preset cross-sectional area parameter to obtain the current density value of each spatial location point.

[0036] Based on the coordinate relationship of the spatial location information, the current density values ​​of all spatial location points are spatially interpolated using the inverse distance weighting method to generate current density distribution data.

[0037] Secondly, this application provides an evaluation system for the remediation effect of heavy metal contaminated soil, comprising:

[0038] The acquisition module is used to acquire the available content of heavy metals, microbial index data, plant index data, and heavy metal ion migration data in the soil monitoring area.

[0039] The determination module is used to determine the soil remediation efficiency index based on the available content of heavy metals, the microbial index data, and the plant index data;

[0040] The catalytic module is used to generate active oxygen by applying microwave energy to catalyze the transformation of heavy metals in the soil and obtain temperature rise curve data during the catalytic transformation process.

[0041] The generation module is used to generate current density distribution data based on the heavy metal ion migration data;

[0042] The fusion module is used to fuse the remediation efficiency index, the temperature rise curve data, and the current density distribution data through a multi-source data fusion algorithm, input the fusion result into a convolutional neural network, and output the soil remediation effect level assessment result and spatial difference analysis result.

[0043] Thirdly, this application provides a computing device, including a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform an evaluation method for the remediation effect of heavy metal contaminated soil as described in any of the first aspects.

[0044] Fourthly, this application provides a computer storage medium storing computer program instructions thereon, which, when executed by a processor, implement the method for evaluating the remediation effect of heavy metal contaminated soil as described in any one of the first aspects.

[0045] This application provides a method for evaluating the remediation effect of heavy metal contaminated soil. The method includes: acquiring the available content of heavy metals, microbial index data, plant index data, and heavy metal ion migration data in a soil monitoring area; determining the soil remediation efficiency index based on the available content of heavy metals, the microbial index data, and the plant index data; generating reactive oxygen species by applying microwave energy to catalyze the speciation of heavy metals in the soil, and obtaining temperature rise curve data during the catalytic transformation process; generating current density distribution data based on the heavy metal ion migration data; fusing the remediation efficiency index, the temperature rise curve data, and the current density distribution data through a multi-source data fusion algorithm, inputting the fusion result into a convolutional neural network, and outputting the soil remediation effect level assessment result and spatial difference analysis result.

[0046] The technical solution provided in this application has the following beneficial effects:

[0047] This application establishes a comprehensive dataset for evaluating remediation effectiveness by collecting data on the available content of heavy metals, microbial indices, plant indicators, and ion migration, reflecting the multidimensional characteristics of the soil environment. It integrates three key indicators—heavy metals, microorganisms, and plants—to form a comprehensive quantitative evaluation standard, overcoming the limitations of single-indicator evaluation. Microwave-induced catalytic reactions are used to promote heavy metal speciation, while reaction intensity is recorded in real-time via temperature rise curves, enabling dynamic tracking of the remediation process. Spatial distribution maps are constructed using electrochemical migration data, visually demonstrating regional differences in heavy metal activity and providing a basis for spatial heterogeneity analysis. Combining physicochemical indicators, dynamic reaction characteristics, and spatial distribution information, deep learning is used to achieve precise grading and spatial visualization of remediation effectiveness.

[0048] Furthermore, this application also creates a multi-source dataset containing repair efficiency index, temperature rise curve and current density distribution, uses a feature fusion algorithm to generate a fused feature vector, and uses the processing layer of a convolutional neural network for in-depth analysis, and finally outputs the repair effect level assessment and spatial difference analysis results simultaneously.

[0049] Furthermore, this technology achieves the fusion of multi-dimensional information, including static indicators and dynamic processes, local features and spatial distribution, thereby improving the accuracy and comprehensiveness of the evaluation results and providing more scientific decision support for restoration projects.

[0050] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 A flowchart illustrating a method for evaluating the remediation effect of heavy metal contaminated soil, provided in an embodiment of this application;

[0053] Figure 2 A schematic diagram of a method for evaluating the remediation effect of heavy metal contaminated soil provided in an embodiment of this application;

[0054] Figure 3 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application. Detailed Implementation

[0055] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0056] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0057] Current methods for evaluating soil remediation effectiveness primarily rely on static indicators (such as heavy metal content and enzyme activity) from laboratory tests of soil samples. This approach has significant limitations: firstly, the testing process is lengthy and costly, making it difficult to provide timely guidance for remediation projects; secondly, static data alone cannot reflect dynamic changes during the remediation process, such as the real-time progress of catalytic reactions or the actual situation of heavy metal migration. This results in evaluations often lagging behind project progress and making it difficult to fully grasp the spatial distribution differences in remediation effectiveness.

[0058] To address the aforementioned issues, this application proposes a method for evaluating the remediation effectiveness of heavy metal-contaminated soil. This method involves real-time collection of multi-dimensional data during the remediation process (including soil physicochemical indicators, catalytic reaction temperature changes, and heavy metal migration currents), and comprehensive analysis using intelligent algorithms to achieve rapid and accurate evaluation of the remediation effect. Specifically, the method monitors temperature changes in real-time through microwave catalytic reaction, generates spatial distribution maps by combining this data with electrochemical migration data, and finally integrates multi-source data into an intelligent model, simultaneously outputting remediation level assessment and spatial difference analysis results. This approach overcomes the limitations of traditional static detection, dynamically tracking remediation progress and visually displaying the spatial distribution of remediation effects. It provides real-time and comprehensive data support for engineering adjustments, effectively solving the problems of lagging and incomplete coverage in existing technologies.

