Simulation parameter optimization method and system for soil bioremediation process

Abstract

The invention provides a soil bioremediation process simulation parameter optimization method and system, and relates to the technical field of environmental engineering.The method comprises the steps that spatial distribution data of a target remediation area is obtained, the spatial distribution data is converted into a discrete sampling point set, and a virtual datum plane is constructed based on the discrete sampling point set; setting a reference area on the virtual reference plane, processing the discrete sampling point set, identifying clusters with relatively high spatial distribution density in the sampling point set, obtaining a minimum enclosing rectangle of the corresponding cluster by taking a boundary extreme point of each cluster as a basis, and dividing the reference area by taking the minimum enclosing rectangle as an initial structure partition, and obtaining a plurality of structure partitions. Accurate optimization of simulation parameters is achieved, and efficient and reliable parameter support is provided for soil bioremediation engineering.

Description

Technical Field

[0001] This invention relates to the field of environmental engineering technology, and in particular to a method and system for optimizing simulation parameters of soil bioremediation processes. Background Technology

[0002] In soil bioremediation projects for industrial legacy contaminated sites, to avoid cost waste and remediation failure caused by blind construction, the industry generally relies on simulation models to pre-set key parameters (such as microbial inoculation density, soil aeration, and water and fertilizer regulation frequency), and then formulate implementation plans based on the simulation results. However, the current mainstream simulation parameter setting methods are mostly based on the overall environmental data of the target remediation area (such as the average content of soil organic matter and total concentration of pollutants in the whole area), without considering the microenvironmental differentiation formed by differences in soil texture and hydrological conditions within the area.

[0003] For example, in a remediation project of a decommissioned pesticide factory site, the northern part of the site is loam with a shallow water table, while the southern part is sandy loam with a deep water table. Technicians used uniform ventilation and microbial inoculation parameters to simulate the entire area. The results showed that the predicted degradation cycle of pollutants in the southern sandy loam area was shorter. However, in actual construction, the sandy loam's high permeability led to rapid water loss, making it difficult for microorganisms to colonize. The actual degradation cycle far exceeded the simulated value, resulting in a significant decrease in remediation efficiency. The technical defect in this scenario is that the existing simulation parameter optimization method does not adapt to the heterogeneity of the microenvironment in the remediation area. It only covers the entire area with a single parameter set, causing the simulation results to be out of touch with the actual local environmental conditions and failing to provide accurate parameter guidance for different microenvironment areas. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for optimizing simulation parameters of soil bioremediation process, so as to achieve accurate optimization of simulation parameters and provide efficient and reliable parameter support for soil bioremediation engineering.

[0005] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows: In a first aspect, a method for optimizing simulation parameters of a soil bioremediation process, the method comprising: Acquire spatial distribution data of the target repair area, convert the spatial distribution data into a discrete sampling point set, and construct a virtual reference surface based on the discrete sampling point set; A reference region is set on the virtual reference surface. The discrete sampling point set is processed to identify clusters with high spatial distribution density in the sampling point set. The minimum bounding rectangle of the corresponding cluster is obtained based on the boundary extreme point of each cluster. The minimum bounding rectangle is used as the initial structural partition to divide the reference region and obtain multiple structural partitions. The discrete sampling point set is assigned to the corresponding structural partition, and the microenvironment adjustment factor is obtained based on the attribute information of the sampling points in each structural partition. Based on the microenvironment adjustment factor, the boundary range and feature definition of the structural partition are optimized to optimize the microenvironment features, and the optimized structural partition is used as a sub-region with different microenvironment features. Based on the optimized microenvironment characteristics of each sub-region, an initial set of simulation parameters matching the microenvironment characteristics is set for each sub-region. Based on the initial simulation parameter set, the soil bioremediation process of each sub-region was simulated independently to obtain the predicted remediation effect of each sub-region during the simulation period; during the simulation period, the actual feedback data of key indicators affecting microbial activity in each sub-region were monitored and obtained. The actual feedback data is compared with the preset control target of the corresponding sub-region to obtain the comparison result. Based on the comparison result, the sub-regions that have not reached the preset control target are dynamically adjusted to obtain the adjusted simulation parameter set.

[0006] Furthermore, spatial distribution data of the target repair area is acquired, and the spatial distribution data is converted into a discrete sampling point set. A virtual reference surface is constructed based on the discrete sampling point set, including: Receive and store multi-source spatial distribution data of the target restoration area uploaded by remote sensing equipment and on-site sampling equipment; Multi-source spatially distributed data is processed to unify coordinates and standardize format, transforming it into a discrete set of sampling points that contains environmental attribute information corresponding to the spatial locations of all sampling points. Based on a discrete set of sampling points, a virtual reference surface covering the entire target repair area is obtained through spatial interpolation algorithms and gridding processing.

[0007] Furthermore, a reference region is set on the virtual reference surface, and the discrete sampling point set is processed to identify clusters with high spatial distribution density within the sampling point set. The minimum bounding rectangle of each cluster is obtained based on its boundary extreme points. This minimum bounding rectangle is then used as the initial structural partition to divide the reference region, resulting in multiple structural partitions, including: Based on the virtual reference surface, the reference area is determined according to the overall boundary of the target repair area. Spatial density analysis is performed on the discrete sampling point set. Based on the preset density threshold, one or more clusters with high spatial distribution density in the sampling point set are identified. For each identified cluster, calculate the boundary extreme points of all sampling points of the cluster in spatial coordinates; Based on the boundary extreme points, construct a minimum bounding rectangle for each cluster that can completely contain all the sampling points of the cluster. Using the smallest bounding rectangle as the initial structural partition, the baseline region is spatially divided to obtain multiple structural partitions that do not overlap or partially overlap in space.

