Method for degrading organic pollutants in garden soil by utilizing rhizosphere microflora

Abstract

The invention provides a garden soil organic pollutant degradation method using rhizosphere microbial communities, and relates to the technical field of soil remediation, and the method comprises the following steps: matching strain parameters according to pollutant types and concentrations, and determining a plurality of strain type thresholds and strain density thresholds; matching plant parameters according to pollutant types, pollutant concentrations and environmental conditions, and determining a plurality of plant type thresholds and plant density thresholds; and based on a plurality of strain type thresholds, strain density thresholds, plant type thresholds and plant density thresholds, executing remediation scheme optimization of the pollution distribution area, and determining an optimal remediation scheme. By means of the method, the problems that a traditional method mainly depends on literature retrieval and data lookup to conduct soil remediation analysis, useful information cannot be quickly retrieved, the matching degree of the retrieved information and the soil degradation requirement is low, and consequently the precision and practicability of soil remediation scheme setting are poor can be solved; and the soil remediation efficiency and remediation quality can be effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of soil remediation, and in particular to a method for degrading organic pollutants in garden soil by utilizing rhizosphere microbial communities. Background Art

[0002] In the field of soil remediation, especially when dealing with the degradation of organic pollutants, traditional analysis methods mainly rely on literature retrieval and technical data review to obtain relevant remediation technologies, pollutant degradation mechanisms and the basis for program formulation. However, with the increasing complexity and diversification of soil pollution problems, traditional soil remediation analysis methods have gradually exposed some technical bottlenecks and shortcomings.

[0003] First, the traditional method relies on manual literature retrieval and data review, which is often time-consuming and inefficient. This inefficient retrieval method not only delays the formulation of remediation plans, but may also lead to the omission of important technical information. Secondly, due to the different types of soil pollution, pollutant concentrations and on-site environmental conditions, it is difficult to fully match the needs of specific contaminated sites by simply relying on theoretical data and technical cases in the literature, resulting in insufficient applicability of technical solutions. In addition, existing methods usually fail to fully consider the specific types of pollutants, the complexity of the soil environment and other conditions, so remediation plans often lack specificity and are difficult to achieve the desired results.

[0004] In summary, traditional soil remediation analysis methods have technical problems such as slow information retrieval speed, low matching between information and demand, insufficient scheme accuracy and poor practicality. There is an urgent need for a new method that can quickly and accurately obtain relevant information and flexibly adjust the remediation scheme according to actual needs to improve the efficiency and effectiveness of soil remediation. Summary of the invention

[0005] The purpose of this application is to provide a method for degrading organic pollutants in garden soil using rhizosphere microbial communities, in order to solve the technical problem that traditional methods mainly rely on literature retrieval and data review for soil remediation analysis, which cannot quickly retrieve useful information, and at the same time, the retrieved information has a low match with soil degradation needs, resulting in poor accuracy and practicality in the setting of soil remediation plans.

[0006] In view of the above problems, the present application provides a method for degrading organic pollutants in garden soil using rhizosphere microbial communities, including: taking multi-point samples of the target soil, and determining the distribution of organic pollutants based on the analysis of the multi-point sampling results, wherein the distribution of organic pollutants includes several pollution distribution areas, and each pollution distribution area is marked with a pollutant type and a pollutant concentration; matching the strain parameters of rhizosphere microorganisms according to the pollutant type and pollutant concentration, and determining several strain parameter thresholds, wherein the strain parameter threshold includes a strain type threshold, and each strain type is marked with a strain density threshold; obtaining the environmental conditions of the area where the target soil is located, matching plant parameters according to the pollutant type, pollutant concentration and environmental conditions, and determining several planting parameter thresholds, wherein the planting parameter threshold includes a plant type threshold, and each plant type is marked with a plant density threshold; based on several strain type thresholds, several strain density thresholds, several plant type thresholds and several plant density thresholds, performing optimization analysis of remediation schemes for the several pollution distribution areas, and integrating and determining the optimal remediation scheme to implement organic pollutant degradation in the target soil.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: By taking multi-point samples of the target soil, the distribution of organic pollutants is determined according to the analysis of the multi-point sampling results, wherein the distribution of organic pollutants includes several pollution distribution areas, and each pollution distribution area is marked with a pollutant type and a pollutant concentration; then, the strain parameters of rhizosphere microorganisms are matched according to the pollutant type and the pollutant concentration, and several strain parameter thresholds are determined, wherein the strain parameter threshold includes a strain type threshold, and each strain type is marked with a strain density threshold; on the other hand, the environmental conditions of the area where the target soil is located are obtained, and plant parameters are matched according to the pollutant type, the pollutant concentration and the environmental conditions to determine several planting parameter thresholds, wherein the planting parameter threshold includes a plant type threshold, and each plant type is marked with a plant density threshold; finally, based on several strain type thresholds, several strain density thresholds, several plant type thresholds and several plant density thresholds, the remediation scheme optimization analysis of the several pollution distribution areas is performed, and the optimal remediation scheme is determined to implement the degradation of organic pollutants in the target soil by integration; the above method can improve the intelligence and comprehensiveness of soil remediation retrieval analysis, improve information retrieval efficiency and information matching, achieve the technical goal of quickly and accurately setting soil remediation schemes, and effectively improve soil remediation efficiency and remediation quality.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 A schematic diagram of a process for degrading organic pollutants in garden soil using rhizosphere microbial communities in this application; Figure 2 This is a schematic diagram of the process of determining the distribution of organic pollutants in a method for degrading organic pollutants in garden soil using rhizosphere microbial communities in this application. DETAILED DESCRIPTION

[0011] This application provides a method for degrading organic pollutants in garden soil using rhizosphere microbial communities, solving the technical problem that traditional methods mainly rely on literature retrieval and data review for soil remediation analysis, which cannot quickly retrieve useful information, and the retrieval information has a low match with soil degradation requirements, resulting in poor accuracy and practicality in the setting of soil remediation plans. It can improve the intelligence and comprehensiveness of soil remediation retrieval analysis, improve information retrieval efficiency and information matching, achieve the technical goal of quickly and accurately setting soil remediation plans, and effectively improve soil remediation efficiency and remediation quality.

