System and method for analyzing soil pollution remediation range

Abstract

The invention discloses an analysis system and method for a soil pollution remediation range, and relates to the technical field of soil pollution remediation and information, the system comprises a biosensor network module, a data processing and analysis module, a feature matching module, a pollution permeation prediction module and a remediation range optimization module, according to the soil pollution remediation range analysis method, the electrical signal change generated by the fact that microorganisms in soil participate in heavy metal pollutant metabolism is monitored in real time through a microbial metabolism electrical signal sensor network, the pollution type and degree are determined through data processing and analysis and feature matching, and the soil pollution remediation range is analyzed by combining the soil layer permeation level and historical pollution migration data. A permeation weight matrix is generated to determine the remediation priority, and for lead, cadmium and arsenic heavy metal pollution, a remediation agent containing astragalus membranaceus and liquorice traditional Chinese medicine component extracts is combined for cooperative treatment, so that the remediation range of the heavy metal pollution in the soil can be accurately determined, and the remediation efficiency of the soil pollution is improved.

Description

Technical Field

[0001] The present invention relates to the fields of soil pollution remediation and information technology, and specifically to an analysis system and method for the scope of soil pollution remediation. Background Art

[0002] Soil pollution poses a serious threat to human health and the ecosystem. With the rapid development of industrialization and urbanization, a large amount of heavy metals, organic pollutants, etc. enter the soil through wastewater discharge, solid waste landfill, pesticide and fertilizer use, etc., resulting in increasingly serious soil pollution. Accurately analyzing and determining the scope of soil pollution remediation is the primary prerequisite for carrying out efficient and precise soil pollution remediation work. Only by clarifying the pollution scope can the remediation plan be reasonably planned and remediation resources be allocated to avoid over-remediation or under-remediation.

[0003] Currently, the existing soil pollution remediation scope analysis technologies mainly rely on limited soil sampling and laboratory analysis. This method has the following limitations:

[0004] It is not only time-consuming, laborious and costly, but also difficult to comprehensively and accurately reflect the true situation and spatial distribution characteristics of soil pollution due to the limitations of sampling points;

[0005] Potential pollution areas are easily missed, resulting in inaccurate definition of the remediation scope. There are no effective real-time monitoring and dynamic analysis means, and it is impossible to timely capture the dynamic information generated by the change of microbial metabolism with heavy metal pollution, making it difficult to accurately delimit the remediation boundary based on this information;

[0006] In addition, the existing technologies also ignore the influence of soil stratification structure on pollutant migration, which is likely to cause "remediation blind spots". Moreover, when the existing remediation means are used for heavy metal pollution, natural substances with unique remediation functions are not fully utilized, such as traditional Chinese medicines rich in special components, such as Astragalus membranaceus, Glycyrrhiza uralensis, Taraxacum mongolicum, Isatis indigotica, etc. Their extracts have potential advantages in heavy metal enrichment and passivation.

[0007] In summary, the existing soil pollution remediation scope analysis technologies have problems such as sampling limitations, lack of dynamic monitoring and traditional Chinese medicine remediation substances, resulting in inaccurate and incomplete determination of the remediation scope, thereby affecting the effect and efficiency of soil pollution remediation. Therefore, there is an urgent need for a new type of soil pollution remediation scope analysis system and method that can comprehensively consider soil microbial metabolism information and achieve real-time dynamic monitoring to meet the actual needs of current soil pollution control work. Summary of the Invention

[0008] The objective of the present invention is to make up for the deficiencies of the prior art and provide an analysis system and method for the scope of soil pollution remediation. It can, through a sensor network, monitor in real time the changes in the electrical signals generated by microbial metabolism in the soil, extract key feature information, and match it with the historical electrical signal feature database, so as to accurately judge the type and degree of pollution, and optimize the remediation boundary in combination with environmental factors. By comprehensively considering the infiltration levels of different soil layers and historical pollution migration data, an accurate infiltration weight matrix is generated to achieve the spatial priority determination of the remediation scope, which is used to further optimize and improve the remediation boundary, ensuring the economy and feasibility of the remediation plan.