[0059] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0060] Figure 1 A flowchart illustrating an evaluation method for the remediation effect of heavy metal contaminated soil, as provided in this application embodiment, is shown below. Figure 1 As shown, the method includes:

[0061] Step 101: Obtain data on the available content of heavy metals, microbial index, plant indicators, and heavy metal ion migration in the soil monitoring area.

[0062] In step 101, the available heavy metal content refers to the content of heavy metal forms in the soil that can be absorbed by plants. Microbial index data reflects the diversity level of the soil's microbial community. Plant index data represents the measured values ​​of physiological indicators such as chlorophyll in plant leaves. Heavy metal ion migration data is the value of the moving current of heavy metal ions under the influence of an electric field, measured through electrodes.

[0063] In this embodiment, several monitoring points are set up, and surface soil samples are collected at each monitoring point. The bioavailable content of heavy metals is determined using chemical extraction. Simultaneously, soil samples are collected for microbial culture analysis to calculate the microbial diversity index. Plant leaves near the monitoring points are selected, and plant physiological indicators are obtained using a chlorophyll meter. Electrode devices are installed at the monitoring points, and the migration current values ​​of heavy metal ions are recorded after applying a weak voltage. All data are wirelessly transmitted and aggregated to a data processing center.

[0064] For example, in a heavy metal contaminated area A, 20 monitoring points were set up. The available cadmium content in the soil was extracted using DTPA solution, and the content at point 1 was measured to be X mg / kg. Soil samples from point 1 were plate-cultured, and the Shannon index (Y) was calculated by counting the number of colonies. The SPAD value (Z) of rice leaves near point 1 was measured. Electrodes were installed at point 1, and the migration current (ImA) was measured after applying a voltage (V). All data were uploaded via an IoT terminal.

[0065] Step 102: Determine the soil remediation efficiency index based on the available content of heavy metals, the microbial index data, and the plant index data.

[0066] In step 102, the remediation efficiency index is a quantitative indicator that comprehensively reflects the soil remediation effect. It is obtained by weighted calculation of three types of indicators: heavy metals, microorganisms, and plants.

[0067] In this embodiment, different weighting coefficients are assigned to the collected heavy metal bioavailability, microbial index, and plant indicators. The measured values ​​of each indicator are multiplied by their corresponding weights and then summed to obtain the remediation efficacy index for each monitoring point. The weighting coefficients are determined using an expert scoring method to reflect the degree of influence of each indicator on the remediation effect.

[0068] For example, we set a weight for heavy metals (a), a weight for microorganisms (b), and a weight for plants (c). The remediation efficacy index for point 1 is calculated as a × X + b × Y + c × Z. The index calculation results for the 20 monitoring points constitute a set of remediation efficacy indices for subsequent analysis.

[0069] Step 103: Active oxygen is generated by applying microwave energy to catalyze the transformation of heavy metals in the soil and obtain temperature rise curve data during the catalytic transformation process.

[0070] In step 103, microwave energy is electromagnetic wave energy of a specific frequency. Reactive oxygen species are highly reactive oxygen free radicals generated by the catalytic reaction. The temperature rise curve is a recorded curve showing the temperature change over time during the reaction.

[0071] In this embodiment, microwave radiation with predetermined parameters is applied to the soil to activate an added nanocatalyst, generating reactive oxygen species. These reactive oxygen species undergo a redox reaction with heavy metals, releasing heat and causing the soil temperature to rise. During the reaction, a temperature sensor records the soil temperature at fixed intervals, generating a temperature rise curve.

[0072] For example, when microwaves with power P are applied to region A, catalyst M generates hydroxyl radicals. Point 1 is at time t1 and temperature T1, t2 is T2, ..., tn is Tn; connecting these points forms a temperature rise curve. The rate of exothermic reaction reflects the catalytic conversion efficiency.

[0073] Step 104: Generate current density distribution data based on the heavy metal ion migration data.

[0074] In step 104, the current density is the numerical value of the current intensity passing through a unit area. The current density distribution data reflects the spatial distribution of heavy metal migration activity.

[0075] In this embodiment, the migration current value measured at each monitoring point is divided by the contact area of ​​its corresponding electrode to obtain the current density value. Based on the coordinates of the monitoring points, a spatial interpolation algorithm is used to calculate the current density in the unmonitored area, generating a distribution map of the entire area.

[0076] For example, dividing the current I at point 1 by the electrode area S yields the current density J1 = I / S. The J values ​​from the 20 monitoring points are interpolated to generate a current density distribution map for region A, showing a higher density in the central area.

[0077] Step 105: Using a multi-source data fusion algorithm, the remediation efficiency index, the temperature rise curve data, and the current density distribution data are fused together. The fusion result is then input into a convolutional neural network to output the soil remediation effect level assessment result and spatial difference analysis result.

[0078] In step 105, multi-source data fusion is a technique for integrating and processing data of different types. The restoration effect level is a classification evaluation of the restoration effect. Spatial difference analysis reflects the regional distribution characteristics of the restoration effect.

[0079] In this embodiment, the repair efficiency index, temperature rise curve, and current density distribution data are standardized. A fused feature vector is generated using a feature extraction algorithm. The feature vector is then input into a pre-trained convolutional neural network, which outputs the repair effect level and spatial difference distribution map.