[0008] Furthermore, the discrete sampling point set is assigned to the corresponding structural partitions, and a microenvironment adjustment factor is obtained based on the attribute information of the sampling points within each structural partition. Based on the microenvironment adjustment factor, the boundary range and feature definition of the structural partitions are optimized for microenvironment characteristics. The optimized structural partitions are then treated as sub-regions with different microenvironment characteristics, including: Each sampling point in the discrete sampling point set is assigned to the corresponding structural partition according to the spatial coordinates of the sampling point and the spatial position relationship between each structural partition; For each structural partition, based on the environmental attribute information of the sampling points assigned to the structural partition, the microenvironment adjustment factor of the structural partition is determined by calculating the statistical characteristic values ​​of the sampling point attribute data; By using microenvironment adjustment factors, the geometric boundary range of the corresponding structural partitions can be optimized by shrinking or expanding, and the microenvironment characteristic type of the partitions can be accurately defined. The structural partitions, after boundary optimization and precise feature definition, are defined as sub-regions with different microenvironmental characteristics.

[0009] Furthermore, based on the optimized microenvironment characteristics of each sub-region, an initial set of simulation parameters matching the microenvironment characteristics is set for each sub-region, including: The optimized microenvironmental characteristics of each sub-region were extracted, and the key characteristic indicators of each sub-region were analyzed based on the pollutant concentration data and soil environmental parameters of the sampling points in each sub-region. Use key feature indicators as query conditions to match the corresponding basic parameter templates from the preset parameter mapping relationship; Based on the basic parameter template and key feature indicators, the simulation parameters of each sub-region are numerically calibrated to obtain an initial simulation parameter set that accurately matches the microenvironment characteristics of each sub-region.

[0010] Furthermore, based on the initial simulation parameter set, the soil bioremediation process in each sub-region was independently simulated to obtain the predicted remediation effect of each sub-region during the simulation period. During the simulation period, actual feedback data of key indicators affecting microbial activity in each sub-region were monitored and acquired, including: Input the initial set of simulation parameters into the soil bioremediation process simulation model, and start independent simulation calculations for each sub-region. Run the simulation calculation until the end of the set simulation period, and output the pollutant concentration change curves of each sub-region during the simulation period and the final remediation effect prediction data; During the simulation period, a sensor network deployed in each sub-region monitors and collects key indicator data affecting microbial activity in real time, including dynamic changes in temperature, humidity, pH value and oxygen concentration, in order to obtain actual feedback data.

[0011] Furthermore, the actual feedback data is compared with the preset control targets for the corresponding sub-regions to obtain the comparison results. Based on the comparison results, dynamic parameter adjustments are made to the sub-regions that have not met the preset control targets, resulting in the adjusted simulation parameter set, including: The actual feedback data is compared and analyzed item by item with the preset control targets of the corresponding sub-regions to obtain the comparison results of the degree of deviation. Based on the comparison results, sub-regions that did not meet the preset control targets were identified, and key control parameters affecting the repair effect were determined. Based on the key control parameters and the degree of deviation, a preset parameter adjustment algorithm is used to dynamically adjust the simulation parameter set of the sub-regions that do not meet the standards, so as to obtain the optimized simulation parameter set.

[0012] Secondly, a soil bioremediation process simulation parameter optimization system includes: The acquisition module is used to acquire spatial distribution data of the target repair area, convert the spatial distribution data into a discrete sampling point set, and construct a virtual reference surface based on the discrete sampling point set. The partitioning module is used to set a reference region on the virtual reference surface, process the discrete sampling point set, identify clusters with high spatial distribution density in the sampling point set, obtain the minimum bounding rectangle of the corresponding cluster based on the boundary extreme point of each cluster, and use the minimum bounding rectangle as the initial structural partition to partition the reference region to obtain multiple structural partitions. The optimization module is used to allocate the discrete sampling point set to the corresponding structural partitions, obtain the microenvironment adjustment factor based on the attribute information of the sampling points in each structural partition, optimize the microenvironment features of the boundary range and feature definition of the structural partitions based on the microenvironment adjustment factor, and use the optimized structural partitions as sub-regions with different microenvironment features. The configuration module is used to set an initial simulation parameter set that matches the microenvironment characteristics of each sub-region based on the optimized microenvironment characteristics of each sub-region. The monitoring module is used to independently simulate the soil bioremediation process in each sub-region based on the initial simulation parameter set, and obtain the predicted remediation effect of each sub-region within the simulation period; during the simulation period, it monitors and obtains the actual feedback data of key indicators affecting microbial activity in each sub-region. The feedback module is used to compare the actual feedback data with the preset control target of the corresponding sub-region, obtain the comparison result, and dynamically adjust the parameters of the sub-region that has not reached the preset control target based on the comparison result, so as to obtain the adjusted simulation parameter set.

[0013] Thirdly, a computing device includes: One or more processors; A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method.

[0014] Fourthly, a computer-readable storage medium storing a program that, when executed by a processor, implements the method.