[0009] To solve the above technical problems, the present invention provides the following technical solutions: On the one hand, an analysis system for the scope of soil pollution remediation, the system consists of: a biosensor network module, a data processing and analysis module, a feature matching module, a pollution infiltration prediction module, and a remediation scope optimization module;

[0010] The biosensor network module distributes multiple microbial metabolism electrical signal sensors in the soil, monitors in real time the changes in the intensity of the electrical signals generated by microorganisms in the soil due to participating in pollutant metabolism, forms a sensor network, and transmits the collected electrical signals to the data processing and analysis module;

[0011] The data processing and analysis module is used to receive the electrical signal data transmitted by the biosensor network module, perform filtering, denoising, and feature extraction, and then transmit it to the feature matching module and the pollution infiltration prediction module, and integrate the information fed back by each module for comprehensive analysis and processing;

[0012] The feature matching module is used to receive the real-time electrical signal data transmitted by the data processing and analysis module, extract the real-time feature information of the electrical signals from it, establish a historical electrical signal feature database, match the feature information of the real-time electrical signals with the feature information of the historical electrical signal feature database to determine the type and degree of pollution, and feed back the matching result to the data processing and analysis module;

[0013] The pollution infiltration prediction module, according to the pollution type and degree information provided by the data processing and analysis module, combines the soil layer infiltration level and historical pollution migration data, generates an infiltration weight matrix through transfer learning to achieve the priority determination of the remediation scope, and sends the determination result to the remediation scope optimization module;

[0014] The remediation scope optimization module, according to the priority determination result sent by the pollution infiltration prediction module, combines the pollution type and degree determined by the feature matching module, optimizes and improves the remediation boundary, finally determines the scope of soil pollution remediation, and outputs the result.

[0015] Furthermore, the sensor network of the biosensing network module consists of multiple microbial metabolic electro-signal sensors distributed in the soil. These sensors can accurately monitor the electro-signals generated by microbial metabolism in the soil. When microorganisms participate in pollutant metabolism, the intensity of the electro-signals they generate will change. The sensors capture this change in real-time and map the pollution concentration gradient in real-time through the electro-signal intensity. The sensors are interconnected with each other. After the collected electro-signals are preliminarily converted from analog to digital, they are sent to the aggregation node in a wireless transmission manner, and then the aggregation node transmits the signals to the data processing and analysis module through the wireless network.

[0016] Even further, the working principle of the data processing and analysis module is as follows:

[0017] Data reception: Establish a connection with the biosensing network module through the data interface, and receive the original electro-signal data transmitted by the biosensing network module in real-time. The received data is preliminarily classified and stored according to the time sequence and sensor number.

[0018] Filtering process: Perform a filtering operation on the original electro-signal data to remove high-frequency and low-frequency noise signals generated by environmental interference and sensor self-noise factors, and retain the effective frequency signals related to the microbial metabolic electro-signals.

[0019] Denoising process: Further denoise the filtered data to obtain cleaner electro-signal data.

[0020] Feature extraction: Extract features from the denoised electro-signal data, map the high-dimensional electro-signal data to a low-dimensional space, and extract the principal components that can represent the main features of the electro-signals. The principal components contain information about the pollution type and degree.

[0021] Data transmission: Transmit the electro-signal data after filtering, denoising, and feature extraction to the feature matching module and the pollution penetration prediction module respectively, providing data support for subsequent pollution type judgment and repair scope priority determination.

[0022] Information integration and analysis: Receive the pollution type and degree information feedback by the feature matching module and the priority determination result feedback by the pollution penetration prediction module, and comprehensively analyze this information with the data processed by itself to provide a comprehensive and accurate data basis for the repair scope optimization module.

[0023] Even further, when the data processing and analysis module performs feature extraction of electro-signals, the denoised electro-signal data matrix is denoted as , is matrix, where represents the number of groups of electro-signal data samples collected, Represents different attribute dimensions corresponding to the electrical signal data samples. For perform standardization processing to make the mean of the features in each dimension 0 and the variance 1. The standardized matrix is denoted as Calculate the covariance matrix of the standardized data matrix The covariance matrix is a square matrix, and its element represents the covariance between the th feature dimension and the th feature dimension, and and are respectively the means of the th and the th feature dimensions. and are respectively the values of the th sample on the th and the th feature dimensions. Perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues and the corresponding eigenvectors where the eigenvector is a -dimensional column vector, and the eigenvalue represents the variance magnitude of the th principal component. Arrange the eigenvalues in descending order and select the eigenvectors corresponding to the first largest eigenvalues to form the eigenvector matrix , is a matrix, where is the number of retained principal components and . Multiply the standardized data matrix by the eigenvector matrix to obtain the principal component data matrix in the low-dimensional space , is a matrix and . Among them, each column in the matrix is a principal component, and the principal component contains information related to the pollution type and degree, thus completing the mapping from high-dimensional electrical signal data to the low-dimensional space and realizing feature extraction.