[0080] For example, the three types of data in area A are standardized to generate a feature vector F. F is input into a CNN (Convolutional Neural Network) model, and the output shows that the effect level in the northeast of area A is good, and that the effect level in the southwest is medium, and a heat map of the spatial distribution of the repair effect is generated.

[0081] This method achieves a comprehensive evaluation of soil remediation effectiveness through multi-dimensional data collection, dynamic process monitoring, and intelligent analysis. It considers both static indicators and dynamic processes, and also displays spatial differences, providing a more scientific and timely basis for remediation projects. The entire method is standardized in operation, and the evaluation results are intuitive and reliable, improving the accuracy and practicality of remediation effectiveness evaluation.

[0082] To improve the comprehensiveness and accuracy of soil remediation effect evaluation, in some embodiments, step 105 involves fusing the remediation efficiency index, the temperature rise curve data, and the current density distribution data using a multi-source data fusion algorithm, inputting the fusion result into a convolutional neural network, and outputting the soil remediation effect level assessment result and spatial difference analysis result, including:

[0083] Step 201: Create a multi-source data set, which includes the repair efficiency index, the temperature rise curve data, and the current density distribution data.

[0084] In step 201, the multi-source dataset refers to a comprehensive dataset that includes the repair efficiency index, temperature rise curve data, and current density distribution data.

[0085] In this embodiment, the three types of data obtained in the previous steps—repair efficiency index, temperature rise curve, and current density distribution—are first summarized and organized. Based on the spatial correspondence of the monitoring points, the three types of data are matched and aligned according to a unified format to establish a dataset containing multi-dimensional features. This dataset provides the foundation for subsequent feature fusion.

[0086] Step 202: Use a multi-source data fusion algorithm to perform feature fusion on the multi-source data set to generate a fused feature vector.

[0087] In step 202, the fused feature vector refers to the unified feature representation formed by integrating features of different types of data.

[0088] In this embodiment, the various types of data in the dataset are standardized to eliminate dimensional differences. Key features are extracted from the three types of data using a feature extraction method. The extracted features are then concatenated and combined according to preset rules to form a fused feature vector containing multi-dimensional features. This vector fully preserves the key information of each type of data.

[0089] Step 203: Input the fused feature vector into the processing layer of the convolutional neural network. Through the sequential operation of multiple modules in the processing layer, output the repair effect level evaluation result and the spatial difference analysis result.

[0090] In step 203, the processing layer refers to the network layer in the convolutional neural network that performs feature processing.

[0091] In this embodiment, the fused feature vector is input into a pre-trained convolutional neural network. The network first extracts spatial features through convolutional layers, then performs feature compression through pooling layers, and finally outputs the repair effect level and spatial distribution features through fully connected layers. The level evaluation is divided into four standards: excellent, good, average, and poor, and spatial analysis generates a visual distribution map.

[0092] Here is a specific example:

[0093] During the evaluation of the remediation effectiveness in Zone A of heavy metal pollution, the data from the 20 monitoring points obtained in the early stage were first integrated into a multi-source dataset. This dataset included 20 values ​​such as the remediation efficiency index for each monitoring point (e.g., the index value for point 1 is aX + bY + cZ = 9.2, and for point 2 it is 8.7), temperature rise curves for each point (e.g., continuous temperature records such as T1 = 25 degrees Celsius at time t1 and T2 = 28 degrees Celsius at time t2 for point 1), and current density distribution data (e.g., J1 for point 1 is I / S = 2.4 mA / cm²). 2 Point 2 has an A / cm value of 2.1 mA. 2 Twenty numerical values ​​were collected. These three data types were standardized to ensure all values ​​were within the same dimension range. The repair efficiency index was standardized by subtracting the mean and dividing by the standard deviation; the temperature rise curve data was normalized to the maximum temperature value; and the current density data was normalized to the regional maximum value. Features were extracted from the standardized data: regional mean features were extracted from the repair efficiency index; temperature rise rate features were extracted from the temperature rise curve; and spatial gradient features were extracted from the current density data. These features were concatenated to form a 160-dimensional fusion feature vector F. This vector was input into a pre-trained convolutional neural network. The network first performed spatial correlation analysis on the features using convolutional kernels, then compressed the feature dimension through pooling operations, and finally processed through fully connected layers. The output showed that the repair effect level of the eight monitoring points in the northeast of Area A was good, with an average repair efficiency index of 8.9, a temperature rise rate of 0.8 degrees Celsius / hour, and a current density of 2.2 mA / cm². 2 The 12 monitoring points in the southwest were classified as medium, corresponding to an average index of 7.8, a temperature rise rate of 0.6 degrees Celsius / hour, and a current density of 1.8 mA / cm³. 2 The generated heatmap shows that the red area represents the northeastern region with better remediation results, while the yellow area represents the southwestern region with moderate results, providing a clear basis for subsequent remediation projects to focus on strengthening the southwestern region. The calculation formulas used throughout the analysis include: Remediation Efficiency Index = aX + bY + cZ, where a is the weight for heavy metals (0.5), b is the weight for microorganisms (0.3), c is the weight for plants (0.2), X is the available cadmium content, Y is the microbial index, Z is the plant chlorophyll value, and the current density J is equal to I / S, where I is the migration current and S is the electrode area.