[0015] The above-described solution of the present invention has at least the following beneficial effects: Because it employs a multi-source data integration to construct a virtual reference surface, clusters structural zones according to sampling point density, and optimizes sub-regions by combining microenvironment adjustment factors—matching exclusive initial simulation parameters to each sub-region, and using a technology that links independent simulation with real-time monitoring feedback for dynamic parameter adjustment—it overcomes the technical problems in traditional soil bioremediation simulations where only uniform parameters are set based on overall regional data, ignoring microenvironmental heterogeneity and leading to a disconnect between simulation results and local reality. This achieves precise adaptation of simulation parameters to the microenvironmental characteristics of each sub-region, improves the accuracy of remediation effect prediction, ensures the timeliness and scientific nature of remediation parameter adjustments, and ultimately achieves the technical effect of improving soil bioremediation efficiency and reducing cost waste and remediation failure risks caused by blind construction. Attached Figure Description

[0016] Figure 1 This is a schematic flowchart of a method for optimizing simulation parameters of a soil bioremediation process, provided by an embodiment of the present invention.

[0017] Figure 2 This is a schematic diagram of a soil bioremediation process simulation parameter optimization system provided by an embodiment of the present invention. Detailed Implementation

[0018] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0019] like Figure 1 As shown in the figure, an embodiment of the present invention proposes a method for optimizing simulation parameters of a soil bioremediation process, the method comprising the following steps: Step 1: Obtain the spatial distribution data of the target repair area, convert the spatial distribution data into a discrete sampling point set, and construct a virtual reference surface based on the discrete sampling point set; Step 2: Set a reference region on the virtual reference surface, process the discrete sampling point set, identify clusters with high spatial distribution density in the sampling point set, obtain the minimum bounding rectangle of the corresponding cluster based on the boundary extreme point of each cluster, and divide the reference region into multiple structural partitions using the minimum bounding rectangle as the initial structural partition. Step 3: Assign the discrete sampling point set to the corresponding structural partitions, and obtain the microenvironment adjustment factor based on the attribute information of the sampling points in each structural partition; optimize the microenvironment features of the boundary range and feature definition of the structural partitions based on the microenvironment adjustment factor, and use the optimized structural partitions as sub-regions with different microenvironment features. Step 4: Based on the optimized microenvironmental characteristics of each sub-region, set an initial simulation parameter set for each sub-region that matches the microenvironmental characteristics. Step 5: Based on the initial simulation parameter set, the soil bioremediation process of each sub-region is simulated independently to obtain the predicted remediation effect of each sub-region during the simulation period; during the simulation period, the actual feedback data of key indicators affecting microbial activity in each sub-region are monitored and obtained. Step 6: Compare the actual feedback data with the preset control target of the corresponding sub-region to obtain the comparison result. Based on the comparison result, dynamically adjust the parameters of the sub-regions that have not reached the preset control target to obtain the adjusted simulation parameter set.

[0020] In this embodiment of the invention, by employing techniques such as acquiring spatial distribution data of the target remediation area and converting it into a discrete set of sampling points to construct a virtual reference surface, identifying clusters based on sampling point density and dividing initial structural partitions, obtaining microenvironmental adjustment factors to optimize sub-regions by combining the attribute information of sampling points within each partition, matching specific initial simulation parameters for each sub-region, and dynamically adjusting parameters of sub-regions that fail to meet standards through independent simulation to obtain predicted results and linked with real-time monitoring feedback data, this invention overcomes the technical problems of traditional soil bioremediation simulation parameter settings, which neglect the heterogeneity of the microenvironment within the region and set uniform parameters based solely on overall data, leading to a disconnect between simulation results and the actual local environment. This achieves precise matching of simulation parameters with the microenvironmental characteristics of each sub-region, improves the accuracy of remediation effect prediction and the targeted nature of parameter adjustments, and ultimately ensures the scientific implementation of soil bioremediation projects, improves remediation efficiency, and reduces cost waste and remediation failure risks caused by blind construction.

[0021] In a preferred embodiment of the present invention, step 1 above may include: Step 1.1: Receive and store multi-source spatial distribution data of the target remediation area uploaded by remote sensing and on-site sampling equipment. Specifically, this includes: First, deploying remote sensing and on-site sampling equipment adapted to industrial legacy contaminated sites. The remote sensing equipment can be a UAV multispectral sensor or satellite remote sensing equipment, used to collect soil texture distribution data, surface vegetation cover data, and approximate spatial distribution range data of pollutants in the target remediation area. The on-site sampling equipment can be a manual soil sampler or an automatic soil columnar sampler, collecting soil samples at different depths according to a preset sampling grid, simultaneously recording the geographical location information of each sampling point, and detecting environmental attribute data such as pollutant concentration, soil organic matter content, soil moisture content, and pH value in the soil samples. Then, all multi-source spatial distribution data collected by the remote sensing and on-site sampling equipment is uploaded to the data processing system via wired or wireless transmission. The data processing system classifies and verifies the received data, confirming its integrity and validity before storing the data in a dedicated spatial database. The spatial database must support the associated storage of geographical location information and environmental attribute data.