[0012] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0013] For examples, please see the attached Figure 1The present application provides a method for degrading organic pollutants in garden soil using rhizosphere microbial communities, which specifically includes the following steps: Step 1: Multi-point sampling is performed on the target soil, and the distribution of organic pollutants is determined based on the analysis of the multi-point sampling results, wherein the distribution of organic pollutants includes several pollution distribution areas, and each pollution distribution area is marked with the pollutant type and pollutant concentration.

[0014] Specifically, first, multiple sampling points are arranged in the target soil area according to certain rules. The arrangement method can be selected according to the area of ​​the polluted site, the location of the pollution source and the terrain conditions, such as grid arrangement or random arrangement. The number and spacing of the sampling points need to be determined according to the specific conditions of the polluted site to ensure the representativeness and coverage of the samples. Then, multi-point sampling is performed on the target soil based on multiple sampling points to obtain multi-point sampled soil. Then, gas chromatography-mass spectrometry technology is used to detect organic matter in the multi-point sampled soil to determine multiple sampling pollutant types (such as polycyclic aromatic hydrocarbons, benzene series, pesticides, volatile organic compounds, etc.) and multiple sampling pollutant concentrations, and an initial pollution distribution map is constructed based on multiple sampling pollutant types and multiple sampling pollutant concentrations.

[0015] Then, the initial pollution distribution map is divided according to the pollutant type and pollutant concentration to determine several pollution distribution areas, each of which is marked with the pollutant type and pollutant concentration. Finally, the organic pollutant distribution is formed according to several pollution distribution areas, that is, the various pollution distribution areas are integrated to form a complete organic pollutant distribution map, which not only contains the boundaries of each pollution area, but also clearly identifies the pollutant type and concentration information of each area. By constructing the distribution of organic pollutants, a scientific basis is provided for subsequent precise and zoned soil remediation, thereby improving the accuracy of soil remediation program settings.

[0016] Step 2: Match the strain parameters of rhizosphere microorganisms according to the pollutant type and pollutant concentration, and determine several strain parameter thresholds, wherein the strain parameter thresholds include strain type thresholds, and each strain type is identified with a strain density threshold.

[0017] Specifically, first, a first pollution distribution area is randomly selected from the several pollution distribution areas, and the first pollutant type and the first pollutant concentration of the first pollution distribution area are obtained; then the first pollutant type and the first pollutant concentration are input into the microbial knowledge reserve library for rhizosphere microorganism matching, wherein the microbial knowledge reserve library contains rich rhizosphere microorganism information, including the degradation ability of different strains (Pseudomonas, Bacillus subtilis, etc.) on specific pollutants, the optimal growth conditions of strains (such as density) and other information, and according to the matching results of the reserve library, the strain type that best matches the specific pollutant type is determined, wherein each pollution distribution area should identify one or more suitable strain types, which will be used as microorganisms in the remediation process, and multiple related strain parameters are obtained, wherein the related strain parameters include strain type and strain density.

[0018] Then, a high-frequency feature analysis is performed on multiple related strain parameters. High-frequency feature analysis refers to identifying the most common and effective strain types and their key parameters in a specific polluted environment through statistical analysis of multiple related strain parameters. For example, the frequency of use of each strain type under similar pollution conditions is counted, and based on the statistical results, multiple strain types with the highest frequency are determined as the first strain type threshold; then multiple strain density sets corresponding to the first strain type threshold are obtained, and the minimum density and maximum density of multiple strain density sets are extracted to construct multiple first strain density thresholds. Finally, the first strain parameter threshold is constructed based on the first strain type threshold and multiple first strain density thresholds. Using the same method for obtaining the first strain parameter threshold, the several pollution distribution areas are matched and analyzed to obtain several strain parameter thresholds.

[0019] Step 3: Obtain the environmental conditions of the area where the target soil is located, match plant parameters according to the pollutant type, pollutant concentration and environmental conditions, and determine several planting parameter thresholds, wherein the planting parameter thresholds include plant type thresholds, and each plant type is identified with a plant density threshold.

[0020] Specifically, first, obtain the environmental conditions of the area where the target soil is located, including climate conditions (average annual temperature, rainfall, sunshine duration, etc.), soil properties (soil pH, nutrient content, water content, air permeability, etc.). Then obtain several pollutant types and several pollutant concentrations in several pollution distribution areas, and then input several pollutant types, several pollutant concentrations and environmental conditions into the plant knowledge reserve for plant parameter matching, wherein the plant knowledge reserve contains the absorption and degradation capabilities of different plants for specific pollutants, and plant types include willows, poplars, alfalfa, etc., and obtain several related plant parameter sets, wherein plant parameters include plant types and plant density. Then perform high-frequency feature analysis on the several related plant parameter sets to determine several planting parameter thresholds, wherein the planting parameter thresholds include plant type thresholds, and each plant type is marked with a plant density threshold.

[0021] Step 4: Based on several strain type thresholds, several strain density thresholds, several plant type thresholds and several plant density thresholds, perform optimization analysis of the remediation schemes for the several pollution distribution areas, and integrate and determine the optimal remediation scheme to implement the degradation of organic pollutants in the target soil.

[0022] Specifically, first, a first pollution distribution area is randomly selected, and the first strain type threshold, the first strain density threshold, the first plant type threshold and the first plant density threshold of the first pollution distribution area are obtained, and multiple initial remediation schemes are randomly generated based on the first strain type threshold, the first strain density threshold, the first plant type threshold and the first plant density threshold. Then, according to the multiple initial remediation schemes, the remediation scheme optimization analysis of the first pollution distribution area is performed to obtain the first optimized remediation scheme. Then, using the same method, the remediation scheme optimization analysis of several pollution distribution areas is performed to obtain several optimized remediation schemes of several pollution distribution areas. Finally, the optimal remediation scheme is generated based on the fusion of several pollution distribution areas and several optimized remediation schemes, and the degradation of organic pollutants in the target soil is implemented according to the optimal remediation scheme.