[0094] In this embodiment, the method achieves a comprehensive evaluation of the restoration effect through multi-source data fusion and intelligent analysis. It provides both an overall level assessment and displays spatial distribution characteristics, offering a more scientific and intuitive decision-making basis for restoration projects. The entire method is standardized in operation, and the evaluation results are reliable, improving the accuracy and practicality of restoration effect evaluation.

[0095] To improve the accuracy and visualization of the repair effect evaluation, in some embodiments, step 203 involves inputting the fused feature vector into the processing layer of a convolutional neural network. Through the sequential operation of multiple modules in the convolutional neural network processing layer, the repair effect level evaluation result and spatial difference analysis result are output, including:

[0096] Step 301: The fused feature vector is transformed by the transformation module in the processing layer to generate intermediate features.

[0097] In step 301, the transformation module refers to the network structure that transforms the input features. Feature transformation refers to the process of extracting deep features from the data through mathematical operations. Intermediate features refer to the feature data with higher representational power obtained after transformation.

[0098] In this embodiment, the fused feature vector first enters the transformation module, where the features are recombined and calculated according to preset transformation rules to highlight key information and eliminate redundant features. The spatial correlation of features is maintained during the transformation process, generating intermediate features that are more conducive to subsequent processing.

[0099] Step 302: The intermediate features are matched with preset level labels by the matching module in the processing layer, and a repair effect level evaluation result is generated based on the matching result.

[0100] In step 302, the matching module is a network structure that compares features with standards. The preset level labels are pre-defined features that categorize repair effectiveness. The matching result refers to the similarity data between the input features and each level standard.

[0101] In this embodiment, after the intermediate feature is input into the matching module, its similarity to the preset four-level label features (excellent, good, average, and poor) is calculated. Based on the principle of highest similarity, the level corresponding to the repair effect is determined, and an evaluation result containing a specific level identifier is generated.

[0102] Step 303: Reconstruct a spatial distribution map matching the soil monitoring area using the spatial resolution module in the processing layer.

[0103] In step 303, the spatial resolution module is the network structure for reconstructing spatial distribution features. A spatial distribution map is a visual graph that reflects the distribution of features in a region.

[0104] In this embodiment of the application, after the intermediate features are input into the spatial analysis module, the spatial distribution features of the repair effect are reconstructed according to the location information contained in the features and the actual distribution relationship of the monitoring points, and a distribution map that completely corresponds to the region is generated.

[0105] Step 304: Generate spatial difference analysis results based on the distribution characteristics of the spatial distribution map.

[0106] In step 304, the distribution characteristics of the spatial distribution map are obtained by analyzing the numerical change trends of each grid point in the reconstructed distribution map. Specifically, the values ​​of each monitoring point and its surrounding area are compared to identify the distribution patterns of high-value areas, low-value areas, and transition areas. Then, combined with the continuity and gradient characteristics of numerical changes, the spatial distribution characteristics of the repair effect are finally determined.

[0107] In this embodiment of the application, the numerical change trend of each region in the spatial distribution map is analyzed, the spatial distribution pattern of the repair effect is identified, and an analysis report containing regional difference descriptions and visualizations is generated.

[0108] Here is a specific example:

[0109] During the evaluation of the remediation effect in heavy metal pollution zone A, the 160-dimensional fused feature vector F, formed in the early stage, was input into a convolutional neural network. First, the feature transformation calculation in the transformation module reduced the 160-dimensional features to 32-dimensional intermediate feature vectors. The feature transformation used matrix multiplication F' = W × F, where W is a 32 × 160 weight matrix, F is the 160-dimensional input feature, and F' is the 32-dimensional output feature. These intermediate features were then input into the matching module for similarity calculation with the preset four-level standard features (excellent, good, medium, and poor). The features of the northeastern monitoring points had a similarity of 0.85 with the good level, while the features of the southwestern monitoring points had a similarity of 0.72 with the medium level. Based on the principle of highest similarity, the remediation level of the 8 monitoring points in the northeast was determined to be good, and the remediation level of the 12 monitoring points in the southwest was determined to be medium. Meanwhile, the spatial analysis module reconstructs a 20m × 20m gridded spatial distribution map that perfectly corresponds to the actual area based on the location coding information contained in the 32-dimensional intermediate features. The value of each grid point in the map ranges from 0 to 1. Analysis of the map reveals that the values ​​of grid points in the northeast are generally above 0.8, while the values ​​in the southwest are between 0.5 and 0.7. There is also a clear gradient characteristic of decreasing values ​​from the northeast to the southwest. Based on this distribution characteristic, the spatial difference analysis report clearly points out that the restoration effect is uneven across regions and recommends strengthening the governance measures in the southwest.

[0110] In this embodiment, the method achieves precise grading and spatial visualization of restoration effects through multi-module collaborative processing of a neural network. It provides both an overall evaluation conclusion and displays detailed regional differences, offering a reliable basis for targeted governance. The entire processing flow is highly automated, and the evaluation results are intuitive and clear, enhancing the practical value of restoration effect evaluation.

[0111] To improve the accuracy of the repair effect level assessment, in some embodiments, step 302: matching the intermediate features with preset level labels through the matching module in the processing layer, and generating a repair effect level assessment result based on the matching result, includes:

[0112] Step 401: Match the intermediate features with the level tag features in the preset level tag library.