[0024] Furthermore, the feature matching module receives the electrical signal data matrix transmitted by the data processing and analysis module after filtering, denoising, and feature extraction., on the basis of the extracted principal components, extract local feature points from the principal component data, that is, for each sample data point in , by detecting stable feature points, obtain the feature vector of each feature point , the feature vector represents the characteristics of the electrical signal data in the local area, extract the feature vector from the historical electrical signal feature database and the corresponding pollution type label and the pollution degree level , match the currently extracted feature vector with all the feature vectors in the historical electrical signal feature database, calculate and each feature vector in the database distance as the similarity metric standard, that is , where represents different attribute dimensions of the corresponding electrical signal data sample, and are the current feature vector and each feature vector in the database of the -th dimension value, select the matching item with the smallest distance , according to the pollution type label and pollution degree level corresponding to the matching item, that is the pollution type and degree corresponding to the current electrical signal data, and feedback the matching result to the data processing and analysis module.

[0025] Further, the pollution penetration prediction module divides the soil layer into three penetration levels: surface layer, transition layer, and deep layer.

[0026] Further, the pollution penetration prediction module generates a penetration weight matrix by training a data set containing historical pollution migration data , assign weight coefficients to each layer of pollution area, where represents the weight coefficient of the -th pollution type at the -th soil layer penetration level, represents the pollution type label, respectively correspond to the surface layer, transition layer, and deep layer. For the detected pollution area, determine the corresponding penetration level according to the soil layer where it is located, and then obtain the corresponding weight coefficient from the penetration weight matrix , that is, when the pollution area is in the surface layer, assign it the weight coefficient, when it is in the transition layer and deep layer, assign and The weight coefficient, combined with the pollution degree value, is used to calculate the comprehensive risk value of each polluted area. , where represents the quantified value of the pollution degree of the th type of pollution, represents the number of pollution types. According to the calculated comprehensive risk value , all polluted areas are sorted. The areas with higher risk values have higher repair priorities. Finally, the sorting results are sent to the repair scope optimization module to provide a basis for accurately determining the repair scope.

[0027] On the other hand, a method for analyzing the soil pollution repair scope, the specific steps of which are as follows:

[0028] S100. In the soil, a biosensing network is constructed through a microbial metabolic electro-signal sensor to continuously monitor the change in the intensity of the electro-signal generated by microorganisms participating in the metabolism of heavy metal pollutants.

[0029] S200. Receive the electro-signal data transmitted by the biosensing network and perform filtering, denoising, and feature extraction.

[0030] S300. Match the extracted electro-signal feature information with the historical electro-signal feature database to determine the matching items, thereby judging the pollution type and degree of the heavy metals.

[0031] S400. Based on the pollution type and degree information obtained from data processing and analysis, combined with the permeability level of the soil layer, sort the heavy metal polluted areas according to the risk value to determine the priority of the repair scope.

[0032] S500. Optimize the repair boundary according to the priority sorting results, match the plant-derived repair agent database, generate a repair plan containing traditional Chinese medicine component extracts, and conduct collaborative treatment on the heavy metal polluted areas.

[0033] Furthermore, in S500, according to the heavy metal pollution type and range information output by S400, the plant-derived repair agent database is matched to generate a repair plan containing plant extracts. The plant extracts include traditional Chinese medicine components with heavy metal enrichment and passivation functions, including one or more of astragalus membranaceus, glycyrrhiza uralensis, taraxacum mongolicum, and isatis indigotica. The heavy metals include one or more of lead, cadmium, arsenic, and mercury.

[0034] The repair plan is as follows: For lead and cadmium polluted areas, match isatis indigotica extract and glycyrrhiza uralensis extract, and use their polysaccharide components to adsorb heavy metal ions; for arsenic polluted areas, match astragalus membranaceus extract and taraxacum mongolicum extract, and promote the redox reaction of arsenic through organic acid components to reduce toxicity.

[0035] Compared with the prior art, the analysis system and method for the scope of soil pollution remediation have the following beneficial effects:

[0036] First, the soil pollution remediation scope analysis system of the present invention can, by constructing a microbial metabolism electrical signal sensor network, monitor in real time and accurately the changes in electrical signals generated by microbial metabolism in the soil. These electrical signals are closely related to the metabolism of pollutants in the soil and can directly reflect the pollution status of the soil, thereby more comprehensively and accurately grasping the distribution of soil pollution. During the data processing and analysis process, the collected electrical signals are deeply mined and analyzed to accurately extract the characteristic information related to the pollution type and degree. Through the feature matching module, it is matched with the historical electrical signal feature database, further improving the accuracy of pollution type and degree judgment, achieving precise definition of the scope of soil pollution remediation, enabling the remediation plan to be formulated more pertinently, and effectively improving the effect of soil pollution remediation.

[0037] Second, the pollution penetration prediction module of the present invention, by combining the soil layer penetration level and historical pollution migration data, generates a penetration weight matrix to realize the determination of the spatial priority of the remediation scope, can more comprehensively evaluate the soil pollution status, thereby predicting the migration path and diffusion range of pollutants in the soil and avoiding the emergence of remediation blind spots.