[0023] By providing a method for degrading organic pollutants in garden soils using rhizosphere microbial communities, the technical problem that traditional methods mainly rely on literature retrieval and data review for soil remediation analysis, are unable to quickly retrieve useful information, and at the same time, the retrieved information has a low match with soil degradation needs, resulting in poor accuracy and practicality in setting up soil remediation plans can be solved. By taking multi-point samples of the target soil, the distribution of organic pollutants is determined according to the analysis of the multi-point sampling results, wherein the distribution of organic pollutants includes several pollution distribution areas, and each pollution distribution area is marked with a pollutant type and a pollutant concentration; then, the strain parameters of rhizosphere microorganisms are matched according to the pollutant type and the pollutant concentration, and several strain parameter thresholds are determined, wherein the strain parameter threshold includes a strain type threshold, and each strain type is marked with a strain density threshold; on the other hand, the environmental conditions of the area where the target soil is located are obtained, and plant parameters are matched according to the pollutant type, the pollutant concentration and the environmental conditions to determine several planting parameter thresholds, wherein the planting parameter threshold includes a plant type threshold, and each plant type is marked with a plant density threshold; finally, based on several strain type thresholds, several strain density thresholds, several plant type thresholds and several plant density thresholds, the remediation scheme optimization analysis of the several pollution distribution areas is performed, and the optimal remediation scheme is determined to implement the degradation of organic pollutants in the target soil by integration; the above method can improve the intelligence and comprehensiveness of soil remediation retrieval analysis, improve information retrieval efficiency and information matching, achieve the technical goal of quickly and accurately setting soil remediation schemes, and effectively improve soil remediation efficiency and remediation quality.

[0024] Further, as attached Figure 2 As shown, the distribution of organic pollutants is determined based on the analysis of multi-point sampling results. This application includes: Gas chromatography-mass spectrometry technology is used to detect organic matter in multi-point soil sampling to determine multiple sampling pollutant types and multiple sampling pollutant concentrations, and pollution diffusion simulation is performed based on the multiple sampling pollutant types and multiple sampling pollutant concentrations to construct an initial pollution distribution map; the initial pollution distribution map is divided once according to the pollutant type to determine multiple initial pollution distribution sub-maps, wherein the pollutant type in each initial pollution distribution sub-map is the same; the multiple initial pollution distribution sub-maps are divided twice according to the pollutant concentration to determine a number of pollution distribution areas, and the organic pollutant distribution is constructed based on the several pollution distribution areas.

[0025] Specifically, the soil samples at each sampling point were tested using gas chromatography-mass spectrometry technology to identify the types of organic pollutants in each sample, such as polycyclic aromatic hydrocarbons, benzene derivatives, pesticides, volatile organic compounds, etc. The concentrations of various pollutants in the samples at each sampling point were determined through quantitative analysis of mass spectrometry signals, and multiple sampling pollutant types and multiple sampling pollutant concentrations at multiple sampling points were obtained.

[0026] Then, a suitable pollution diffusion model is selected, such as a Gaussian diffusion model or a numerical simulation model, to predict the diffusion of the detected organic pollutants. That is, the pollutant type and concentration data of each sampling point are input into the diffusion simulation model, and the diffusion trend and distribution range of pollutants are simulated in combination with soil (permeability, porosity, water content, etc.) and environmental conditions (temperature, precipitation, etc.). Based on the simulation results, the diffusion distribution of pollutants in the target area is obtained. At the same time, spatial drawing tools are used to visualize the type and concentration information of each pollutant to generate an initial pollutant distribution map, in which the spatial distribution and concentration gradient of pollutants are marked.

[0027] Then, the initial pollution distribution map is divided once according to the pollutant type, that is, the areas of the same pollutant type are grouped into one category, and multiple initial pollution distribution sub-maps are determined, each of which contains only the same type of pollutants. Then, the multiple initial pollution distribution sub-maps are divided twice according to the pollutant concentration, that is, the pollution distribution areas in the same concentration range in each initial pollution distribution sub-map are grouped into one category to obtain several pollution distribution areas. Finally, several pollution distribution areas are integrated to construct the distribution of organic pollutants. This map not only shows the type of pollutants, but also identifies the gradient distribution of pollutant concentrations, which helps to formulate more accurate and efficient pollution remediation plans, improve resource utilization efficiency, and ensure that polluted areas are comprehensively and effectively governed.

[0028] Further, the multiple initial pollution distribution sub-maps are divided twice according to the pollutant concentration to determine a number of pollution distribution areas. The present application includes: A first initial pollution distribution submap is randomly selected from the multiple initial pollution distribution submaps, and the minimum pollutant concentration in the first initial pollution distribution submap is obtained; taking the position of the minimum pollutant concentration as the starting point, the first initial pollution distribution submap is simulated for water filling to determine the first pollutant concentration, wherein the first pollutant concentration is the first pollutant concentration that is not covered by the water surface; the deviation between the minimum pollutant concentration and the first pollutant concentration is calculated to obtain a first concentration deviation, and if the first concentration deviation is greater than or equal to a predetermined concentration deviation scalar, a first dividing line is set at the position of the first pollutant concentration, and taking the first pollutant concentration as the starting point, the simulated water filling is continued until the water surface is not covered by the maximum pollutant concentration of the first initial pollution distribution submap, then the water filling is stopped to obtain multiple dividing lines; the first initial pollution distribution submap is divided by the multiple dividing lines to obtain multiple pollutant distribution areas, which are added to the several pollution distribution areas, wherein the middle value of the pollutant concentration in the pollution distribution area is set as the pollutant concentration corresponding to the distribution area.

[0029] Specifically, first, a first initial pollution distribution subgraph is randomly selected from the multiple initial pollution distribution subgraphs, wherein the first initial pollution distribution subgraph is any one of the multiple initial pollution distribution subgraphs, and the minimum pollutant concentration in the first initial pollution distribution subgraph is obtained. Then, starting from the location of the minimum pollutant concentration, the first initial pollution distribution subgraph is simulated for watering, where the simulated watering means gradually filling the area in the subgraph that is lower than the current water level until a new pollutant concentration value is found, and the first pollutant concentration that is flooded to the water surface for the first time is called the first pollutant concentration. At this time, the water surface covers part of the area, but has not yet completely covered the entire subgraph.

[0030] Then, the deviation between the minimum pollutant concentration and the first pollutant concentration is calculated to obtain the first concentration deviation; then, the first concentration deviation is judged according to a predetermined concentration deviation scalar, which is a predetermined deviation threshold value and can be set according to actual conditions. If the first concentration deviation is greater than or equal to the predetermined concentration deviation scalar, a first dividing line is set at the location of the first pollutant concentration, and then the first pollutant concentration is used as the starting point to continue the simulated irrigation until the water surface covers the maximum pollutant concentration in the entire first initial pollution distribution sub-map, that is, when the water surface covers the entire sub-map and the maximum pollutant concentration is covered, the irrigation process ends. At the same time, during the irrigation process, each time the concentration deviation is detected to be greater than or equal to the predetermined scalar, a dividing line will be generated. As the simulated irrigation proceeds, multiple dividing lines will gradually be formed, and these dividing lines will distinguish areas with different concentrations to obtain multiple dividing lines.

