Micro-plastic treatment method for soil remediation

Abstract

The invention discloses a micro-plastic treatment method for soil remediation, and particularly relates to the field of micro-plastic treatment, which comprises the following steps: collecting a soil sample in a target treatment area, separating micro-plastic, identifying the type and content of the plastic, and constructing a soil micro-plastic pollution distribution model. The method comprises the following steps: carrying out a flora mixed degradation test on a micro-plastic sample, establishing a time sequence degradation sequence, screening stage experiment items with the highest degradation efficiency, detecting metabolic intermediates, and integrating experiment environment parameters and flora matching data. And carrying out degradation stage marking on the degradation experiment data set through a deep neural network algorithm, establishing a degradation stage identification model and optimizing parameters. By constructing a degradation stage recognition model, the optimal flora ratio of each stage is accurately screened, so that different enzyme systems play a synergistic role in degradation of a plastic main chain, intermediate product conversion, final mineralization and other key degradation stages, and the degradation time is effectively shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of microplastic management, and more specifically, to a microplastic management method for soil remediation. Background Art

[0002] Microplastic pollution has become a major threat in the soil environment. It is widely present in farmland, wetlands, industrial sites and other areas, causing significant impacts on soil ecological functions and microbial community structure, and endangering human health through the food chain. Traditional physical and chemical remediation methods have problems of high cost, low efficiency and secondary pollution. Therefore, bioremediation technology with microbial degradation as the core has gradually become a research focus. Microplastic degradation is a complex multi-stage process that requires the synergistic effect of multiple microbial flora. Due to differences in chemical structure and molecular weight, different types of plastics (such as PET, PE, PP, etc.) have different degradation pathways and intermediates, requiring specific bacterial communities to secrete enzyme systems for cleavage and transformation. Degradation is usually divided into at least three (or more) stages: main chain cleavage, intermediate product transformation and final mineralization. The optimal bacterial community ratio at different stages is crucial to improving degradation efficiency.

[0003] Therefore, how to combine experimental data with deep learning models to establish a soil microplastic management solution that can identify different degradation stages and output the optimal bacterial community ratio scheme, dynamically adjust the bacterial community ratio according to time to adapt to actual soil conditions and microplastic characteristics, thereby improving management efficiency and eco-friendliness, is an urgent problem that needs to be solved.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a microplastic management method for soil remediation to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: S1: Collect soil samples in the target treatment area, separate microplastic samples from the soil samples and calculate the content of microplastic samples, determine the chemical composition of microplastic samples to identify the types of plastics in microplastic samples; S2: Integrate the coordinate information of the sampling points, the types of microplastics, and the microplastic content of the sampling points, and use geographic information system technology to construct a soil microplastic pollution distribution model; S3: Divide the microplastic sample into a set number of test samples, conduct mixed degradation tests on the microbial flora selected for degradation treatment of the test samples, and establish a time-series degradation sequence of different mixed ratios of microbial flora; S4: Convert the time-series degradation sequence into an alignment sequence based on the degradation stage, select the experimental items with the least time steps in each degradation stage, and detect the metabolic intermediates of the experimental items in the degradation stage; S5: Conduct synchronous replication experiments on each experimental culture system, and integrate the environmental parameters of all experimental culture systems, as well as the corresponding degradation stages, optimal microbial flora mixing ratios, and metabolic intermediates into a degradation experimental data set; S6: Perform data preprocessing on the degradation experiment data set, label the degradation stages of the preprocessed data, use the deep neural network algorithm to establish a degradation stage recognition model and adjust the model parameters; S7: Based on the microplastic pollution area in the soil microplastic pollution distribution model, collect soil environmental parameters in the polluted area and information on metabolic intermediates produced by microorganisms, input them into the degradation stage identification model, adjust the proportion of the microbial flora to be released based on the optimal mixed proportion of the microbial flora corresponding to the degradation stage output by the model identification, and release the adjusted microbial flora into the corresponding pollution area.