[0113] In step 401, the preset grade label library refers to a pre-established dataset containing standard features for four grades: excellent, good, average, and poor. Grade label features refer to the typical feature patterns corresponding to each grade. Matching refers to the process of calculating the similarity between the input features and the features of each grade.

[0114] In this embodiment, the similarity between the intermediate feature vector and the four level features in the level label library is calculated. A specific similarity algorithm is used to quantify the closeness between the intermediate feature and each level feature, providing a basis for subsequent level determination.

[0115] Step 402: Based on the matching results, calculate the quantitative difference value between the intermediate features and the label features at each level.

[0116] In step 402, the quantified difference value refers to the degree of feature difference expressed numerically. Difference value calculation refers to the process of quantifying the difference between two features using mathematical methods.

[0117] In this embodiment, a difference algorithm is used to calculate the difference between intermediate features and each level feature. The smaller the value, the higher the similarity, providing an objective basis for level selection through numerical comparison.

[0118] Step 403: Select the grade label corresponding to the smallest quantitative difference value, and use the grade label as the evaluation result of the repair effect grade.

[0119] In step 403, the minimum difference value refers to the smallest value among the calculated results. The grade label as a result means that the grade with the smallest difference value is determined as the final evaluation grade.

[0120] In this embodiment of the application, all difference values ​​between the intermediate feature and each level feature are compared, and the smallest one is selected as the level label corresponding to it as the assessment result of the repair effect level of the monitoring area.

[0121] Here is a specific example:

[0122] During the evaluation of the remediation effectiveness in Zone A of heavy metal pollution, the 32-dimensional intermediate feature vector F' generated from eight monitoring points in the northeast was matched with four standard features from a pre-set grade label library. The Euclidean distance formula was used. Calculate the difference value, where F′ i G represents the value of the i-th dimension of the intermediate feature vector. i Let represent the i-th dimension of the corresponding grade standard feature, where i ranges from 1 to 32. The calculation results are as follows: the difference from the excellent grade standard is 15.6, compared to the good grade is 8.3, compared to the medium grade is 12.7, and compared to the poor grade is 25.4. By comparison, the good grade corresponding to the smallest difference value of 8.3 was selected as the assessment result for the remediation effect level of the northeastern region. Meanwhile, the calculation of the median feature vector of the 12 monitoring points in the southwest shows that the smallest difference value from the medium grade standard is 9.2; therefore, the grade for this region is determined to be medium.

[0123] In this embodiment of the application, the method achieves objective determination of the repair effect level through a matching mechanism of quantitative feature differences, avoids the bias of subjective judgment, and the evaluation results are accurate and reliable, providing a scientific basis for repair project management.

[0124] To improve the scientific rigor and comprehensiveness of soil remediation effectiveness evaluation, in some embodiments, step 102: determining the soil remediation efficiency index based on the available heavy metal content, the microbial index data, and the plant index data includes:

[0125] Step 501: Assign a first weighting factor to the available heavy metal content, a second weighting factor to the microbial index data, and a third weighting factor to the plant index data.

[0126] In step 501, the first weighting factor refers to the importance coefficient of the available heavy metal content in the comprehensive evaluation. The second weighting factor refers to the importance coefficient of the microbial index data. The third weighting factor refers to the importance coefficient of the plant indicator data.

[0127] In this embodiment, an expert team first assesses and scores the importance of three categories of indicators: heavy metals, microorganisms, and plants. Based on data analysis of historical remediation cases, a reasonable weighting ratio for each indicator is determined. The sum of the weighting factors is a fixed value to ensure the consistency of the evaluation system.

[0128] Step 502: Multiply the available heavy metal content, the microbial index data, and the plant index data by the corresponding first weighting factor, second weighting factor, and third weighting factor, respectively, to obtain the weighted available heavy metal content, weighted microbial index data, and weighted plant index data.

[0129] In step 502, the weighted heavy metal bioavailability content refers to the result of multiplying the original content data by the weights. The weighted microbial index data refers to the result of multiplying the original content data by the weights. The weighted plant index data refers to the result of multiplying the original content data by the weights.

[0130] In this embodiment, the collected raw data on the available heavy metal content, microbial index, and plant indicators are multiplied by their corresponding weighting factors. This weighting process preserves the true information of the original data while reflecting the relative importance of different indicators in the evaluation system.

[0131] Step 503: Add the weighted heavy metal available content, the weighted microbial index data, and the weighted plant index data to obtain the remediation efficacy index.

[0132] In this embodiment, the weighted values ​​of the three categories of indicators are summed to obtain the final remediation effectiveness index. This index comprehensively considers the degree of reduction in soil pollution, the restoration of ecological functions, and the improvement in plant growth, providing basic data for subsequent analysis.