[0031] Finally, the first initial pollution distribution submap is divided into multiple pollutant distribution areas by multiple dividing lines, each of which represents a different pollutant concentration level, and multiple pollutant distribution areas are obtained; at the same time, for each divided pollutant distribution area, the median value of its pollutant concentration is calculated as the representative pollutant concentration of the area, and the median value can be obtained by calculating the average of the maximum concentration and the minimum concentration of the area; finally, the multiple pollutant distribution areas are added to several pollution distribution areas to obtain the several pollution distribution areas. By refining the initial pollution distribution submap by simulating irrigation method to generate multiple pollutant distribution areas, and accurately calculating the median value of the pollutant concentration of each area, it is possible to dynamically and accurately divide the pollution area, help decision makers to rationally plan soil remediation work, and improve remediation efficiency and accuracy.

[0032] Furthermore, the present application also includes the following steps: If the first concentration deviation is less than a predetermined concentration deviation scalar, the simulated flooding is continued until the concentration deviation between the pollutant concentration at the position submerged by the water surface and the minimum pollutant concentration is greater than or equal to the predetermined concentration deviation scalar, and then a first dividing line is set.

[0033] Specifically, if the first concentration deviation (the difference between the first pollutant concentration submerged by the water surface and the minimum pollutant concentration) is less than the predetermined concentration deviation scalar, no dividing line is set and the simulated watering continues. The process of simulated watering is to gradually fill the area in the pollutant distribution submap until the water surface submerges a new pollutant concentration. In the process of continued watering, the water surface will gradually submerge new areas, detect the pollutant concentration that is submerged each time, and calculate the concentration deviation between the pollutant concentration and the minimum pollutant concentration. The concentration deviation between the submerged pollutant concentration and the minimum pollutant concentration is continuously detected until a pollutant position with a concentration deviation greater than or equal to the predetermined concentration deviation scalar is found, and the first dividing line is set at the position where the pollutant concentration is located; at the same time, after the first dividing line is set, the pollutant concentration at the dividing line just set is used as the new starting point, and the simulated watering process continues.

[0034] Further, according to the pollutant type and pollutant concentration, the strain parameters of the rhizosphere microorganisms are matched to determine several strain parameter thresholds. The present application includes: A first pollution distribution area is randomly selected from the several pollution distribution areas, and a first pollutant type and a first pollutant concentration of the first pollution distribution area are obtained; the first pollutant type and the first pollutant concentration are input into a microbial knowledge reserve for matching, and a plurality of relevant strain parameters of rhizosphere microorganisms are obtained; high-frequency feature extraction is performed on the multiple relevant strain parameters to determine a first strain type threshold and a first strain density threshold of the first strain type; the first strain type threshold and the first strain density threshold are used as first strain parameter thresholds, and added to the several strain parameter thresholds.

[0035] Specifically, first, a first pollution distribution area is randomly selected from the several pollution distribution areas, and the first pollutant type and the first pollutant concentration of the first pollution distribution area are obtained. Then, the first pollutant type and the first pollutant concentration are input into the microbial knowledge reserve for matching. The microbial knowledge reserve matches suitable rhizosphere microbial strains according to the type and concentration of the pollutants, and outputs a plurality of related strain parameters, wherein the related strain parameters include strain type and strain density. Then, high-frequency feature extraction is performed on the multiple related strain parameters, that is, the most commonly used and most effective strain types and their density thresholds in similar pollution environments are identified, and the first strain type threshold and the first strain density threshold of the first strain type are determined. Finally, the first strain type threshold and the first strain density threshold are added as the first strain parameter threshold to several strain parameter thresholds to obtain the several strain parameter thresholds.

[0036] By inputting the pollutant type and concentration into the microbial knowledge reserve for matching, we can accurately find the suitable rhizosphere microbial strain type and density threshold. By extracting high-frequency features, we can determine the optimal strain type and density threshold, which can ensure the high efficiency of pollutant degradation and the targeted nature of the remediation plan, and provide customized microbial remediation strategies for different polluted areas.

[0037] Further, high-frequency feature extraction is performed on the multiple related strain parameters, and the present application includes: The occurrence frequencies of the same strain type in the multiple related strain parameters are counted to obtain multiple strain types and multiple type frequencies; the multiple type frequencies are screened according to a predetermined frequency threshold to determine multiple high-frequency strain types to construct the first strain type threshold; the minimum density and maximum density are extracted for multiple strain density sets of the multiple high-frequency strain types to obtain multiple first strain density thresholds.

[0038] Specifically, first, calculate the frequency of occurrence of each strain type in the multiple related strain parameters, that is, count the number of occurrences of the same strain type. This step will help us understand which strains appear most frequently in similar polluted environments, and obtain multiple strain types and multiple type frequencies. Type frequency refers to the number of times each strain appears in the matching results. Then set a frequency threshold for screening high-frequency strain types. This threshold determines which strain types have a high enough frequency of occurrence and should be regarded as high-frequency strains. The threshold can be set according to specific needs. For example, strain types with a frequency of occurrence greater than or equal to 3 times will be regarded as high-frequency strains. Then, the multiple type frequencies are screened according to a predetermined frequency threshold, and the strain types with a frequency of occurrence greater than or equal to the predetermined threshold are set as high-frequency strain types to obtain multiple high-frequency strain types, and a first strain type threshold is constructed based on the multiple high-frequency strain types, wherein the first strain type threshold represents the most suitable set of high-frequency strain types under the current pollutant type and concentration.

[0039] Then, for each high-frequency strain type screened out, the corresponding strain density set is collected, that is, the different densities corresponding to each high-frequency strain in the matching, and multiple strain density sets are obtained; then, for the strain density set of each high-frequency strain type, the minimum density and maximum density are extracted to construct the first strain density threshold, that is, the optimal density range suitable for the polluted environment, and multiple first strain density thresholds are obtained. By performing frequency statistics and screening on multiple related strain parameters, the high-frequency strain type that is most suitable for the current polluted environment can be determined, and by extracting the minimum and maximum values ​​of the strain density, a reasonable strain density threshold is constructed. This process ensures that the most effective microorganisms are selected during the pollution remediation process and can be applied within the optimal concentration range, greatly improving the efficiency of pollutant degradation.