[0007] In a preferred embodiment, in S1, soil samples are collected in the set target treatment area, microplastic samples in the soil samples are separated and the content of the microplastic samples is calculated, and the chemical composition of the microplastic samples is determined to identify the type of plastic in the microplastic samples, which specifically includes: According to the geographic information of the target treatment area, soil samples containing microplastics are collected through a set gradient grid distribution, and the coordinates of the sampling locations are recorded; The microplastics were separated from the soil samples by saturated salt solution flotation method, and the microplastic samples in the flotation layer were separated by a low-pore size filtration membrane. The mass ratio of the microplastic samples to the soil samples was calculated as the microplastic content of the soil sample. Use Fourier transform infrared spectroscopy to analyze the molecular structure and characteristic groups of microplastics, qualitatively mark the main chemical components, and determine the type of plastic in the microplastic samples based on the chemical composition.

[0008] In a preferred embodiment, in S2, the coordinate information of the sampling points, the type of microplastics and the microplastic content of the sampling points are integrated, and a soil microplastic pollution distribution model is constructed in combination with geographic information system technology.

[0009] In a preferred embodiment, in S3, the microplastic sample is divided into a set number of test samples, and a mixed degradation test is performed on the test samples using a microbial flora selected for degradation treatment. The establishment of a time-series degradation sequence of different microbial flora mixing ratios specifically includes: The microplastic samples separated from all sampling points are concentrated, evenly mixed and divided into a set number of test samples. Based on the types of plastics in the microplastic samples, the microbial flora used for degradation treatment is selected for mixed degradation testing; Construct multiple experimental culture systems, each with different environmental parameters, including soil temperature, humidity and pH value; The microplastic test samples were mixed with microbial flora in different proportions for group degradation experiments, with each mixing ratio corresponding to one experimental item; The mass of the microplastic test samples in the group degradation experiment was measured according to the set reaction time step, the mass change values ​​of the microplastic samples in time sequence were obtained, the degradation amount of the microplastics was calculated based on the mass change, and a time-series degradation sequence of different mixed ratios of microbial flora was established.

[0010] In a preferred embodiment, in S4, the time-series degradation sequence is converted into an alignment sequence based on the degradation stage, and the experimental items with the least number of time steps used in each degradation stage process are screened out. The metabolic intermediates of the experimental items in the degradation stage are specifically detected, including: Transform the temporal degradation sequence from alignment with set reaction time steps to alignment with degradation stages based on set degradation amount gradients; In the group degradation experiment of the experimental culture system, the number of time steps spanned by each experimental item in the same degradation stage is counted, and the experimental item with the least time steps used in each degradation stage process is screened out, and the experimental microbial flora mixing ratio corresponding to the experimental item is marked as the optimal ratio of the stage; Liquid chromatography-mass spectrometry was used to analyze the information on metabolic intermediates produced by microorganisms in each degradation stage of the experimental items, and the types and concentrations of metabolic intermediates were recorded.

[0011] In a preferred embodiment, in S5, a synchronous replication experiment is performed on each experimental culture system, and the environmental parameters of all experimental culture systems, as well as the corresponding degradation stages, optimal microbial flora mixing ratios, and metabolic intermediates are integrated into a degradation experimental data set, specifically including: Conduct synchronous replication experiments for each experimental culture system and extract the experimental items with the shortest number of time steps used in each degradation stage in the degradation experiment grouping; The optimal ratio of the experimental items in each degradation stage is obtained, and combined with the type and concentration data of the metabolic intermediates produced, the joint data of degradation stage-optimal microbial flora mixing ratio-metabolic intermediates of different experimental culture systems are established and marked as the degradation experimental data set.

[0012] In a preferred embodiment, in S6, data preprocessing is performed on the degradation experiment data set, and degradation stage marking is performed on the preprocessed data. A degradation stage recognition model is established using a deep neural network algorithm and model parameter adjustment is performed, specifically including: The degradation experiment data set was preprocessed, and the outlier detection method was used to remove noise from the multidimensional data in the degradation experiment data set. The value range of all data was adjusted to a unified scale through the data standardization method. The pre-treated degradation experimental data are labeled according to the degradation stage to which they belong, and the environmental parameters and metabolic intermediate product parameters are used as input, and the labeled degradation stage and the optimal microbial flora mixing ratio corresponding to the stage are used as output to establish the training data set and the verification data set; Establish a degradation stage recognition model based on a deep neural network algorithm and configure the model initialization parameters; The labeled degradation experimental data set is input into the initialization model, and the association pattern of environmental parameters, metabolic intermediate product parameters and degradation stage identification results is preliminarily trained through supervised learning methods. The optimization objective function is set to adjust the internal parameters of the model to fit the nonlinear relationship between metabolic intermediate products and degradation stages under different environmental parameters. The validation set data is input into the initially trained model, and the accuracy, recall, and F1 score indicators of the model on the validation data segmentation are calculated using the cross-validation method. The hyperparameters of the model are adjusted in combination with grid search until the model recognition accuracy reaches the set indicators.