[0038] Other advantages, objectives, and features of the present invention will, to some extent, be described in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on the study of the following text, or can be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is an operation schematic diagram of an analysis system for the scope of soil pollution remediation;

[0041] Figure 2 It is a step flow chart of an analysis method for the scope of soil pollution remediation. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention objective, the following will, in combination with the drawings and preferred embodiments, detail the specific embodiments, structures, features, and their effects of the present invention as follows.

[0043] Example 1

[0044] As Figure 1 described, this embodiment focuses on an analysis system for the scope of soil pollution remediation, elaborating in detail its working principle and operation process. The system includes a biosensing network module, a data processing and analysis module, a feature matching module, a pollution penetration prediction module, and a remediation scope optimization module. Through the collaborative work of each module, the system uses microbial metabolic electro-signal sensors to monitor soil pollution in real time. Combining data processing, feature matching, and penetration prediction technologies, it accurately determines the scope of soil pollution remediation, providing strong support for soil pollution control.

[0045] In the area affected by potential pollution, the work of analyzing the scope of soil pollution remediation is carried out, and the biosensing network module is deployed. This module consists of multiple microbial metabolic electro-signal sensors, which are distributed in the soil of the polluted area to form a biosensing layer, ensuring comprehensive and uniform monitoring of the soil. The microbial metabolic electro-signal sensors can accurately monitor the electro-signals generated by microbial metabolism in the soil. In the soil environment, microorganisms carry out metabolic activities on various pollutants. When microorganisms participate in pollutant metabolism, their metabolic process generates electro-signals, and the intensity of the electro-signals changes with the concentration of pollutants and metabolic activities. For example, in areas with higher pollutant concentrations, microbial metabolic activities are more active, and the intensity of the generated electro-signals will increase accordingly. The sensors capture these changes in electro-signal intensity in real time and convert them into digital signals. Each sensor is interconnected with adjacent sensors to form a self-organizing sensor network. After the sensors collect the electro-signals, they first perform preliminary analog-to-digital conversion to convert the analog signals into digital signals for subsequent transmission and processing. The converted signals are sent to the aggregation node in a wireless transmission manner, ensuring the reliability of signal transmission, reducing signal interference and loss. After the aggregation node collects the signals from each sensor, it uniformly transmits the signals to the data processing and analysis module through the wireless network. During the transmission process, the transmitted data is verified. If data transmission errors are found, the aggregation node automatically requests the sensor to resend the data.

[0046] After the data processing and analysis module receives the original electrical signal data transmitted by the biosensor network module, it establishes a stable connection with the biosensor network module through a data interface to receive data in real time. The received data is initially classified and stored according to time sequence and sensor number for convenient subsequent data processing and query. For example, the data collected by different sensors at the same time point is stored in the same batch and arranged according to the sensor number to form an ordered data storage structure. Since the original electrical signal data contains high-frequency and low-frequency noise signals generated by environmental interference and sensor self-noise factors, these noises will affect the accurate analysis of microbial metabolic electrical signals in the future. Therefore, a filtering operation is performed on the original electrical signal data to remove high-frequency and low-frequency noise signals and only retain the effective frequency signals related to microbial metabolic electrical signals. Further denoising operations are performed on the filtered data to obtain cleaner electrical signal data; feature extraction is performed on the denoised electrical signal data, and the denoised electrical signal data matrix is denoted as , is matrix of, where represents the number of groups of electrical signal data samples collected, represents different attribute dimensions of the corresponding electrical signal data samples. Since the electrical signal data has a high dimension, direct analysis will increase the computational complexity and there is information redundancy. Therefore, it is mapped to a low-dimensional space to extract the principal components that can represent the main features of the electrical signal. First, is standardized so that the mean of the features in each dimension is 0 and the variance is 1. The standardized matrix is denoted as . The purpose of standardization is to eliminate the dimensional differences between the features of different dimensions and make each feature have the same importance in subsequent analysis. For example, the electrical signal data may contain features of different physical quantities such as voltage and current. Through standardization, these features are unified to the same scale. Calculate the covariance matrix of the standardized data matrix . The covariance matrix is square matrix of, and its element represents the covariance between the th feature dimension and the th feature dimension. The calculation formula is . Here, and are the means of the th and th feature dimensions respectively, and are the th sample in the th and The values on each feature dimension. The covariance matrix reflects the correlation between different feature dimensions. By calculating the covariance matrix, the internal relationship between each feature of the electrical signal data can be understood. For the covariance matrix perform eigenvalue decomposition to obtain eigenvalues and the corresponding eigenvectors , where the eigenvector is a -dimensional column vector, and the eigenvalue represents the variance size of the th principal component. The larger the variance, the more information the principal component contains and the stronger its ability to explain the data. Arrange the eigenvalues in descending order, select the eigenvectors corresponding to the top p largest eigenvalues to form the eigenvector matrix is a matrix, where is the number of retained principal components and . Multiply the standardized data matrix by the eigenvector matrix to obtain the principal component data matrix in the low-dimensional space . is a matrix and . Each column in the matrix is a principal component, and these principal components contain information related to the pollution type and degree, thus completing the mapping from high-dimensional electrical signal data to a low-dimensional space and realizing feature extraction. For example, after feature extraction, the electrical signal data originally containing dimensional features is compressed into principal components. These principal components retain the most important information in the data, while reducing the data dimension and improving the efficiency of subsequent analysis. Transmit the electrical signal data matrix after filtering, denoising, and feature extraction to the feature matching module and the pollution penetration prediction module respectively to provide data support for subsequent pollution type judgment and repair scope priority determination. During the transmission process, ensure the accuracy of the data. Receive the pollution type and degree information feedback from the feature matching module and the priority determination result feedback from the pollution penetration prediction module, and perform comprehensive analysis on this information and the data processed by itself. For example, compare and verify the pollution type and degree information determined by the feature matching module with the principal component information extracted by the data processing and analysis module to check the consistency of the results; at the same time, combine the priority determination result of the pollution penetration prediction module to analyze the potential risks and repair priorities of different pollution areas, providing a comprehensive and accurate data basis for the repair scope optimization module.