[0022] Step 1.2 involves performing coordinate unification and format standardization on the multi-source spatial distribution data. This transforms the multi-source spatial distribution data into a discrete sampling point set containing environmental attribute information corresponding to the spatial locations of all sampling points. Specifically, this includes: first, performing coordinate unification on the stored multi-source spatial distribution data to determine a unified spatial coordinate system applicable to the target restoration area; then, using professional geographic information processing software to convert the image coordinates of remote sensing data and the GPS coordinates of field sampling points to eliminate coordinate deviations when data is collected from different devices, ensuring that the spatial reference benchmark of all data is consistent; and finally, performing format standardization. The image data output by remote sensing equipment may be in TIFF format, and the attribute data recorded by field sampling equipment may be in Excel or CSV format. These different formats of data need to be converted into a unified structured data format. Each data record needs to include spatial location information such as the longitude, latitude, and sampling depth of the sampling point, as well as corresponding environmental attribute information such as pollutant concentration, soil texture type, soil organic matter content, soil moisture content, and pH value. Finally, these are integrated to form a discrete sampling point set containing complete information of all sampling points.

[0023] Step 1.3: Based on the discrete sampling point set, a virtual reference surface covering the entire target remediation area is obtained through spatial interpolation algorithm and gridding processing. Specifically, this includes: based on the obtained discrete sampling point set, data completion is first performed using a spatial interpolation algorithm. Spatial interpolation is a geographic data processing method that utilizes the spatial continuity of environmental attributes to infer the corresponding attribute values ​​of surrounding unsampled areas using accurate data from known sampling points. The core logic is that the closer the known sampling point, the greater its influence on the attribute values ​​of unknown areas. This effectively compensates for the limitation of limited sampling points in actual sampling processes that cannot cover the entire area. Considering the spatial continuity of environmental attributes of industrial legacy contaminated sites, this embodiment uses inverse distance... The weighted interpolation algorithm uses existing environmental attribute data such as pollutant concentration and soil moisture content in a discrete sampling point set as its core basis. It calculates the spatial distance between the unknown location and each known sampling point, assigns a distance weight to each known sampling point, and gives higher weights to sampling points that are closer to the unknown location. The estimated value of the environmental attribute at the unknown location is then obtained by weighted calculation. During the estimation process, the interpolation parameters need to be adjusted in combination with the site's historical pollution situation and soil texture distribution patterns. For example, the weight ratio of nearby sampling points can be appropriately increased for areas near historical pollution sources, and the weight calculation coefficient can be optimized for areas with abrupt changes in soil texture to ensure that the estimation results can truly reflect the spatial variation characteristics of environmental attributes in the region.

[0024] Next, a gridding process is performed. Based on the size of the target remediation area and the accuracy requirements of soil bioremediation, an appropriate grid size is set. For small and medium-sized contaminated sites, a 1m×1m grid is set, and for large sites, a 2m×2m grid is set. The interpolated environmental attribute data is associated with the set grid. Each grid node corresponds to a unique spatial location, identified by the coordinates of the upper left corner or center point of the grid. At the same time, the estimated environmental attribute values ​​for that location, including pollutant concentration and soil moisture content, are also provided. Finally, a virtual reference surface that can completely cover the entire target remediation area and contains both spatial location and environmental attribute information is constructed.

[0025] In this embodiment of the invention, by receiving and storing multi-source spatial distribution data from remote sensing and on-site sampling, and performing coordinate unification and format standardization processing to transform it into a discrete set of sampling points containing the spatial location of sampling points and corresponding environmental attributes, and then constructing a virtual reference surface covering the entire target remediation area through spatial interpolation algorithms and gridding processing, the technical problems of traditional soil bioremediation simulation, such as the chaotic format of multi-source spatial data, inconsistent coordinates, difficulty in effective integration, and lack of data carriers that can completely and accurately reflect the overall environmental characteristics of the area, leading to a weak foundation for simulation analysis, are overcome. This achieves efficient fusion and standardization of multi-source data, resulting in a complete and uniform discrete set of sampling points and a virtual reference surface that fully covers the target area, ultimately providing a precise and reliable data foundation for sub-region division, parameter matching, and simulation analysis.

[0026] In a preferred embodiment of the present invention, step 2 above may include: Step 2.1: Based on the virtual reference surface, determine the reference area according to the overall boundary of the target repair area, perform spatial density analysis on the discrete sampling point set, and identify one or more clusters with high spatial distribution density in the sampling point set based on the preset density threshold. Specifically, this includes: first, retrieving the constructed virtual reference surface, which contains complete spatial coordinates and environmental attribute association data of the target repair area. By comparing the actual boundaries of industrial legacy contaminated sites, including the area of ​​ground-level walls and the boundaries determined by underground pollution diffusion surveys, a reference area is delineated on a virtual reference surface that perfectly matches the actual boundary. This ensures that the zoning does not exceed the actual space required for remediation. Next, the obtained discrete sampling point set is loaded, and spatial density analysis is performed on these sampling points in geographic information processing software. First, a fixed statistical unit area is set, for example, 10 square meters per statistical unit, and the number of sampling points contained in each statistical unit is calculated. Then, a density threshold is preset based on the microenvironmental characteristics of the target remediation area. For example, referring to the sampling distribution patterns of the northern loam area and the southern sandy loam area of ​​the site in the background, the threshold is set to at least 3 sampling points within each 10-square-meter statistical unit. Finally, all statistical units that meet the conditions are selected based on this threshold. The continuous area formed by these units is the cluster with high spatial distribution density. If multiple unconnected high-density statistical unit areas exist within the site, multiple clusters are identified.