[0013] In a preferred embodiment, in S7, based on the microplastic pollution area in the soil microplastic pollution distribution model, soil environmental parameters of the polluted area and information on metabolic intermediates produced by microorganisms are collected, and the degradation stage identification model is input, and the microbial flora to be released is adjusted based on the optimal microbial flora mixed ratio corresponding to the degradation stage output by the model identification, and the microbial flora after the adjusted ratio is released to the corresponding pollution area specifically includes: The areas where the microplastic content in the soil microplastic pollution distribution model exceeds the set pollution content threshold are marked as microplastic pollution areas. For each pollution area, soil environmental parameters and information on metabolic intermediates produced by microorganisms are collected at time intervals corresponding to the set reaction time step; Input environmental parameters and metabolic intermediate product information into the degradation stage identification model to identify the degradation stage of microplastic pollution in each polluted area and the corresponding optimal microbial flora mixing ratio; The microbial flora to be released is adjusted according to the optimal mixing ratio of the microbial flora, and the adjusted microbial flora is released into the corresponding microplastic contaminated area.

[0014] Technical effects and advantages of a microplastic management method for soil remediation of the present invention: Soil samples were collected in the target treatment area to separate microplastics and identify the types and contents of plastics, and a soil microplastic pollution distribution model was constructed. Microplastic samples were subjected to mixed degradation tests by bacterial communities, a time-series degradation sequence was established, and the phased experimental items with the highest degradation efficiency were screened. Metabolic intermediates were detected and experimental environmental parameters and bacterial community ratio data were integrated. The degradation experimental data set was marked with degradation stages using a deep neural network algorithm, and a degradation stage identification model was established and parameters were optimized. By constructing a degradation stage identification model, the optimal bacterial community ratio for each stage was accurately screened, so that different enzyme systems can work synergistically in degrading the main chain of plastics, intermediate product conversion, final mineralization, and other key degradation stages, effectively reducing the degradation time. In addition, based on the soil pollution distribution model and the deep learning model, the bacterial community ratio is dynamically adjusted in real time according to soil environmental parameters to ensure that the bacterial community activity can adapt to complex and changeable soil conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of the process of a microplastic management method for soil remediation according to the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Embodiment 1, Figure 1 The present invention provides a microplastic management method for soil remediation, which comprises the following steps: S1: Collect soil samples in the target treatment area, separate microplastic samples from the soil samples and calculate the content of microplastic samples, determine the chemical composition of microplastic samples to identify the types of plastics in microplastic samples; S2: Integrate the coordinate information of the sampling points, the types of microplastics, and the microplastic content of the sampling points, and use geographic information system technology to construct a soil microplastic pollution distribution model; S3: Divide the microplastic sample into a set number of test samples, conduct mixed degradation tests on the microbial flora selected for degradation treatment of the test samples, and establish a time-series degradation sequence of different mixed ratios of microbial flora; S4: Convert the time-series degradation sequence into an alignment sequence based on the degradation stage, select the experimental items with the least time steps in each degradation stage, and detect the metabolic intermediates of the experimental items in the degradation stage; S5: Conduct synchronous replication experiments on each experimental culture system, and integrate the environmental parameters of all experimental culture systems, as well as the corresponding degradation stages, optimal microbial flora mixing ratios, and metabolic intermediates into a degradation experimental data set; S6: Perform data preprocessing on the degradation experiment data set, label the degradation stages of the preprocessed data, use the deep neural network algorithm to establish a degradation stage recognition model and adjust the model parameters; S7: Based on the microplastic pollution area in the soil microplastic pollution distribution model, collect soil environmental parameters in the polluted area and information on metabolic intermediates produced by microorganisms, input them into the degradation stage identification model, adjust the proportion of the microbial flora to be released based on the optimal mixed proportion of the microbial flora corresponding to the degradation stage output by the model identification, and release the adjusted microbial flora into the corresponding pollution area.