[0047] The feature matching module receives the electro-signal data matrix that has been filtered, denoised, and feature-extracted and transmitted by the data processing and analysis module. , based on the extracted principal components, further extract local feature points from the principal component data to obtain more detailed electro-signal feature information. For each sample data point in , describe the features of the electro-signal in the local area by detecting stable feature points, and calculate the feature vector of each feature point , this feature vector represents the features of the electro-signal data in the local area. Extract the feature vector and the corresponding pollution type label and the pollution degree level from the historical electro-signal feature database. The historical electro-signal feature database contains a large amount of electro-signal feature data under different pollution types and pollution degrees. Match the currently extracted feature vector with all the feature vectors in the historical electro-signal feature database, and calculate the distance between it and each feature vector in the database as the similarity metric standard. The calculation method is , where represents different attribute dimensions of the corresponding electro-signal data sample, and are the values of the -th dimension of the current feature vector and each feature vector in the database respectively. By calculating the distance , the similarity between the current electro-signal feature and each feature in the historical database can be measured. The smaller the distance, the higher the similarity. Select the matching item with the smallest distance . According to the pollution type label and the pollution degree level corresponding to this matching item, it is the pollution type and degree corresponding to the current electro-signal data. For example, if the pollution type label corresponding to the matching item with the smallest distance from the current feature vector is "heavy metal pollution" and the pollution degree level is "moderate pollution", it is determined that the soil in the current monitoring area is moderately polluted by heavy metals.

[0048] The pollution penetration prediction module, based on the pollution type and degree information provided by the data processing and analysis module, combines the soil layer penetration level and historical pollution migration data to determine the priority of the repair scope. The soil layer is divided into three penetration levels: the surface layer, the transition layer, and the deep layer. By training a dataset containing historical pollution migration data, an infiltration weight matrix is generated , historical pollution migration data contains information such as the migration of different pollution types in different soil layers and at different times. During the training process, the influence weights of different pollution types under different soil layer infiltration levels are learned to obtain the infiltration weight matrix. , where represents the -th pollution type's weight coefficient under the -th soil layer infiltration level. represents the pollution type label. respectively correspond to the surface layer, transition layer, and deep layer. For the detected pollution areas, determine the corresponding infiltration level according to the soil layer where they are located, and then obtain the corresponding weight coefficient from the infiltration weight matrix . For example, when the pollution area is in the surface layer, assign it the weight coefficient; when it is in the transition layer and deep layer, assign and weight coefficients. Combine with the pollution degree value to calculate the comprehensive risk value of each pollution area. The calculation formula is , where represents the quantified value of the pollution degree of the -th pollution type, represents the number of pollution types. The quantified value of the pollution degree is quantified according to the pollution degree level determined by the feature matching module. For example, mild pollution is quantified as 1, moderate pollution is quantified as 2, and severe pollution is quantified as 3. According to the calculated comprehensive risk value , sort all pollution areas. The areas with high risk values have high repair priorities. For example, if a certain pollution area has a relatively high comprehensive risk value , it indicates that the pollution type in this area has a greater possibility of migration in the current soil layer and the pollution degree is relatively serious. Therefore, it needs to be repaired first. Finally, send the sorting result to the repair scope optimization module to provide a basis for accurately determining the repair scope.