[0027] Step 2.2: For each identified cluster, calculate the boundary extreme points of all sampling points in the spatial coordinates of the cluster. Specifically, for each identified cluster, first extract the complete spatial coordinate data of all sampling points within the cluster individually in the data processing system. These coordinates include the longitude, latitude, and vertical sampling depth of the sampling points. Then, calculate the boundary extremes of the extracted coordinate data according to each dimension: In the longitude dimension, compare the longitude values ​​of all sampling points one by one and select the maximum and minimum values; in the latitude dimension, similarly compare the latitude values ​​of all sampling points one by one and select the corresponding maximum and minimum values; in the depth dimension, compare the sampling depth values ​​of all sampling points and select the maximum and minimum depth values. Mark the sampling points corresponding to the maximum and minimum values ​​in each dimension as the boundary extreme points of the cluster. Each cluster will eventually obtain six boundary extreme points in three dimensions: longitude, latitude, and depth. These points together define the spatial range of the cluster.

[0028] Step 2.3: Based on the boundary extreme points, construct a minimum bounding rectangle for each cluster that completely contains all sampling points of the cluster. Specifically, using the six boundary extreme points as the core basis, first construct the planar outline of the rectangle in the planar coordinate system of the virtual reference plane: the extreme points corresponding to the minimum longitude and minimum latitude are the lower left vertices of the rectangle, the extreme points corresponding to the maximum longitude and minimum latitude are the lower right vertices, the extreme points corresponding to the maximum longitude and maximum latitude are the upper right vertices, and the extreme points corresponding to the minimum longitude and maximum latitude are the upper left vertices. Connect these four vertices sequentially to form a planar rectangle. Then, combined with the extreme points of the depth dimension, determine the vertical coverage range of the rectangle, that is, the interval from the minimum depth to the maximum depth. In this way, a spatial rectangle that can cover both the planar range of the cluster and the vertical sampling depth range is constructed, and this rectangle can completely contain all sampling points within the cluster, finally obtaining the minimum bounding rectangle corresponding to each cluster.

[0029] Step 2.4 involves using the minimum bounding rectangle as the initial structural partition to spatially divide the baseline region, resulting in multiple spatially non-overlapping or partially overlapping structural partitions. Specifically, this includes: directly using the minimum bounding rectangle constructed for each cluster as the initial structural partition; spatially dividing the defined baseline region by first superimposing each minimum bounding rectangle onto the baseline region according to its spatial coordinates, assigning a unique partition number to each rectangle, and recording the cluster characteristics corresponding to that partition. If the minimum bounding rectangles of different clusters do not overlap spatially, the resulting initial structural partitions are spatially non-overlapping. If the sampling points of some clusters have overlapping distributions at the boundary of the baseline region, the corresponding minimum bounding rectangles may partially overlap, resulting in partially overlapping initial structural partitions. Ultimately, through this division, multiple initial structural partitions are obtained within the baseline region. These partitions initially correspond to different microenvironmental concentration areas within the site, laying the foundation for optimizing the microenvironmental characteristics of sub-regions.

[0030] In this embodiment of the invention, because a reference region consistent with the overall boundary of the target remediation area is determined based on a virtual reference surface, spatial density analysis is performed on the discrete sampling point set, and clusters with high spatial distribution density are identified based on a preset density threshold. The extreme points of the spatial coordinate boundary of each cluster are calculated, and the minimum bounding rectangle that can completely contain all sampling points of the corresponding cluster is constructed based on the extreme points of the spatial coordinate boundary. This rectangle is then used as the initial structural partition to spatially divide the reference region. Therefore, this invention overcomes the technical problem that traditional soil bioremediation simulation partitioning does not combine the spatial distribution characteristics of sampling points and only roughly divides according to geographical range. This makes it difficult to accurately identify concentrated areas with similar microenvironmental attributes, resulting in a mismatch between the partitioning and the actual microenvironmental distribution and an inability to provide an effective partitioning basis for accurate parameter adaptation. As a result, it achieves accurate identification and reasonable partitioning of similar microenvironmental areas within the target remediation area. The resulting initial structural partitioning can objectively reflect the spatial aggregation characteristics of sampling points, ultimately providing a scientific and accurate partitioning basis for optimizing the microenvironmental characteristics of sub-regions and matching specific simulation parameters.

[0031] In a preferred embodiment of the present invention, step 3 above may include: Step 3.1 assigns each sampling point in the discrete sampling point set to the corresponding structural partition based on the spatial coordinates of the sampling point and its spatial relationship with each structural partition. Specifically, this includes: first, retrieving the spatial coordinate boundary data of all initial structural partitions to clarify the range of each structural partition in longitude, latitude, and depth. Then, extracting the complete spatial coordinates of each sampling point in the discrete sampling point set, including the longitude, latitude, and depth values, and comparing the coordinate data of a single sampling point with the coordinate boundaries of each structural partition to determine if the sampling point is within the spatial range of a certain structural partition. If the longitude and latitude of a sampling point fall within the planar boundary of a structural partition, and the sampling depth is within the depth boundary of that partition, then the sampling point is assigned to that structural partition. If a sampling point's coordinates are close to the boundaries of two structural partitions simultaneously, considering the preliminary environmental characteristics such as soil texture and moisture content, it is assigned to a structural partition with more closely matching attribute characteristics. After comparing all sampling points, the association between each structural partition and its corresponding sampling point set is obtained, ensuring that no sampling points are missed or duplicated.