[0018] In S1, soil samples are collected in the target treatment area, microplastic samples in the soil samples are separated and the content of microplastic samples is calculated, and the chemical composition of the microplastic samples is determined to identify the types of plastics in the microplastic samples.

[0019] In the target governance area, the spatial gradient grid is set through the geographic information system (GIS) to select the multi-point sampling area. Standard sampling tools (such as ground drills) are used to collect soil samples from the surface layer 0-20 cm and the deep layer 20-50 cm. The mass of soil samples collected at each sampling point is 500 g, and the geographic coordinates (latitude and longitude) and environmental parameters of each sampling point, including soil moisture, pH value and temperature, are recorded.

[0020] The collected soil samples were air-dried (about 48 hours) and sieved with a 2 mm pore size sieve to remove large particles of impurities. 100 g of dry soil sample was weighed and placed in a beaker, 300 mL of saturated sodium chloride solution was added, and a magnetic stirrer was used to stir at 400 rpm for 10 minutes and then allowed to stand for 30 minutes. The microplastic particles in the flotation layer were separated from the sediment by density difference, and the upper flotation liquid was filtered through a 0.22 μm low-pore size filter membrane to collect the microplastic particles on the filter membrane, and the filter membrane was rinsed with deionized water to remove salt. After drying the filter membrane, it was weighed to obtain the mass of the separated microplastic sample, and the ratio of the microplastic mass to the initial soil mass was calculated as the microplastic content of the soil sample.

[0021] The separated microplastic particles were transferred to the Fourier transform infrared spectroscopy (FTIR) sample stage with tweezers and scanned in ATR (attenuated total reflection) mode, with the wavelength range set to 4000-600 cm⁻¹, the scanning resolution to 4 cm⁻¹, and the number of scans to 64 times. The absorption peaks unique to plastics in the obtained spectrum were analyzed, the bands corresponding to the characteristic groups (such as CH, C=O, CO, etc.) were calibrated, and the chemical composition of microplastics was qualitatively identified in combination with the reference spectral library. According to the identification results, the microplastic samples were classified into main types such as polyethylene (PE), polypropylene (PP), polyethylene terephthalate (PET) or polystyrene (PS).

[0022] In S2, the coordinate information of the sampling points, the types of microplastics, and the microplastic content at the sampling points are integrated, and the soil microplastic pollution distribution model is constructed in combination with geographic information system technology.

[0023] According to the microplastic type data of each sampling point, the sampling points are classified by plastic type (such as PE, PP, PET) to generate multiple type distribution layers. A spatial interpolation algorithm is applied to each layer to generate distribution heat maps of different plastic types, showing the spatial distribution characteristics of various types of microplastics.

[0024] Integrate the distribution layers of each type of plastic and the pollution gradient grid to build a comprehensive pollution distribution model for the target area. Visually display the scope and degree of pollution areas through classification (such as low pollution, medium pollution, and high pollution areas). Superimpose soil environmental parameters (such as humidity and pH value) into the pollution distribution model to analyze the impact of environmental conditions on the distribution of microplastic pollution.

[0025] In S3, the microplastic samples are divided into a set number of test samples, and the microbial flora selected for degradation treatment of the test samples is subjected to a mixed degradation test to establish a time-series degradation sequence of different mixed ratios of microbial flora.

[0026] The microplastic samples separated from all sampling points in the target treatment area were collected and concentrated, and evenly mixed using a homogenizer to ensure the uniformity of the sample source. The mixed samples were weighed and divided into 1,000 groups of test samples of equal mass, each group weighing 1 g, to ensure that the type and content of plastic in each test sample were consistent with the distribution of the original sample.

[0027] In order to test the effects of different environmental conditions on the degradation of microplastics, 10 experimental culture systems were established. The environmental parameters (temperature, humidity, pH value) of each culture system were set to different gradients in sequence, with a temperature range of 15°C, 25°C, and 35°C, a humidity range of 30%, 50%, and 70%, and a pH range of 5, 7, and 9. A simulated soil matrix was introduced into each system to ensure that the physical and chemical properties were consistent with the actual soil environment.