[0049] The remediation scope optimization module optimizes and improves the remediation boundary according to the priority determination result sent by the pollution penetration prediction module, in combination with the pollution type and degree determined by the feature matching module. First, according to the priority determination result, the highly prioritized polluted areas are taken as the key consideration objects. For these areas, the pollution situation of the surrounding soil is further analyzed. In combination with the pollution type and degree determined by the feature matching module, it is judged whether there is a tendency for the pollution to spread. For example, if the electrical signal characteristics of the soil around the highly prioritized polluted area also show a certain degree of pollution and the pollution type is the same as that of this area, then it is necessary to appropriately expand the remediation scope of this area to ensure that the pollution source can be completely removed and prevent the pollution from spreading further. After optimizing and improving the remediation boundary, the soil pollution remediation scope is finally determined, and the results are stored in the historical electrical signal feature database and output, intuitively showing information such as the location, scope, pollution type and degree of the polluted area, as well as the corresponding remediation priority, providing detailed guidance for subsequent soil pollution remediation work.

[0050] In summary, this embodiment details the operation process of an analysis system for the soil pollution remediation scope. By using the biosensor network module to monitor the microbial metabolic electrical signals in the soil in real time, the data processing and analysis module processes the signals and extracts features, the feature matching module determines the pollution type and degree, the pollution penetration prediction module evaluates the priority of the remediation scope, and the remediation scope optimization module improves the remediation boundary. The entire system realizes the accurate determination of the soil pollution remediation scope. Each module works closely together, enabling a more comprehensive and accurate understanding of the soil pollution situation, and improving the effect and efficiency of soil pollution remediation.

[0051] Embodiment 2

[0052] As Figure 2 shown, this embodiment mainly demonstrates an analysis method for the soil pollution remediation scope, elaborating on its specific implementation steps in detail, and presenting how this method determines the soil pollution remediation scope through a detailed description of each step.

[0053] First, enter the stage of arranging the biosensor network (S100). In the soil area to be detected, arrange microbial metabolic electrical signal sensors to comprehensively monitor the changes in microbial metabolic electrical signals in different soil layers. Once microorganisms participate in the metabolism of heavy metal pollutants, the change in the intensity of the generated electrical signal will be keenly captured by the sensors. The sensors form a network through wireless communication technology to ensure the real-time and continuity of data.

[0054] Then, enter the data processing and analysis stage (S200). After receiving the electrical signal data transmitted from the biosensor network, process the data, perform filtering and denoising operations to remove the noise data generated by factors such as environmental interference and unstable sensors themselves, and perform feature extraction to find the key information in the data that can reflect the soil pollution situation, which becomes an important basis for judging the type and degree of soil heavy metal pollution.

[0055] Subsequently, enter the feature matching and pollution determination stage (S300). Match the extracted electrical signal feature information with the pre-established historical electrical signal feature database, adopt similarity measurement criteria such as Euclidean distance to calculate the distance between feature vectors, determine the most similar matching item, and thus judge the type and degree of heavy metal pollution.

[0056] Next, enter the pollution penetration prediction and priority determination stage (S400). Based on the heavy metal pollution type and degree information obtained from data processing and analysis, combined with the physical properties, geological structure of the soil layer and historical pollution migration data, divide the soil layer into three penetration levels: surface layer, transition layer, and deep layer. Train the historical pollution migration data to generate a penetration weight matrix. According to the penetration level of the soil layer where the pollution area is located, obtain the corresponding weight coefficient from the weight matrix, combined with the pollution degree quantization value, calculate the comprehensive risk value of each pollution area, sort the pollution areas according to the risk value, and determine the spatial priority of the repair scope.

[0057] Finally, enter the repair scope determination and optimization stage (S500). According to the type and degree of heavy metal pollution determined by feature matching and the spatial priority determination result obtained from pollution penetration prediction, optimize and improve the initially generated repair boundary, and match it with the plant-derived remediation agent database to generate a repair plan containing traditional Chinese medicine ingredient extracts. The repair plan is as follows: for lead and cadmium pollution areas, match indigo woad root extract and licorice extract, and use their polysaccharide components to adsorb heavy metal ions; for arsenic pollution areas, match astragalus extract and dandelion extract, and promote the redox reaction of arsenic through organic acid components to reduce toxicity. The plant extracts contain traditional Chinese medicine components with heavy metal enrichment and passivation functions, including one or more of astragalus, licorice, dandelion, and indigo woad root. The heavy metals include one or more of lead, cadmium, arsenic, and mercury. Finally, determine the precise heavy metal soil pollution repair scope and output the result.