[0133] Here is a specific example:

[0134] In the evaluation of the remediation effect in heavy metal pollution zone A, the weight allocation of each indicator was first determined, with the weight of the available heavy metal content (a) set at 0.5, the weight of the microbial index data (b) set at 0.3, and the weight of the plant indicator data (c) set at 0.2. For monitoring point 1, the available cadmium content (X) was measured to be 0.82 mg / kg, the microbial Shannon index (Y) at 2.15, and the SPAD value of rice leaves (Z) at 38.2. According to the remediation efficacy index calculation formula REI = aX + bY + cZ, where REI represents the remediation efficacy index, a is the heavy metal weight, X is the available cadmium content, b is the microbial weight, Y is the microbial index, c is the plant weight, and Z is the plant indicator, the remediation efficacy index for point 1 was calculated to be 0.5 × 0.82 + 0.3 × 2.15 + 0.2 × 38.2 = 0.41 + 0.645 + 7.64 = 8.695. Similarly, the index values ​​for the other 19 monitoring points were calculated. For example, at point 2, X was measured to be 0.78 mg / kg, Y to be 2.08, and Z to be 36.5. The calculated REI was 0.5 × 0.78 + 0.3 × 2.08 + 0.2 × 36.5 = 0.39 + 0.624 + 7.3 = 8.314. The repair efficiency indices from these 20 monitoring points constituted a dataset, which was used for subsequent fusion analysis with temperature rise curve data and current density distribution data.

[0135] In this embodiment, the method achieves a comprehensive evaluation of multiple indicators through reasonable weight allocation and weighted calculation. It considers both the removal effect of pollutants and the restoration status of the ecosystem, making the evaluation of restoration effects more comprehensive and objective. The entire calculation method is simple and effective, and the results are intuitive and comparable, providing a reliable quantitative basis for restoration project management.

[0136] To achieve dynamic monitoring of the remediation process of heavy metal contaminated soil, in some embodiments, step 103: generating active oxygen by applying microwave energy to catalyze the speciation of heavy metals in the soil, and obtaining temperature rise curve data during the catalytic transformation process, includes:

[0137] Step 601: Apply microwave energy to the soil to excite the nanocatalyst and generate active oxygen.

[0138] In step 601, the nanocatalyst refers to nanomaterial particles with catalytic function added to the soil.

[0139] In this embodiment, a microwave transmitting device emits microwaves with set parameters into the contaminated soil area. The nanocatalyst added to the soil absorbs the microwave energy, causing its surface electrons to undergo excited transitions, generating reactive oxygen species. This process provides a reaction medium for subsequent heavy metal conversion.

[0140] Step 602: The active oxygen triggers the redox reaction of heavy metals, catalyzes the transformation of heavy metal forms, and the temperature of the soil at each moment during the redox reaction is monitored simultaneously.

[0141] In step 602, the redox reaction refers to the electron transfer reaction between heavy metals and reactive oxygen species. Speciation refers to the chemical transformation of heavy metals from an active state to a stable state. Temperature monitoring refers to recording soil temperature changes during the reaction process using sensors.

[0142] In this embodiment, reactive oxygen species undergo an electron exchange reaction with heavy metals in the soil, causing the heavy metals to transform from a form easily absorbed by plants into a stable form. Simultaneously, temperature sensors placed in the soil collect temperature data at fixed time intervals, recording the exothermic reaction process.

[0143] Step 603: Generate temperature rise curve data based on the temperature of the soil at various times during the redox reaction.

[0144] In this embodiment, the collected temperature data at various time points are connected sequentially to form a complete temperature change curve. This curve can visually display the initiation, vigorous, and decay stages of the reaction, providing a basis for evaluating the catalytic effect.

[0145] Here is a specific example:

[0146] During the remediation of heavy metal contamination zone A, an 800-watt microwave device was used to irradiate the soil. Nano-ferric oxide catalysts pre-added to the soil generated hydroxyl radicals under microwave irradiation. At monitoring point 1, a temperature sensor recorded soil temperature data every 5 minutes during the reaction. The temperature was 25.3 degrees Celsius at 0 minutes, rising to 28.6 degrees Celsius at 5 minutes, 32.1 degrees Celsius at 10 minutes, 35.4 degrees Celsius at 15 minutes, 38.2 degrees Celsius at 20 minutes, 40.5 degrees Celsius at 25 minutes, and 42.7 degrees Celsius at 30 minutes. Connecting these temperature data points chronologically formed a complete temperature rise curve. Analysis of this curve revealed that the temperature rose rapidly in the first 15 minutes, averaging 0.67 degrees Celsius per minute, indicating the most intense redox reaction during this stage. After 15 minutes, the temperature rise rate slowed to 0.27 degrees Celsius per minute, showing that the reaction gradually stabilized.

[0147] In this embodiment, the method combines microwave catalysis with temperature monitoring to achieve real-time dynamic tracking of the remediation reaction. This not only promotes heavy metal conversion but also visually reflects the reaction progress through temperature rise curves, providing crucial process data support for evaluating remediation effectiveness. The entire monitoring scheme is simple to operate, provides reliable data, and enhances the level of refined management in remediation projects.

[0148] To accurately reflect the spatial distribution characteristics of heavy metal ion migration activity, in some embodiments, step 104: generating current density distribution data based on the heavy metal ion migration data includes:

[0149] Step 701: Extract the migration current value and corresponding spatial location information from the heavy metal ion migration data.

[0150] In step 701, the migration current value refers to the current intensity data generated by the movement of heavy metal ions under the action of an electric field. Spatial location information refers to the specific coordinate location data of the monitoring point in the region.

[0151] In this embodiment, raw current readings are obtained from the electrode monitoring device, and the latitude and longitude coordinates or relative position numbers of each monitoring point are recorded. The current values ​​are paired and stored with the corresponding location information to establish a basic dataset for subsequent spatial analysis.