[0028] Select microbial flora A, B and C that are known to be able to degrade microplastics, mix them in different proportions (such as 3:1:1, 1:2:2, etc.), design 100 groups of different flora mixing ratios, and inoculate each flora with the test sample at a solid-liquid ratio of 1:10 (w / v). Add 100 groups of test samples and 100 groups of flora mixtures to each culture system to ensure that each flora ratio corresponds to an experimental item.

[0029] The reaction time step was set to 48 hours (flexibly set according to the type of microplastics, up to 30 days), and samples were collected at 48 hours, 96 hours...48N hours (N is the set number of monitoring times), and the microplastic samples were taken out and separated by filtration. The separated microplastic samples were dried and weighed, and the residual mass value of the samples was recorded.

[0030] According to the degradation data of each experimental culture system and bacterial community mixing ratio, the degradation trend of microplastic samples at different time steps was sorted out. For each bacterial community mixing ratio, a curve of degradation over time was drawn to establish a time-series degradation sequence, and the degradation efficiency, bacterial community activity and corresponding environmental parameters of each stage were marked to form a complete experimental data set.

[0031] In S4, the temporal degradation sequence is converted into an alignment sequence based on the degradation stage, the experimental items with the least number of time steps used in each degradation stage are screened out, and the metabolic intermediates of the experimental items in the degradation stage are detected.

[0032] The time-series degradation sequence of each bacterial community mix ratio in the experimental culture system is divided into five degradation stages according to the microplastic degradation gradient (such as 10%, 30%, 50%, 70%, and 90% of the initial mass). The time step data of each group of experiments is aligned with the corresponding degradation gradient to determine the number of time steps spanned by each experimental item in each degradation stage. A phased degradation sequence based on the degradation gradient is formed to replace the original time step sequence.

[0033] Count the time steps of all experimental items in the same degradation stage, and select the experimental item that takes the least time to complete the stage. Record the bacterial flora mixture ratio of the experimental item and mark it as the optimal ratio of the degradation stage. Organize the screening results into a table corresponding to the degradation stage and the optimal ratio to ensure that each stage corresponds to a unique bacterial flora ratio.

[0034] The culture fluid of the optimal experimental item in the screened stage was centrifuged (4000 rpm, 10 minutes), and the supernatant was analyzed by liquid chromatography-mass spectrometry (LC-MS). The types of metabolic intermediates and their peak areas in each degradation stage were recorded, and the relative concentrations were calculated and correlated with the bacterial flora ratio after normalization. The main metabolites (such as phenols, aldehydes or organic acids) were marked and their concentration change trends were statistically analyzed.

[0035] In S5, synchronous replication experiments were performed on each experimental culture system, and the environmental parameters of all experimental culture systems, as well as the corresponding degradation stages, optimal microbial flora mixing ratios, and metabolic intermediates were integrated into a degradation experimental data set.

[0036] Synchronous replication experiments were performed on each experimental culture system (i.e., experiments on 100 groups of test samples and 100 groups of bacterial mixtures were performed simultaneously), and the experimental items with the shortest number of time steps used in each degradation stage in the degradation experiment grouping were extracted.

[0037] The optimal ratio of the experimental items in each degradation stage is obtained, and combined with the type and concentration data of the metabolic intermediates produced, the joint data of degradation stage-optimal microbial flora mixing ratio-metabolic intermediates of different experimental culture systems are established and marked as degradation experimental data sets. The data fields of the degradation experimental data sets include: degradation stage, optimal flora ratio, metabolic intermediate information, and experimental culture conditions.

[0038] In S6, the degradation experiment data set is preprocessed, and the degradation stage is marked on the preprocessed data. A degradation stage recognition model is established using a deep neural network algorithm and the model parameters are adjusted.

[0039] The degradation experimental data set was cleaned and standardized in multiple dimensions. First, the outlier detection method (such as the triple standard deviation method or the IQR method) was used to identify and remove abnormal data in environmental parameters (such as temperature, humidity, pH value) and metabolic intermediate parameters (such as concentration and type) to eliminate noise interference. Subsequently, the normalization method was used to adjust all data to the range of [0,1] to ensure the consistency of the data value range and improve the convergence speed and accuracy of model training.