[0040] Further, according to the pollutant type, pollutant concentration and environmental conditions matching plant parameters, several planting parameter thresholds are determined. This application includes: The first pollutant type and the first pollutant concentration are input into a plant knowledge reserve for matching, and a plurality of relevant plant parameters are determined, wherein the relevant plant parameters include relevant plant types and relevant planting densities, and the relevant plant parameters are marked with relevant environmental conditions; based on the environmental conditions, deviation calculations are performed on the plurality of relevant environmental conditions to determine a plurality of environmental deviations; if the environmental deviation is less than an expected deviation index, the corresponding relevant plant parameters are set as adapted plant parameters to obtain a plurality of adapted plant parameters; high-frequency feature extraction is performed on the plurality of adapted plant parameters to determine a first plant type threshold and a first plant density threshold of the first plant type.

[0041] Specifically, first, the first pollutant type and the first pollutant concentration are input into a plant knowledge reserve for matching. The plant knowledge reserve contains a large amount of relevant information such as the restoration ability, adaptability, planting conditions, etc. of plants, and multiple relevant plant parameters are determined, wherein the relevant plant parameters include relevant plant types and relevant planting densities, and the relevant plant parameters are marked with relevant environmental conditions, which refer to the environmental conditions required for plant growth, such as soil pH, water requirements, temperature requirements, etc.

[0042] Then, based on the actual environmental conditions of the polluted area (such as the current soil pH value, temperature, etc.), the deviation of multiple related environmental conditions is calculated to obtain multiple environmental deviations. Then, an expected deviation index, that is, the expected deviation threshold, is set, which can be set according to the actual scenario; multiple environmental deviations are judged according to the expected deviation index. If the environmental deviation is less than the expected deviation index, the corresponding related plant parameters are set as adaptive plant parameters to obtain multiple adaptive plant parameters. Finally, high-frequency feature extraction is performed on the multiple adaptive plant parameters, that is, from the multiple adaptive plant parameters selected, the frequency of occurrence of each adaptive plant type is counted to perform high-frequency feature extraction, such as counting the application frequency and success rate of plant types in historical restoration data, extracting those plant types that are used more frequently in similar polluted environments, and selecting the plant type with the highest frequency as the first plant type threshold through high-frequency feature extraction. For example, willows and poplars have a high frequency of occurrence, so they are used as the first plant type threshold. On the other hand, for each adapted plant type, the corresponding planting density data is collected. The planting density is usually expressed as the number of plants per square meter. By analyzing historical data, the minimum planting density and the maximum planting density of each adapted plant type are extracted to determine the first plant density threshold. Finally, the determined first plant type threshold and the first plant density threshold are set as the first planting parameter threshold and added to the plurality of planting parameter thresholds.

[0043] By inputting the pollutant type and concentration into the plant knowledge reserve library to match and screen the suitable plant types and densities, and combining the deviation calculation of environmental conditions to determine the most suitable plant parameters, and extracting high-frequency features to obtain the planting parameter threshold, the selection of restoration plants and their planting density can be optimized to ensure the scientificity and effectiveness of the restoration plan, thereby maximizing the pollution restoration effect.

[0044] Further, deviation calculation is performed on multiple related environmental conditions to determine multiple environmental deviations. The present application includes: A first relevant environmental condition is randomly selected from the multiple relevant environmental conditions; based on multiple environmental attribute parameters, attribute parameter deviations are calculated for the environmental condition and the first relevant environmental condition to determine multiple first attribute deviation values; the number of parameters whose first attribute deviation values ​​are greater than the benchmark attribute deviation value in the multiple first attribute deviation values ​​is counted, set as a first environmental deviation degree, and added to the multiple environmental deviation degrees.

[0045] Specifically, first, any one of the multiple related environmental conditions is randomly selected as the first related environmental condition; then multiple environmental attribute parameters are configured, including but not limited to soil pH value, temperature, humidity, soil permeability, sunshine duration, etc.; then, based on the multiple environmental attribute parameters, the environmental condition and the first related environmental condition are subjected to attribute parameter deviation calculation to determine multiple first attribute deviation values. A reference attribute deviation value is set as a judgment standard. For example, for pH value, the allowable deviation range is ±0.5, and for temperature, the allowable deviation is ±3°C. Then, the first attribute deviation value of each attribute is compared with the preset reference attribute deviation value, and the number of parameters whose deviation value exceeds the reference is counted. For example, if the deviation value of soil pH value is 0.5, which is equal to the reference value, the number of parameters exceeding the reference is not counted; if the temperature deviation value is 4°C, which is greater than the reference attribute deviation value by 3°C, the number of parameters exceeding the reference is counted; then the number of parameters whose deviation value is greater than the reference value is defined as the first environmental deviation degree. It reflects the degree of deviation of the environmental adaptability of the selected plant. For example, if the deviation value of 2 attributes is greater than the reference value, the first environmental deviation degree is 2. Finally, the first environmental deviation is added to the multiple environmental deviations. By calculating the deviations of various environmental attribute parameters, the adaptability of plants to the current environment can be accurately determined, and based on the statistics of environmental deviations, the most suitable restoration plants for the current environmental conditions can be screened out, thereby improving the efficiency and effect of pollution remediation.

[0046] Further, based on several strain type thresholds, several strain density thresholds, several plant type thresholds and several plant density thresholds, the optimization analysis of the remediation schemes for the several pollution distribution areas is performed, and the optimal remediation scheme is determined by integration. The present application includes: Obtain a first strain type threshold, a first strain density threshold, a first plant type threshold and a first plant density threshold of the first pollution distribution area, and randomly generate multiple initial remediation schemes based on the first strain type threshold, the first strain density threshold, the first plant type threshold and the first plant density threshold; input the multiple initial remediation schemes into a resource investment plug-in for cost calculation to determine multiple investment costs; input the first pollutant type, the first pollutant concentration, the environmental conditions and the multiple initial remediation schemes into a soil degradation predictor to obtain multiple predicted removal ratios and multiple predicted degradation rates, wherein the soil degradation predictor is a prediction model constructed based on machine learning; calculate multiple scheme fitnesses of the multiple initial remediation schemes according to the multiple input costs, the multiple predicted removal ratios and the multiple predicted degradation rates, wherein the scheme fitness is negatively correlated with the input cost, and positively correlated with the predicted removal ratio and the predicted degradation rate; perform remediation scheme optimization analysis based on the multiple scheme fitnesses, and output the optimal remediation scheme.