[0032] Step 3.2: For each structural partition, based on the environmental attribute information of the sampling points assigned to the partition, the microenvironment adjustment factor of the structural partition is determined by calculating the statistical characteristic values ​​of the sampling point attribute data. Specifically, this includes: for each structural partition, first summarizing the environmental attribute information of all sampling points assigned to that partition. This information includes data directly related to microenvironment characteristics such as soil texture type, pollutant concentration, soil moisture content, groundwater level, and pH value. For each environmental attribute data point, a statistical characteristic value is calculated, including the average, maximum, minimum, and standard deviation of that attribute within the partition, with background values... Taking the zoning of pesticide factory decommissioning sites as an example, the northern structural zone needs to focus on calculating the average moisture content of loam and the standard deviation of pollutant concentration, while the southern structural zone needs to focus on calculating the average porosity of sandy loam and the average depth of groundwater. Based on the degree of difference between the statistical characteristic values ​​and the corresponding attribute statistical values ​​of the whole region, the specific value of the microenvironment adjustment factor is determined. When the average pollutant concentration of a certain structural zone is 1.5 times the average value of the whole region and the standard deviation of moisture content is 0.8 times that of the whole region, the microenvironment adjustment factor of the zone is set by taking into account these two differences. The value of the adjustment factor should be able to reflect the microenvironment characteristics of high pollution and stable moisture content of the zone.

[0033] Step 3.3 involves optimizing the geometric boundary range of the corresponding structural partition by shrinking or expanding it using a microenvironment adjustment factor, and precisely defining the microenvironment feature type of the partition. Specifically, this includes: optimizing the geometric boundary of the corresponding structural partition based on the determined microenvironment adjustment factor; if the adjustment factor shows that the microenvironment attributes within a structural partition are highly consistent, and the attributes of adjacent areas outside the boundary differ significantly from those within the partition, then the partition boundary is shrunk inward to eliminate sporadic areas with inconsistent attributes at the boundary; if the adjustment factor indicates that the attribute features within the partition extend to a certain range outside the boundary, and the attributes of adjacent sampling points outside the boundary are highly consistent with those within the partition, then the partition boundary is expanded outward to include these consistent areas within the partition range. Taking the sandy loam soil structure zone in the southern part of the pesticide factory site as an example, if the adjustment factor reflects that the soil texture of some areas outside the boundary is still sandy loam and the groundwater level is also relatively deep, then the boundary of the zone is extended outward to include these areas. The microenvironmental characteristic type is accurately defined by combining the statistical characteristic values ​​within the zone. For example, the northern structural zone is defined as loam-shallow groundwater-medium pollutant concentration zone, and the southern structural zone is defined as sandy loam, deep groundwater level and high pollutant concentration zone, to ensure that the characteristic description of each zone accurately corresponds to the actual environment.

[0034] Step 3.4 defines the structural partitions after boundary optimization and precise feature definition as sub-regions with different microenvironmental characteristics. Specifically, this includes: collecting all structural partition data after boundary optimization and precise feature definition, uniquely identifying each partition, labeling its optimized spatial coordinate boundaries, precise microenvironmental characteristic type, and corresponding statistical characteristic value data, and formally defining these optimized partitions as sub-regions. Each sub-region represents an independent unit with unified and clear microenvironmental characteristics within the target remediation area. For example, the optimized partition in the northern part of the pesticide factory site is defined as sub-region one, with features labeled as loam texture, groundwater level of 0.8 to 1.2 meters, and organophosphorus pesticide concentration of 1.2 to 1.8 mg / kg; the optimized partition in the southern part is defined as sub-region two, with features labeled as sandy loam texture, groundwater level of 3.5 to 4.2 meters, and organophosphorus pesticide concentration of 2.5 to 3.2 mg / kg. Finally, multiple sets of sub-regions with clear and differentiated microenvironmental characteristics are obtained, providing a direct basis for matching specific simulation parameters for each region.

[0035] In this embodiment of the invention, step 3 employs a technique that uses the spatial coordinates of sampling points to accurately allocate sampling points based on their positional relationship with the structural partitions. It determines a microenvironmental adjustment factor based on the statistical characteristic values ​​of the environmental attribute data of the sampling points within the partitions. This factor optimizes the geometric boundaries of the structural partitions and precisely defines their microenvironmental characteristic types. Finally, the optimized partitions are defined as sub-regions with different microenvironmental characteristics. This overcomes the technical problem that initial structural partitions are only divided based on the density clustering of sampling points without precise optimization incorporating microenvironmental attributes, resulting in partition boundaries that do not match the actual microenvironmental distribution and ambiguous feature definitions, thus failing to provide a precise basis for setting differentiated parameters. This achieves a deep match between structural partitions and the actual microenvironmental characteristics of the site, making the microenvironmental attributes of each partition more unified and the boundaries more precise. Ultimately, it achieves the technical effect of providing precise microenvironmental basis for matching exclusive simulation parameters to each sub-region, ensuring the targeted and scientific nature of soil bioremediation simulation parameters.