[0058] In summary, from collecting data from the biosensor network, to data processing and analysis, pollution situation judgment, repair scope priority determination, and finally to the optimization and determination of the final repair scope, this soil pollution repair scope analysis method can comprehensively and accurately determine the soil pollution repair scope, provide scientific and reliable guidance for subsequent soil pollution repair work, and help to efficiently control soil pollution.

[0059] As described above, it is only the preferred embodiment of the present invention, and it does not impose any formal restrictions on the present invention. Although the present invention has been disclosed above with the preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to equivalent embodiments with equivalent changes within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A soil pollution remediation scope analysis system, characterized in that: The system consists of: biosensor network module, data processing and analysis module, feature matching module, pollution penetration prediction module, and remediation range optimization module; The biosensor network module distributes multiple microbial metabolism electrical signal sensors in the soil, monitors in real time the changes in the intensity of electrical signals generated by microorganisms in the soil due to their participation in the metabolism of heavy metal pollutants, forms a sensor network, and transmits the collected electrical signals to the data processing and analysis module; The data processing and analysis module is used to receive the electrical signal data transmitted by the biosensor network module, filter, denoise and extract features, and then transmit them to the feature matching module and the pollution penetration prediction module, and integrate the information fed back by each module for comprehensive analysis and processing; The feature matching module is used to receive the real-time electrical signal data transmitted by the data processing and analysis module, extract the real-time feature information of the electrical signal therefrom, and establish a historical electrical signal feature database, match the feature information of the real-time electrical signal with the feature information of the historical electrical signal feature database, determine the type and degree of pollution, and feed back the matching result to the data processing and analysis module; The pollution infiltration prediction module generates a permeability weight matrix through transfer learning based on the pollution type and degree information provided by the data processing and analysis module, combined with the soil layer permeability level and historical pollution migration data, to achieve priority determination of the repair range, and sends the determination result to the repair range optimization module; The remediation range optimization module optimizes and improves the remediation boundary according to the priority determination result sent by the pollution penetration prediction module and the pollution type and degree determined by the feature matching module, and finally determines the soil pollution remediation range and outputs the result.

2. A soil pollution remediation range analysis system according to claim 1, characterized in that: The sensor network of the biosensor network module is composed of a plurality of microbial metabolism electrical signal sensors distributed in the soil. The sensors can accurately monitor the electrical signals generated by the metabolism of microorganisms in the soil. When microorganisms participate in the metabolism of pollutants, the intensity of the electrical signals generated by them will change. The sensors capture the changes in real time and map the pollution concentration gradient in real time through the intensity of the electrical signals. The sensors are interconnected, and the collected electrical signals are initially converted into digital signals and then sent to the aggregation node by wireless transmission. The aggregation node then transmits the signals to the data processing and analysis module through the wireless network.

3. A soil pollution remediation range analysis system according to claim 1, characterized in that: The working principle of the data processing and analysis module is as follows: Data reception: Establish a connection with the biosensor network module through the data interface, receive the original electrical signal data transmitted by the biosensor network module in real time, and preliminarily classify and store the received data according to time sequence and sensor number; Filtering: Filter the raw electrical signal data to remove high-frequency and low-frequency noise signals caused by environmental interference and sensor noise factors, and retain the effective frequency signals related to the electrical signals of microbial metabolism; De-noising: further denoise the filtered data to obtain purer electrical signal data; Feature extraction: extract features from the denoised electrical signal data, map the high-dimensional electrical signal data to a low-dimensional space, and extract the principal components that can represent the main features of the electrical signal. The principal components contain information about the type and degree of contamination. Data transmission: The electrical signal data after filtering, denoising and feature extraction are transmitted to the feature matching module and the pollution penetration prediction module respectively, providing data support for the subsequent pollution type judgment and repair scope priority determination; Information integration analysis: Receive the pollution type and degree information fed back by the feature matching module and the priority determination results fed back by the pollution penetration prediction module, conduct a comprehensive analysis of this information with the data processed by itself, and provide a comprehensive and accurate data basis for the repair range optimization module.

4. A soil pollution remediation range analysis system according to claim 3, characterized in that: When the data processing and analysis module extracts the features of the electrical signal, the denoised electrical signal data matrix is ​​recorded as , yes The matrix of Indicates the number of collected electrical signal data sample groups, Represents the different attribute dimensions of the corresponding electrical signal data samples. Standardization is performed so that the feature mean of each dimension is 0 and the variance is 1. The standardized matrix is ​​recorded as , calculate the standardized data matrix The covariance matrix of , the covariance matrix yes A square matrix whose elements Indicates feature dimensions and The covariance between the feature dimensions, and ,in, and They are and The mean of the feature dimensions, and They are The sample in and The values ​​on the feature dimensions, for the covariance matrix Perform eigenvalue decomposition and obtain the eigenvalue and the corresponding eigenvector , where the eigenvector is a dimensional column vector, eigenvalue Indicates The variance of the principal components is calculated by arranging the eigenvalues ​​from large to small, and selecting the first The eigenvectors corresponding to the largest eigenvalues ​​form the eigenvector matrix , yes The matrix of is the number of principal components retained and , the standardized data matrix With the eigenvector matrix Multiply to get the principal component data matrix in low-dimensional space , yes The matrix and ,in, Each column in the matrix is ​​a principal component, which contains information related to the type and degree of pollution, thereby completing the mapping from high-dimensional electrical signal data to low-dimensional space and realizing feature extraction.