[0040] According to the degradation stage classification information in the degradation experiment data set (such as 10%, 30%, 50%, 70%, 90% degradation gradient), the degradation stage of the preprocessed data was marked. Environmental parameters and metabolic intermediate product parameters were used as input features of the model, and the degradation stage label and the optimal bacterial community mixing ratio of the corresponding stage were used as output results. The data was randomly divided into a training set (80%) and a validation set (20%) to ensure balanced data distribution in each degradation stage.

[0041] A degradation stage recognition model was constructed based on a deep neural network algorithm. The model includes: an input layer (accepting environmental parameters and metabolic intermediate product parameters), a hidden layer (setting 3 hidden layers, each containing 128, 64 and 32 neurons, and the activation function is ReLU), and an output layer (outputting the degradation stage classification results, using the Softmax function to achieve multi-classification).

[0042] The Xavier initialization method is used to initialize the model parameters (such as weights and bias values), the optimization objective function is set to the cross entropy loss function, and the Adam optimizer is used as the optimization algorithm.

[0043] The labeled training set data was input into the initialization model, and preliminary training was performed using supervised learning methods. During the training process, environmental parameters and metabolic intermediate parameters were used as input, and degradation stage labels were used as target outputs. The model adjusted internal parameters by calculating the loss (cross entropy) between the predicted value and the target value. The learning rate was set to 0.001, the batch size was 64, and the training iteration was 50 epochs. The model fits the nonlinear relationship between metabolic intermediates and degradation stages under different environmental parameters.

[0044] Input the validation set data into the preliminarily trained model, and use the cross-validation method to calculate the performance indicators of the model on the validation data, including accuracy, recall, and F1 score. Combine the grid search method to optimize the model hyperparameters (such as learning rate, number of hidden layer nodes, batch size, etc.). Gradually adjust the parameters until the accuracy of the model on the validation set reaches the set target (such as ≥95%), and ensure that the F1 score is high (such as ≥0.9) to improve the stability and accuracy of the classification results.

[0045] In S7, based on the microplastic pollution area in the soil microplastic pollution distribution model, the soil environmental parameters of the polluted area and the information on metabolic intermediates produced by microorganisms are collected and input into the degradation stage identification model. The microbial flora to be released is adjusted based on the optimal mixed ratio of the microbial flora corresponding to the degradation stage output by the model identification, and the microbial flora with the adjusted ratio is released to the corresponding pollution area.

[0046] According to the soil microplastic pollution distribution model, the microplastic content data in the polluted area was extracted. A pollution content threshold (such as ≥0.5%) was set, and the areas exceeding the threshold were marked as microplastic pollution areas.

[0047] In each marked contaminated area, multiple interval sampling was performed according to the set reaction time step. When collecting samples, standard soil sampling tools were used to obtain surface (0-20 cm) and deep (20-50 cm) soil samples. Soil environmental parameters were measured and recorded, including temperature (using soil temperature probe, accuracy ±0.1°C), humidity (gravimetric determination, accuracy ±1%), and pH value (potential method, accuracy ±0.01). At the same time, the sample supernatant was analyzed by liquid chromatography-mass spectrometry (LC-MS) to analyze the information of microbial metabolic intermediates, and the main metabolite types and concentration changes were recorded.

[0048] The collected soil environmental parameters and metabolic intermediate product information are input into the degradation stage identification model. Based on the input data, the model outputs the microplastic degradation stage corresponding to each contaminated area and extracts the optimal microbial flora mixing ratio for that stage. The model output results include the degradation stage classification results, flora mixing ratio recommendations (such as flora A:B:C = 2:1:1), and the dynamic degradation stage distribution of the contaminated area is marked.

[0049] According to the optimal flora mix ratio output by the model, the adjusted microbial flora combination is prepared in the laboratory. The flora is cultured to the target concentration (e.g., the flora density is 10 6 CFU / mL), mixed according to the set ratio, and transferred to a controllable delivery carrier (such as slow-release particles or liquid spraying device). Before delivery, reasonable delivery points and delivery amounts are designed according to the distribution characteristics of the contaminated area (area, soil permeability) to ensure that the bacterial community is evenly distributed in the contaminated area. The slow-release carrier technology is used to control the active release rate of the bacterial community to adapt to the degradation needs of the contaminated area. After the bacterial community is delivered, soil samples in the contaminated area are recollected according to the set time step to monitor environmental parameters and metabolic intermediate information. The monitoring data is input into the degradation stage identification model to track the degradation effect of the bacterial community in real time. If it is found that the degradation efficiency decreases or the stage conversion is not up to standard, the bacterial community ratio is adjusted or the bacterial community delivery is supplemented in combination with the model recommendations to ensure the continuity and efficiency of the degradation process.