[0047] Specifically, first, the first strain type threshold, the first strain density threshold, the first plant type threshold and the first plant density threshold of the first pollution distribution area are obtained; then, based on the first strain type threshold, the first strain density threshold, the first plant type threshold and the first plant density threshold, a plurality of initial remediation schemes are generated in a randomized manner, wherein each scheme combines different configurations of strain type, strain density, plant type and plant density to varying degrees.

[0048] Then, the multiple initial remediation plans are input into the resource investment plug-in for cost calculation. For example, according to the strain type and the required density, the strain purchase cost, transportation cost, etc. are calculated; according to the plant type and planting density, the plant purchase cost, planting cost and maintenance cost, etc. are calculated; the resource investment plug-in will calculate the total investment cost of each remediation plan based on the costs of the above-mentioned microbial remediation and plant remediation. The plug-in will comprehensively consider various costs and generate the final cost output of multiple remediation plans to obtain multiple investment costs of multiple initial remediation plans.

[0049] A soil degradation predictor is constructed based on machine learning. For example, a soil degradation predictor is constructed based on a BP neural network, wherein the soil degradation predictor is a neural network model that can be iteratively optimized in machine learning, including an input layer, multiple hidden layers, and an output layer, wherein the input data of the input layer are pollutant type, pollutant concentration, environmental conditions, and remediation schemes, and the output data of the output layer are the predicted removal ratio and predicted degradation rate of each remediation scheme, wherein the removal ratio refers to the percentage of pollutants degraded during the remediation process, for example, a removal ratio of 80% means that the concentration of the pollutant drops from 80 mg / kg to 16 mg / kg, and the degradation rate refers to the speed at which pollutants are decomposed during the remediation process, usually expressed in terms of the amount of pollutants degraded per unit time (such as a degradation rate of mg / kg per month). Then, sample training data is collected, wherein the sample training data includes sample pollutant type, sample pollutant concentration, sample environmental conditions, sample initial remediation scheme, sample removal ratio and sample degradation rate; and the sample training data is used to supervise the soil degradation predictor, wherein supervised learning is a machine learning method, that is, the model is trained using labeled data (i.e., sample data with known input and output), the goal is to let the model learn to predict the output results (removal ratio, degradation rate) from the input data (pollutant type, concentration, environmental conditions, remediation scheme); the model parameters are adjusted through the training algorithm so that the model can minimize the error between the predicted value (removal ratio and degradation rate) and the actual value, and the gap between the predicted value and the true value is evaluated through the loss function (such as mean square error), and the model weight is updated using gradient descent or other optimization algorithms to obtain a soil degradation predictor that meets the expected convergence conditions. Finally, the first pollutant type, the first pollutant concentration, the environmental conditions and multiple initial remediation schemes are input into the soil degradation predictor, and multiple predicted removal ratios and multiple predicted degradation rates are output.

[0050] A scheme fitness calculation function is further constructed, in which the scheme fitness is negatively correlated with the input cost, and positively correlated with the predicted removal ratio and predicted degradation rate. The scheme fitness is the product of the proportion weight and the removal ratio, the product of the acceleration rate weight and the degradation rate / the product of the cost weight and the input cost, in which the proportion weight, rate weight and cost weight are used to adjust the relative importance of the removal ratio, degradation rate and cost, and can be set according to actual conditions. Then, using the scheme fitness calculation function, the fitness calculation is performed on the multiple input costs, multiple predicted removal ratios and multiple predicted degradation rates to obtain multiple scheme fitnesses of multiple initial remediation schemes. The larger the scheme fitness, the better the degradation effect of soil organic pollutants. Finally, based on the fitness of the multiple schemes, the remediation scheme optimization analysis is performed to output the optimal remediation scheme.

[0051] Further, based on the fitness of the multiple solutions, a repair solution optimization analysis is performed to output the optimal repair solution. The present application includes: Based on the fitness of the multiple schemes, the multiple initial repair schemes are arranged in descending order of fitness to construct an initial repair scheme sequence, and the first 10% of the initial repair schemes in the initial repair scheme sequence are selected as the better repair schemes, and the last 5% of the initial repair schemes in the initial repair scheme sequence are selected as the worse repair schemes to obtain a better repair scheme group and a worse repair scheme group; based on the better repair scheme group, high-frequency features of strain types and plant types are extracted to determine the better strain type and the better plant type; based on the better strain type, the first strain density threshold, the better plant type and the first plant density A preset number of supplementary repair schemes are randomly generated according to a degree threshold to obtain a supplementary repair scheme group, wherein the preset number is 5% of the number of initial repair schemes; the inferior repair scheme group is replaced by the supplementary repair scheme group to obtain an updated repair scheme sequence, and repair schemes are iteratively optimized according to the updated repair scheme sequence until a predetermined number of optimization searches is met, and the head repair scheme of the current repair scheme sequence is output as the first adaptive repair scheme; multiple adaptive repair schemes for the multiple pollution distribution areas are obtained by optimization in turn, and the optimal repair scheme is generated based on the fusion of the multiple pollution distribution areas and the multiple adaptive repair schemes.

[0052] Specifically, first, based on the fitness of the multiple schemes, the multiple initial repair schemes are arranged from large to small according to the fitness, and an initial repair scheme sequence is constructed; then the first 10% of the initial repair schemes in the initial repair scheme sequence are selected as the better repair schemes, and the last 5% of the initial repair schemes in the initial repair scheme sequence are selected as the worse repair schemes, and a better repair scheme group and a worse repair scheme group are obtained. Then, based on the better repair scheme group, high-frequency features of strain types and plant types are extracted, that is, the strain types used in each better repair scheme are counted, and the number of occurrences of each strain type in all better repair schemes is calculated. By counting the high-frequency features of the strain types, the most commonly used and most effective strain types are determined; similarly, the plant types used in each better repair scheme are counted, and the number of occurrences of each plant type is calculated to determine the most commonly used plant type; then, by counting the frequency of strain types in the better repair scheme group, the strain type with the most occurrences is selected as the better strain type, and by counting the frequency of plant types, the plant type with the most occurrences is selected as the better plant type, and the better strain type and better plant type are obtained.