5. A soil pollution remediation range analysis system according to claim 4, characterized in that: The feature matching module receives the electric signal data matrix after filtering, denoising and feature extraction transmitted by the data processing and analysis module. , based on the extracted principal components, local feature points are extracted from the principal component data, that is, For each sample data point in , the feature vector of each feature point is obtained by detecting stable feature points , the feature vector Represents the characteristics of the electrical signal data in the local area, and extracts the feature vector from the historical electrical signal feature database And the corresponding pollution type label and pollution level , the currently extracted feature vector Match all feature vectors in the historical electrical signal feature database and calculate With each feature vector in the database Distance As a similarity metric, ,in, Represents different attribute dimensions of corresponding electrical signal data samples, and They are the current feature vectors and each feature vector in the database No. The value of the dimension, select the distance The smallest match, according to the pollution type label corresponding to the match and pollution level , which is the pollution type and degree corresponding to the current electrical signal data, and the matching result is fed back to the data processing and analysis module.

6. A soil pollution remediation range analysis system according to claim 1, characterized in that: The pollution penetration prediction module divides the soil layer into three penetration levels: surface layer, transition layer and deep layer.

7. The soil pollution remediation range analysis system according to claim 1, characterized in that: The pollution penetration prediction module generates a penetration weight matrix by training a dataset containing historical pollution migration data , assign a weight coefficient to each layer of pollution area, where Indicates The pollution type The weight coefficient under the permeability level of each soil layer is: Represents the pollution type label, Corresponding to the surface layer, transition layer, and deep layer respectively, for the detected contaminated area, the corresponding permeability level is determined according to the soil layer where it is located, and then the permeability weight matrix is ​​used to calculate the permeability level. The corresponding weight coefficient is obtained from the surface layer, that is, when the polluted area is on the surface, it is given The weight coefficient of is in the transition layer and deep layer, then it is given and The weight coefficient is combined with the pollution degree value to calculate the comprehensive risk value of each polluted area. ,in Indicates Quantitative value of pollution degree of each pollution type, Indicates the number of pollution types, based on the calculated comprehensive risk value , sort all polluted areas, and the areas with high risk values ​​have high repair priority. Finally, the sorting results are sent to the repair range optimization module to provide a basis for accurately determining the repair range.

8. A method for analyzing the scope of soil pollution remediation, applicable to a system for analyzing the scope of soil pollution remediation according to any one of claims 1 to 7, characterized in that: The specific steps of this method are: S100, construct a biosensor network in the soil through microbial metabolism electrical signal sensors to monitor in real time the changes in electrical signal intensity generated by microorganisms in the soil due to their participation in the metabolism of heavy metal pollutants; S200, receiving electrical signal data transmitted by the biosensor network, and performing filtering, denoising and feature extraction; S300, matching the extracted electrical signal feature information with the historical electrical signal feature database to determine matching items, thereby determining the type and degree of heavy metal pollution; S400, based on the heavy metal pollution type and degree information obtained through data processing and analysis, combined with the permeability level of the soil layer, sort the heavy metal pollution areas according to the risk value, and determine the priority of the remediation scope; S500. Optimize the restoration boundary according to the priority sorting results, match the plant-based restoration agent database, generate a restoration plan containing Chinese herbal medicine extracts, and conduct collaborative governance of heavy metal polluted areas.

9. A method for analyzing the scope of soil pollution remediation according to claim 8, characterized in that: The S500 matches the plant-derived remediation agent database according to the heavy metal pollution type and range information output by S400, and generates a remediation scheme including plant extracts, wherein the plant extracts contain Chinese medicinal ingredients with heavy metal enrichment and passivation functions, including one or more of astragalus, licorice, dandelion, and isatis indigotica, and the heavy metals include one or more of lead, cadmium, arsenic, and mercury; The remediation scheme is: for lead and cadmium polluted areas, isatis indigotica extract and licorice extract are matched to use their polysaccharide components to absorb heavy metal ions; For arsenic-contaminated areas, astragalus extract and dandelion extract are matched to promote the redox reaction of arsenic through organic acid components and reduce toxicity.

Images