[0036] In a preferred embodiment of the present invention, step 4 above may include: Step 4.1: Extract the optimized microenvironmental characteristics of each sub-region. Based on the pollutant concentration data and soil environmental parameters of the sampling points in each sub-region, analyze and obtain the key characteristic indicators of each sub-region. Specifically, this includes: first, retrieving the defined data of each sub-region, and extracting the optimized complete microenvironmental characteristics of each sub-region. These characteristics include core information such as clear soil texture type, groundwater level depth, soil moisture content level, and pollutant types. Taking the pesticide factory decommissioning site sub-region in the background as an example, extract the loam texture, shallow groundwater level, medium moisture content, and organophosphorus pesticide pollution characteristics of the northern sub-region, and extract the sandy loam texture, deep groundwater level, low moisture content, and other characteristics of the southern sub-region. The study then focused on the pollutant concentration data and soil environmental parameters of all sampling points in each sub-region, based on the characteristics of similar pesticide pollution. The average, peak, and spatial distribution gradient of the pollutant concentration data were calculated. For the soil environmental parameters, the study focused on the correlation data of soil texture, such as porosity, water retention capacity, and air permeability. Based on these analytical results, key characteristic indicators for each sub-region were determined. For the northern sub-region, key indicators were set as loam, shallow groundwater level, moderate pollutant concentration, and high water retention capacity. For the southern sub-region, key indicators were set as sandy loam, deep groundwater level, high pollutant concentration, strong air permeability, and low water retention capacity. This ensured that the key indicators accurately summarized the core attributes of the sub-region that decisively influenced the remediation parameters.

[0037] Step 4.2: Using key feature indicators as query conditions, the corresponding basic parameter templates are matched from the preset parameter mapping relationships. Specifically, this includes: pre-establishing a parameter mapping relationship database, which is constructed based on a large number of industrial contaminated site remediation engineering case data. The core content is to associate key indicators of different microenvironmental characteristics with the corresponding basic parameter templates for remediation simulation. The basic parameter templates cover the baseline ranges of all core simulation parameters, including microbial inoculation density, soil aeration, water and fertilizer regulation frequency, and nutrient addition ratio. For example, in the template for loam soil with high water retention capacity, the baseline range for aeration parameter is relatively low, while in the template for sandy loam soil with low water retention capacity, the baseline range for water and fertilizer regulation frequency is relatively high. Subsequently, the key feature indicators of each sub-region are used as search conditions and input into the parameter mapping relationship database for matching queries. In the northern sub-region, the search criteria for loam soil with shallow groundwater level, moderate pollutant concentration, and high water retention capacity are used to match basic parameter templates suitable for areas with good water retention and moderate pollutant load. In the southern sub-region, the search criteria for sandy loam soil with deep groundwater level, high pollutant concentration, strong permeability, and low water retention capacity are used to match basic parameter templates suitable for areas with strong permeability, easy water loss, and high pollutant load, ensuring that the basic parameter templates of each sub-region are consistent with the core microenvironment characteristics.

[0038] Step 4.3: Based on the basic parameter template and key feature indicators, numerical calibration is performed on the simulation parameters of each sub-region to obtain an initial simulation parameter set that accurately matches the microenvironmental characteristics of each sub-region. Specifically, for each sub-region, the baseline range of each core parameter in the matched basic parameter template is first determined. The basic template for the northern sub-region includes the baseline for microbial inoculation density, ventilation volume, and water and fertilizer regulation frequency corresponding to its microenvironmental characteristics. The basic template for the southern sub-region includes the baseline for microbial inoculation density, ventilation volume, and water and fertilizer regulation frequency adapted to its sandy loam soil characteristics. The parameters are calibrated in combination with the specific attributes of the key feature indicators. The pollutant concentration in the northern sub-region is slightly higher than the baseline level corresponding to the basic parameter template, so the microbial inoculation density is appropriately increased. At the same time, due to the shallow groundwater level, the ventilation volume is slightly reduced to avoid the soil becoming too wet and affecting the microbial activity. The pollutant concentration in the southern sub-region was significantly higher than the baseline level corresponding to the basic parameter template. The microbial inoculation density was further increased. Considering the rapid water loss of sandy loam, the time interval for water and fertilizer regulation was shortened. The ventilation volume was maintained within the baseline range to ensure the oxygen supply required by the microorganisms. Through such calibration, an initial simulation parameter set exclusive to each sub-region was finally obtained, achieving accurate matching between parameters and microenvironment characteristics.

[0039] In this embodiment of the invention, by employing the technique of extracting optimized microenvironmental characteristics of each sub-region, analyzing key characteristic indicators based on pollutant concentration data and soil environmental parameters of sampling points within the sub-region, matching basic parameter templates from a preset parameter mapping relationship using these indicators as query conditions, and then numerically calibrating the template parameters in conjunction with key characteristic indicators, the technical problem of traditional simulations—which directly use uniform parameters or coarsely matched parameters without customizing parameters based on the precise microenvironmental characteristics of the sub-regions—is overcome. This results in poor adaptability of initial simulation parameters to the local microenvironment and an inability to support accurate simulation. Consequently, the invention achieves precise matching between initial simulation parameters and the microenvironmental characteristics of each sub-region, ensuring that each sub-region receives exclusive and scientific initial parameter support. Ultimately, this improves the accuracy of soil bioremediation process simulation and lays a reliable foundation for dynamic parameter adjustment.