[0152] Step 702: Correlate the migration current value corresponding to each spatial location point in the spatial location information with the preset cross-sectional area parameter to obtain the current density value of each spatial location point.

[0153] In step 702, the preset cross-sectional area parameter refers to the effective area of ​​contact between the electrode and the soil. The current density value refers to the current intensity passing through a unit area, reflecting the activity level of heavy metal migration.

[0154] In this embodiment, the standard area of ​​the electrode in contact with the soil is determined according to its design specifications. The current density value at each monitoring point is obtained by dividing the measured current value by this standard area. This calculation eliminates the influence of electrode size differences, making the data comparable.

[0155] Step 703: Based on the coordinate relationship of the spatial location information, perform spatial interpolation calculation on the current density values ​​of all spatial location points using the inverse distance weighting method to generate current density distribution data.

[0156] In step 703, the coordinate relationship refers to the topological relationship established using the latitude and longitude coordinates or relative position coordinates of each sampling point in a preset soil monitoring grid. This coordinate relationship originates from GPS positioning data recorded during heavy metal ion migration data collection or a pre-deployed location mapping table corresponding to the monitoring point numbers, and is used to determine the spatial distribution structure of each sampling point on a two-dimensional plane. The inverse distance weighting method is an interpolation algorithm that considers spatial positional relationships; points that are closer together have a greater influence. Spatial interpolation calculation refers to the process of extrapolating values ​​for unknown areas based on known point data.

[0157] In this embodiment, a planar coordinate system is established based on the coordinate positions of the monitoring points. Using the current density values ​​at each point as a basis, and following the calculation rules of the inverse distance weighting method, the current density values ​​at various locations throughout the entire area are calculated. These calculation results are then plotted as a color-gradient distribution map to visually demonstrate the spatial characteristics of heavy metal migration activities.

[0158] Here is a specific example:

[0159] During the heavy metal pollution remediation monitoring in Area A, the specific implementation for generating current density distribution data was as follows: At each of the 20 initially set monitoring points, the same voltage V was applied to the electrode device, and the migration current data was measured. The current I at monitoring point 1 was 1.2 mA, at monitoring point 2 it was 1.0 mA, and so on, completing the current measurement for all monitoring points. All electrodes used uniform specifications, with a contact area S of 0.5 square centimeters. Based on the current density calculation formula J = I / S, where J represents current density, I represents migration current, and S represents electrode area, the current density at monitoring point 1 was calculated as J1 = 1.2 / 0.5 = 2.4 mA / cm², and at monitoring point 2 it was J2 = 1.0 / 0.5 = 2.0 mA / cm². The spatial coordinates of the 20 monitoring points were recorded using GPS positioning, establishing a Cartesian coordinate system. The inverse distance weighted interpolation method was used to calculate the current density value of the unmonitored area, with the interpolation formula Z = Σ(zi / di)2 ) / Σ(1 / di 2 ), where Z represents the current density at the point to be determined, zi represents the current density at the i-th known monitoring point, and di represents the distance between the point to be determined and the i-th monitoring point. This calculation generates a current density distribution map covering the entire area. The results show that the density values ​​in the central region are generally above 2.0 mA / cm², reaching a maximum of 2.8 mA / cm², while the edge regions are mostly between 1.5 and 2.0 mA / cm².

[0160] In this embodiment, the method uses current density calculation and spatial interpolation to achieve a visual representation of heavy metal migration activities. This reflects both the overall distribution pattern and identifies local feature differences, providing an important basis for analyzing the spatial heterogeneity of remediation effects. The entire processing procedure is standardized and reliable, and the results are intuitive and clear, improving the precision of remediation monitoring.

[0161] Figure 2 A schematic diagram of the structure of an evaluation system for the remediation effect of heavy metal contaminated soil provided in this application embodiment is shown below. Figure 2 As shown, the system includes:

[0162] The acquisition module 21 is used to acquire the available content of heavy metals, microbial index data, plant index data, and heavy metal ion migration data in the soil monitoring area.

[0163] The determination module 22 is used to determine the soil remediation efficiency index based on the available content of heavy metals, the microbial index data, and the plant index data.

[0164] The catalytic module 23 is used to generate active oxygen by applying microwave energy to catalyze the transformation of heavy metals in the soil and obtain temperature rise curve data during the catalytic transformation process.

[0165] The generation module 24 is used to generate current density distribution data based on the heavy metal ion migration data.

[0166] The fusion module 25 is used to fuse the remediation efficiency index, the temperature rise curve data and the current density distribution data through a multi-source data fusion algorithm, input the fusion result into a convolutional neural network, and output the soil remediation effect level assessment result and spatial difference analysis result.

[0167] Figure 2 The aforementioned evaluation system for the remediation effect of heavy metal contaminated soil can be executed. Figure 1The implementation principle and technical effects of the method for evaluating the remediation effect of heavy metal contaminated soil described in the above embodiment will not be repeated here. The specific operation methods of each module and unit in the evaluation system for the remediation effect of heavy metal contaminated soil in the above embodiment have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0168] In one possible design, Figure 2 The evaluation system for the remediation effect of heavy metal contaminated soil shown in the embodiment can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0169] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0170] The processing component 32 is used to perform the above. Figure 1 The embodiment describes a method for evaluating the remediation effect of heavy metal contaminated soil.

[0171] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0172] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0173] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0174] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0175] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0176] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0177] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 An evaluation method for the remediation effect of heavy metal contaminated soil according to the embodiment shown.