[0053] Then, based on the superior strain type, the first strain density threshold, the superior plant type and the first plant density threshold, a preset number of supplementary repair schemes are randomly generated, wherein the preset number is 5% of the number of initial repair schemes, and a supplementary repair scheme group is obtained. Then, the inferior repair scheme group is replaced by the supplementary repair scheme group to obtain an updated repair scheme sequence. Further, according to the updated repair scheme sequence, iterative optimization of the repair scheme is performed, that is, in each round of optimization, the inferior repair scheme is replaced by a new supplementary repair scheme, and the fitness of each repair scheme is recalculated, and then the repair schemes are reordered to obtain a new scheme sequence; until the current number of optimizations meets the predetermined number of optimizations, the head repair scheme of the current repair scheme sequence is output as the first adaptive repair scheme, wherein the head repair scheme is the scheme with the highest fitness in the current repair scheme sequence, and the first adaptive repair scheme is obtained. By replacing the inferior repair scheme group with the supplementary repair scheme group, an updated repair scheme sequence is constructed, and iterative optimization is performed. This optimization process enables the repair scheme to continuously improve its fitness in each round, ensuring that the first adaptive repair scheme finally selected can maximize the efficiency and effect of pollution remediation.

[0054] Using the same method as that used to obtain the first adapted remediation solution, several adapted remediation solutions for the several pollution distribution areas are optimized in turn; then the several pollution distribution areas and the several adapted remediation solutions are merged, and during the fusion process, the remediation solutions for different areas are ensured to be compatible. For example, if the same strain or plant is used in multiple areas, the strain density and plant density can be adjusted according to the area and pollution concentration of each area; the remediation resources (such as strains, plants, application time, etc.) are reasonably allocated in different pollution areas to maximize the overall remediation effect; and the optimal remediation solution is obtained, which not only takes into account the specific needs of each area, but also takes into account the resource optimization and coordination of the overall remediation.

[0055] In summary, the method for degrading organic pollutants in garden soil using rhizosphere microbial communities provided in this application has the following technical effects: By taking multi-point samples of the target soil, the distribution of organic pollutants is determined according to the analysis of the multi-point sampling results, wherein the distribution of organic pollutants includes several pollution distribution areas, and each pollution distribution area is marked with a pollutant type and a pollutant concentration; then, the strain parameters of rhizosphere microorganisms are matched according to the pollutant type and the pollutant concentration, and several strain parameter thresholds are determined, wherein the strain parameter threshold includes a strain type threshold, and each strain type is marked with a strain density threshold; on the other hand, the environmental conditions of the area where the target soil is located are obtained, and plant parameters are matched according to the pollutant type, the pollutant concentration and the environmental conditions to determine several planting parameter thresholds, wherein the planting parameter threshold includes a plant type threshold, and each plant type is marked with a plant density threshold; finally, based on several strain type thresholds, several strain density thresholds, several plant type thresholds and several plant density thresholds, the remediation scheme optimization analysis of the several pollution distribution areas is performed, and the optimal remediation scheme is determined to implement the degradation of organic pollutants in the target soil by integration; the above method can improve the intelligence and comprehensiveness of soil remediation retrieval analysis, improve information retrieval efficiency and information matching, achieve the technical goal of quickly and accurately setting soil remediation schemes, and effectively improve soil remediation efficiency and remediation quality.

[0056] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0057] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for degrading organic pollutants in garden soil using rhizosphere microbial communities, characterized in that: include: Taking multi-point samples of the target soil, and determining the distribution of organic pollutants according to the multi-point sampling results, wherein the distribution of organic pollutants includes a plurality of pollution distribution areas, each pollution distribution area is marked with a pollutant type and a pollutant concentration; According to the pollutant type and pollutant concentration, the strain parameters of the rhizosphere microorganisms are matched to determine a plurality of strain parameter thresholds, wherein the strain parameter thresholds include strain type thresholds, and each strain type is identified with a strain density threshold; Acquire the environmental conditions of the area where the target soil is located, match the plant parameters according to the pollutant type, pollutant concentration and environmental conditions, and determine a number of planting parameter thresholds, wherein the planting parameter thresholds include plant type thresholds, and each plant type is identified with a plant density threshold; Based on several strain type thresholds, several strain density thresholds, several plant type thresholds and several plant density thresholds, an optimization analysis of remediation schemes for the several pollution distribution areas is performed, and the optimal remediation scheme is determined to implement the degradation of organic pollutants in the target soil.

2. The method for degrading organic pollutants in garden soil using rhizosphere microbial communities according to claim 1, characterized in that: The distribution of organic pollutants is determined based on the analysis of multi-point sampling results, including: Using gas chromatography-mass spectrometry technology to detect organic matter in multi-point soil sampling, determine multiple sampling pollutant types and multiple sampling pollutant concentrations, and perform pollution diffusion simulation based on the multiple sampling pollutant types and multiple sampling pollutant concentrations to construct an initial pollution distribution map; Dividing the initial pollution distribution map once according to pollutant types to determine a plurality of initial pollution distribution sub-maps, wherein the pollutant type in each initial pollution distribution sub-map is the same; The multiple initial pollution distribution sub-maps are divided twice according to the pollutant concentration to determine a number of pollution distribution areas, and the organic pollutant distribution is constructed based on the number of pollution distribution areas.

3. The method for degrading organic pollutants in garden soil using rhizosphere microbial communities according to claim 2, characterized in that: The multiple initial pollution distribution submaps are divided twice according to the pollutant concentration to determine a number of pollution distribution areas, including: Randomly selecting a first initial pollution distribution sub-map from the multiple initial pollution distribution sub-maps, and obtaining a minimum pollutant concentration in the first initial pollution distribution sub-map; Taking the location of the minimum pollutant concentration as the starting point, simulating watering the first initial pollution distribution submap to determine a first pollutant concentration, wherein the first pollutant concentration is the first pollutant concentration that is submerged by the water surface; Calculating the deviation between the minimum pollutant concentration and the first pollutant concentration to obtain a first concentration deviation; if the first concentration deviation is greater than or equal to a predetermined concentration deviation scalar, setting a first dividing line at the location of the first pollutant concentration, and starting from the first pollutant concentration, continuing to simulate watering until the water surface exceeds the maximum pollutant concentration of the first initial pollution distribution subgraph, then stopping watering to obtain multiple dividing lines; The first initial pollution distribution submap is divided by the multiple dividing lines to obtain multiple pollutant distribution areas, which are added to the multiple pollution distribution areas, wherein the middle value of the pollutant concentration of the pollution distribution area is set as the pollutant concentration corresponding to the distribution area.