[0050] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0051] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0052] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0053] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0054] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0055] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0056] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0057] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0058] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0059] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for treating microplastics for soil remediation, characterized in that: The steps include: S1: Collect soil samples in the target treatment area, separate microplastic samples from the soil samples and calculate the content of microplastic samples, determine the chemical composition of microplastic samples to identify the types of plastics in microplastic samples; S2: Integrate the coordinate information of the sampling points, the types of microplastics, and the microplastic content of the sampling points, and use geographic information system technology to construct a soil microplastic pollution distribution model; S3: Divide the microplastic sample into a set number of test samples, conduct mixed degradation tests on the microbial flora selected for degradation treatment of the test samples, and establish a time-series degradation sequence of different mixed ratios of microbial flora; S4: Convert the time-series degradation sequence into an alignment sequence based on the degradation stage, select the experimental items with the least time steps in each degradation stage, and detect the metabolic intermediates of the experimental items in the degradation stage; S5: Conduct synchronous replication experiments on each experimental culture system, and integrate the environmental parameters of all experimental culture systems, as well as the corresponding degradation stages, optimal microbial flora mixing ratios, and metabolic intermediates into a degradation experimental data set; S6: Perform data preprocessing on the degradation experiment data set, label the degradation stages of the preprocessed data, use the deep neural network algorithm to establish a degradation stage recognition model and adjust the model parameters; S7: Based on the microplastic pollution area in the soil microplastic pollution distribution model, collect soil environmental parameters in the polluted area and information on metabolic intermediates produced by microorganisms, input them into the degradation stage identification model, adjust the proportion of the microbial flora to be released based on the optimal mixed proportion of the microbial flora corresponding to the degradation stage output by the model identification, and release the adjusted microbial flora into the corresponding pollution area.

2. A method for treating microplastics for soil remediation according to claim 1, characterized in that: In S1, soil samples are collected in the target treatment area, microplastic samples in the soil samples are separated and the content of microplastic samples is calculated, and the chemical composition of microplastic samples is determined to identify the types of plastics in microplastic samples. Specifically, the following are included: According to the geographic information of the target treatment area, soil samples containing microplastics are collected through a set gradient grid distribution, and the coordinates of the sampling locations are recorded; The microplastics were separated from the soil samples by saturated salt solution flotation method, and the microplastic samples in the flotation layer were separated by a low-pore size filtration membrane. The mass ratio of the microplastic samples to the soil samples was calculated as the microplastic content of the soil sample. Use Fourier transform infrared spectroscopy to analyze the molecular structure and characteristic groups of microplastics, qualitatively mark the main chemical components, and determine the type of plastic in the microplastic samples based on the chemical composition.

3. A method for treating microplastics for soil remediation according to claim 2, characterized in that: In S2, the coordinate information of the sampling points, the types of microplastics, and the microplastic content at the sampling points are integrated, and the soil microplastic pollution distribution model is constructed in combination with geographic information system technology.

4. A method for treating microplastics for soil remediation according to claim 3, characterized in that: In S3, the microplastic samples are divided into a set number of test samples, and a mixed degradation test is performed on the test samples using the microbial flora selected for degradation treatment. The time-series degradation sequence of different mixed proportions of microbial flora is established, specifically including: The microplastic samples separated from all sampling points are concentrated, evenly mixed and divided into a set number of test samples. Based on the types of plastics in the microplastic samples, the microbial flora used for degradation treatment is selected for mixed degradation testing; Construct multiple experimental culture systems, each with different environmental parameters, including soil temperature, humidity and pH value; The microplastic test samples were mixed with microbial flora in different proportions for group degradation experiments, with each mixing ratio corresponding to one experimental item; The mass of the microplastic test samples in the group degradation experiment was measured according to the set reaction time step, the mass change values ​​of the microplastic samples in time sequence were obtained, the degradation amount of the microplastics was calculated based on the mass change, and a time-series degradation sequence of different mixed ratios of microbial flora was established.