[0178] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0179] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0180] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0181] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for evaluating the remediation effect of heavy metal contaminated soil, characterized in that, include: Acquire data on the available content of heavy metals, microbial index data, plant index data, and heavy metal ion migration data in the soil monitoring area; Based on the available content of heavy metals, the microbial index data, and the plant index data, the soil remediation efficiency index is determined. By applying microwave energy to generate active oxygen, heavy metals in the soil are catalyzed to undergo speciation transformation, and temperature rise curve data are obtained during the catalytic transformation process. Based on the heavy metal ion migration data, current density distribution data is generated; The remediation efficiency index, the temperature rise curve data, and the current density distribution data are fused using a multi-source data fusion algorithm. The fusion result is then input into a convolutional neural network to output the soil remediation effect level assessment result and spatial difference analysis result.

2. The method according to claim 1, characterized in that, The process involves fusing the remediation efficiency index, the temperature rise curve data, and the current density distribution data using a multi-source data fusion algorithm. The fusion result is then input into a convolutional neural network, outputting soil remediation effectiveness level assessment results and spatial difference analysis results, including: Create a multi-source dataset, which includes the repair efficiency index, the temperature rise curve data, and the current density distribution data; The multi-source data set is fused using a multi-source data fusion algorithm to generate a fused feature vector. The fused feature vector is input into the processing layer of the convolutional neural network. Through the sequential operation of multiple modules in the processing layer, the repair effect level evaluation result and spatial difference analysis result are output.

3. The method according to claim 2, characterized in that, The process involves inputting the fused feature vector into the processing layer of a convolutional neural network. Through the sequential operation of multiple modules within the processing layer, the system outputs a repair effect level evaluation result and a spatial difference analysis result, including: The fused feature vector is transformed by the transformation module in the processing layer to generate intermediate features; The intermediate features are matched with preset level labels by the matching module in the processing layer, and a repair effect level evaluation result is generated based on the matching result. The spatial analysis module in the processing layer reconstructs a spatial distribution map that matches the soil monitoring area. Based on the distribution characteristics of the spatial distribution map, spatial difference analysis results are generated.

4. The method according to claim 3, characterized in that, The process involves using a matching module in the processing layer to match the intermediate features with preset level labels, and generating a repair effect level evaluation result based on the matching result, including: The intermediate features are matched with the level label features in the preset level label library; Based on the matching results, calculate the quantitative difference value between the intermediate features and the label features at each level; Select the grade label corresponding to the smallest quantitative difference value, and use the grade label as the evaluation result of the repair effect grade.

5. The method according to claim 1, characterized in that, The determination of the soil remediation efficiency index based on the available heavy metal content, the microbial index data, and the plant index data includes: A first weighting factor is assigned to the available content of heavy metals, a second weighting factor is assigned to the microbial index data, and a third weighting factor is assigned to the plant index data. The available heavy metal content, the microbial index data, and the plant index data are multiplied by the corresponding first weighting factor, second weighting factor, and third weighting factor, respectively, to obtain the weighted available heavy metal content, the weighted microbial index data, and the weighted plant index data. The remediation efficacy index is obtained by adding the weighted heavy metal bioavailability content, the weighted microbial index data, and the weighted plant index data.

6. The method according to claim 1, characterized in that, The process of generating reactive oxygen species by applying microwave energy to catalyze the transformation of heavy metals in soil and obtaining temperature rise curve data during the catalytic transformation includes: Microwave energy is applied to the soil, and the microwave energy is used to excite the nanocatalyst to generate active oxygen; The active oxygen triggers the redox reaction of heavy metals, catalyzes the transformation of heavy metal forms, and the temperature of the soil at each moment during the redox reaction is monitored simultaneously. Based on the temperature of the soil at various points during the redox reaction, temperature rise curve data are generated.

7. The method according to claim 1, characterized in that, The generation of current density distribution data based on the heavy metal ion migration data includes: Extract migration current values ​​and corresponding spatial location information from the heavy metal ion migration data; The migration current value corresponding to each spatial location point in the spatial location information is correlated with the preset cross-sectional area parameter to obtain the current density value of each spatial location point. Based on the coordinate relationship of the spatial location information, the current density values ​​of all spatial location points are spatially interpolated using the inverse distance weighting method to generate current density distribution data.

8. An evaluation system for the remediation effect of heavy metal contaminated soil, characterized in that, include: The acquisition module is used to acquire the available content of heavy metals, microbial index data, plant index data, and heavy metal ion migration data in the soil monitoring area. The determination module is used to determine the soil remediation efficiency index based on the available content of heavy metals, the microbial index data, and the plant index data; The catalytic module is used to generate active oxygen by applying microwave energy to catalyze the transformation of heavy metals in the soil and obtain temperature rise curve data during the catalytic transformation process. The generation module is used to generate current density distribution data based on the heavy metal ion migration data; The fusion module is used to fuse the remediation efficiency index, the temperature rise curve data, and the current density distribution data through a multi-source data fusion algorithm, input the fusion result into a convolutional neural network, and output the soil remediation effect level assessment result and spatial difference analysis result.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the evaluation method for the remediation effect of heavy metal contaminated soil as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements a method for evaluating the remediation effect of heavy metal contaminated soil as described in any one of claims 1 to 7.

Images