4. The method for degrading organic pollutants in garden soil using rhizosphere microbial communities according to claim 3, characterized in that: If the first concentration deviation is less than a predetermined concentration deviation scalar, the simulated flooding is continued until the concentration deviation between the pollutant concentration at the position submerged by the water surface and the minimum pollutant concentration is greater than or equal to the predetermined concentration deviation scalar, and then a first dividing line is set.

5. The method for degrading organic pollutants in garden soil using rhizosphere microbial communities according to claim 1, characterized in that: According to the pollutant type and pollutant concentration, the strain parameters of rhizosphere microorganisms are matched to determine several strain parameter thresholds, including: Randomly selecting a first pollution distribution area from the plurality of pollution distribution areas, and obtaining a first pollutant type and a first pollutant concentration in the first pollution distribution area; Inputting the first pollutant type and the first pollutant concentration into a microbial knowledge reserve for matching, and obtaining a plurality of relevant strain parameters of rhizosphere microorganisms; Extracting high-frequency features from the plurality of related strain parameters to determine a first strain type threshold and a first strain density threshold of the first strain type; The first strain type threshold and the first strain density threshold are used as first strain parameter thresholds and added to the plurality of strain parameter thresholds.

6. The method for degrading organic pollutants in garden soil using rhizosphere microbial communities according to claim 5, characterized in that: The high-frequency feature extraction of the multiple related strain parameters includes: Counting the occurrence frequencies of the same strain type in the multiple related strain parameters to obtain multiple strain types and multiple type frequencies; Screening the multiple type frequencies according to a predetermined frequency threshold, determining multiple high-frequency strain types to construct the first strain type threshold; Minimum density and maximum density are extracted for the multiple strain density sets of the multiple high-frequency strain types to obtain multiple first strain density thresholds.

7. The method for degrading organic pollutants in garden soil using rhizosphere microbial communities according to claim 5, characterized in that: According to the pollutant type, pollutant concentration and environmental conditions, the plant parameters are matched to determine several planting parameter thresholds, including: Inputting the first pollutant type and the first pollutant concentration into a plant knowledge repository for matching, and determining a plurality of relevant plant parameters, wherein the relevant plant parameters include relevant plant types and relevant planting densities, and the relevant plant parameters are identified with relevant environmental conditions; Taking the environmental condition as a reference, performing deviation calculation on a plurality of relevant environmental conditions to determine a plurality of environmental deviation degrees; If the environmental deviation is less than the expected deviation index, the corresponding relevant plant parameters are set as the adapted plant parameters to obtain a plurality of adapted plant parameters; High-frequency features are extracted from the multiple adapted plant parameters to determine a first plant type threshold and a first plant density threshold of the first plant type.

8. The method for degrading organic pollutants in garden soil using rhizosphere microbial communities according to claim 7, characterized in that: Deviation calculations are performed on multiple relevant environmental conditions to determine multiple environmental deviations, including: Randomly selecting a first relevant environmental condition from the plurality of relevant environmental conditions; Based on a plurality of environmental attribute parameters, performing attribute parameter deviation calculation on the environmental condition and the first related environmental condition to determine a plurality of first attribute deviation values; The number of parameters whose first attribute deviation values ​​are greater than the reference attribute deviation value among the plurality of first attribute deviation values ​​is counted, set as a first environmental deviation degree, and added to the plurality of environmental deviation degrees.

9. The method for degrading organic pollutants in garden soil using rhizosphere microbial communities according to claim 8, characterized in that: Based on a number of strain type thresholds, a number of strain density thresholds, a number of plant type thresholds and a number of plant density thresholds, an optimization analysis of the remediation schemes for the several pollution distribution areas is performed, and an optimal remediation scheme is determined by integration, including: Obtaining a first strain type threshold, a first strain density threshold, a first plant type threshold, and a first plant density threshold of the first pollution distribution area, and randomly generating a plurality of initial restoration plans based on the first strain type threshold, the first strain density threshold, the first plant type threshold, and the first plant density threshold; Inputting the multiple initial repair solutions into a resource investment plug-in for cost calculation to determine multiple investment costs; Inputting the first pollutant type, the first pollutant concentration, the environmental conditions and a plurality of initial remediation schemes into a soil degradation predictor to obtain a plurality of predicted removal ratios and a plurality of predicted degradation rates, wherein the soil degradation predictor is a prediction model constructed based on machine learning; Calculating multiple scheme fitnesses of multiple initial remediation schemes according to the multiple input costs, multiple predicted removal ratios, and multiple predicted degradation rates, wherein the scheme fitnesses are negatively correlated with the input costs, and positively correlated with the predicted removal ratios and predicted degradation rates; Based on the fitness of the multiple solutions, a repair solution optimization analysis is performed to output an optimal repair solution.

10. The method for degrading organic pollutants in garden soil using rhizosphere microbial communities according to claim 9, characterized in that: Performing a repair solution optimization analysis based on the fitness of the multiple solutions and outputting an optimal repair solution includes: Based on the fitness of the multiple solutions, the multiple initial repair solutions are arranged in descending order of fitness to construct an initial repair solution sequence, and the first 10% of the initial repair solutions in the initial repair solution sequence are selected as the better repair solutions, and the last 5% of the initial repair solutions in the initial repair solution sequence are selected as the worse repair solutions, to obtain a better repair solution group and a worse repair solution group; Extract high-frequency features of strain types and plant types based on the optimal restoration scheme group to determine optimal strain types and optimal plant types; Randomly generate a preset number of supplementary restoration schemes based on the preferred strain type, the first strain density threshold, the preferred plant type and the first plant density threshold to obtain a supplementary restoration scheme group, wherein the preset number is 5% of the number of initial restoration schemes; The inferior repair solution group is replaced by the supplementary repair solution group to obtain an updated repair solution sequence, and the repair solution is iteratively optimized according to the updated repair solution sequence until a predetermined number of optimizations is met, and the head repair solution of the current repair solution sequence is output as the first adapted repair solution; A plurality of adaptive repair schemes for the plurality of pollution distribution areas are successively optimized, and the optimal repair scheme is generated based on the fusion of the plurality of pollution distribution areas and the plurality of adaptive repair schemes.

Images