5. A method for treating microplastics for soil remediation according to claim 4, characterized in that: In S4, the time-series degradation sequence is converted into an alignment sequence based on the degradation stage, and the experimental items with the least time steps used in each degradation stage are screened out. The metabolic intermediates of the experimental items in the degradation stage are specifically detected, including: Transform the temporal degradation sequence from alignment with set reaction time steps to alignment with degradation stages based on set degradation amount gradients; In the group degradation experiment of the experimental culture system, the number of time steps spanned by each experimental item in the same degradation stage is counted, and the experimental item with the least time steps used in each degradation stage process is screened out, and the experimental microbial flora mixing ratio corresponding to the experimental item is marked as the optimal ratio of the stage; Liquid chromatography-mass spectrometry was used to analyze the information on metabolic intermediates produced by microorganisms in each degradation stage of the experimental items, and the types and concentrations of metabolic intermediates were recorded.

6. A method for treating microplastics for soil remediation according to claim 5, characterized in that: In S5, a synchronous replication experiment is performed on each experimental culture system, and the environmental parameters of all experimental culture systems, as well as the corresponding degradation stages, optimal microbial flora mixing ratios, and metabolic intermediates are integrated into a degradation experimental data set, specifically including: Conduct synchronous replication experiments for each experimental culture system and extract the experimental items with the shortest number of time steps used in each degradation stage in the degradation experiment grouping; The optimal ratio of the experimental items in each degradation stage is obtained, and combined with the type and concentration data of the metabolic intermediates produced, the joint data of degradation stage-optimal microbial flora mixing ratio-metabolic intermediates of different experimental culture systems are established and marked as the degradation experimental data set.

7. A method for treating microplastics for soil remediation according to claim 6, characterized in that: In S6, the degradation experiment data set is preprocessed, and the degradation stage is marked on the preprocessed data. A degradation stage recognition model is established using a deep neural network algorithm and model parameter adjustment is performed, including: The degradation experiment data set was preprocessed, and the outlier detection method was used to remove noise from the multidimensional data in the degradation experiment data set. The value range of all data was adjusted to a unified scale through the data standardization method. The pre-treated degradation experimental data are labeled according to the degradation stage to which they belong, and the environmental parameters and metabolic intermediate product parameters are used as input, and the labeled degradation stage and the optimal microbial flora mixing ratio corresponding to the stage are used as output to establish the training data set and the verification data set; Establish a degradation stage recognition model based on a deep neural network algorithm and configure the model initialization parameters; The labeled degradation experimental data set is input into the initialization model, and the association pattern of environmental parameters, metabolic intermediate product parameters and degradation stage identification results is preliminarily trained through supervised learning methods. The optimization objective function is set to adjust the internal parameters of the model to fit the nonlinear relationship between metabolic intermediate products and degradation stages under different environmental parameters. The validation set data is input into the initially trained model, and the accuracy, recall, and F1 score indicators of the model on the validation data segmentation are calculated using the cross-validation method. The hyperparameters of the model are adjusted in combination with grid search until the model recognition accuracy reaches the set indicators.

8. A method for treating microplastics for soil remediation according to claim 7, characterized in that: In S7, based on the microplastic pollution area in the soil microplastic pollution distribution model, soil environmental parameters of the pollution area and information on metabolic intermediates produced by microorganisms are collected, and input into the degradation stage identification model. Based on the optimal microbial flora mixed ratio corresponding to the degradation stage output by the model identification, the proportion of the microbial flora to be released is adjusted, and the microbial flora with the adjusted proportion is released to the corresponding pollution area, specifically including: The areas where the microplastic content in the soil microplastic pollution distribution model exceeds the set pollution content threshold are marked as microplastic pollution areas. For each pollution area, soil environmental parameters and information on metabolic intermediates produced by microorganisms are collected at time intervals corresponding to the set reaction time step; Input environmental parameters and metabolic intermediate product information into the degradation stage identification model to identify the degradation stage of microplastic pollution in each polluted area and the corresponding optimal microbial flora mixing ratio; The microbial flora to be released is adjusted according to the optimal mixing ratio of the microbial flora, and the adjusted microbial flora is released into the corresponding microplastic contaminated area.

Images