[0040] In a preferred embodiment of the present invention, step 5 above may include: Step 5.1: Input the initial simulation parameter set into the soil bioremediation process simulation model, and start independent simulation calculations for each sub-region. Specifically, this includes: first, organizing the initial simulation parameter set specific to each sub-region, clarifying the complete parameter content such as microbial inoculation density, soil aeration, and water and fertilizer regulation frequency corresponding to each sub-region, ensuring that the parameter sets of the northern loam sub-region and the southern sandy loam sub-region are completely matched with their respective microenvironmental characteristics. Here, independent calculation means that, considering the microenvironmental heterogeneity of different sub-regions, the remediation process simulation of each sub-region is carried out in a dedicated calculation logic and data space. The calculation process, parameter calls, and result generation of each region do not interfere with each other, avoiding parameter cross-influence caused by regional characteristic differences, thereby accurately reflecting the remediation law under different microenvironments. Then, start the soil bioremediation process simulation model. This model needs to support multi-region parallel independent calculation function, be able to open up independent calculation threads and data storage units for the parameter set of each sub-region, and construct calculation scenarios that fit its characteristics. It will not substitute water retention-related parameters of the northern sub-region into the calculation of the southern sub-region, nor will it allow the aeration-related logic of the southern sub-region to interfere with the simulation of the northern sub-region.

[0041] After inputting the initial simulation parameter sets for each sub-region into the model, a calculation module adapted to its high water retention characteristics is configured for the northern loam sub-region. This module focuses on the coupling relationship between water retention and microbial activity. The calculation logic of this module only serves the northern sub-region, and its core is to deduce the microbial colonization and pollutant degradation process based on the characteristic that water is not easily lost in loam. A calculation module adapted to its strong aeration characteristics is configured for the southern sandy loam sub-region. This module focuses on strengthening the logic of the impact of water loss and oxygen supply on the degradation process. When this module runs independently, it only performs calculations based on the characteristics of sandy loam that is highly aerated and poorly water-retaining, and is not constrained by the calculation logic of the northern sub-region. After completing the parameter input and module configuration, the simulation calculation process of each sub-region is started. The model will allocate independent computing resources to each process. The calculation of changes in microbial activity in the northern sub-region and the simulation of water dynamics in the southern sub-region are carried out simultaneously, but the data do not interact with each other, ensuring that the calculation process of each sub-region is completely independent. This fundamentally avoids parameter interference between different sub-regions and makes the simulation results more consistent with the actual remediation scenarios of each region.

[0042] Step 5.2: Run the simulation calculation until the end of the set simulation period, and output the pollutant concentration change curves for each sub-region during the simulation period, as well as the final remediation effect prediction data. Specifically, this includes: setting a reasonable simulation period based on the pollution severity of the target remediation area, the difficulty of pollutant degradation, and the project schedule requirements, ensuring that the period covers the main stages of pollutant degradation while meeting the time planning needs of the project implementation. During the simulation calculation, the calculation progress of each sub-region is monitored in real time to ensure stable model operation and no data anomalies. When the simulation calculation ends at the end of the set period, the model's data output function is triggered. For each sub-region, output the pollutant concentration change curves during the simulation period. The curves should clearly show the dynamic trend of pollutant concentration changes at different time points, such as a steady decrease in concentration in the northern sub-region and a slower initial decrease followed by an accelerated decrease in concentration in the southern sub-region. Simultaneously, output the final remediation effect prediction data, including core indicators such as residual pollutant concentration, degradation rate, and microbial survival rate at the end of the period, providing a clear basis for comparison with actual data.

[0043] Step 5.3: During the simulation period, key indicators affecting microbial activity, including dynamic changes in temperature, humidity, pH, and oxygen concentration, are monitored and collected in real time through a sensor network deployed in each sub-region to obtain actual feedback data. Specifically, this includes: within each defined sub-region, a sensor network is deployed according to the differences in microenvironmental characteristics. In the northern loam sub-region, due to its shallow groundwater level and strong water retention, humidity and pH sensors are evenly distributed in soil layers at different depths, along with temperature and oxygen concentration sensors. In the southern sandy loam sub-region, due to its high permeability and easy water loss, the deployment density of humidity and oxygen concentration sensors is increased to ensure accurate capture of rapid changes in moisture and fluctuations in oxygen concentration. After the sensor deployment is completed, network debugging is performed to ensure that all sensors communicate normally with the data acquisition terminal. During the simulation period, the real-time acquisition frequency of the sensors is set, and the acquisition frequency is appropriately increased for the southern sub-region where the soil environment changes more rapidly. The sensors continuously monitor and collect dynamic changes in temperature, humidity, pH value, and oxygen concentration. This data is transmitted to the data acquisition terminal in real time. The terminal performs preprocessing such as deduplication and noise reduction on the data and removes abnormal data to form a complete actual feedback dataset.

[0044] In this embodiment of the invention, because it employs a technique of inputting the initial simulation parameter set specific to each sub-region into the soil bioremediation process simulation model for independent simulation calculation, and outputting pollutant concentration change curves and remediation effect prediction data after running for a set period, while simultaneously monitoring and collecting dynamic data of key indicators affecting microbial activity such as temperature, humidity, pH, and oxygen concentration in real time through a sensor network deployed in each sub-region to obtain actual feedback, it overcomes the technical problems of traditional simulations that only perform unified calculations across the entire region and lack real-time feedback of actual environmental data, resulting in a disconnect between the prediction results and the actual remediation process in the sub-region, and an inability to timely grasp the dynamic changes of factors affecting microbial activity. Thus, it achieves accurate and independent prediction of the remediation process in each sub-region and real-time capture of the actual environmental state, providing a predictive basis and real data support for subsequent dynamic parameter adjustments, and ultimately achieving the technical effect of ensuring the timeliness of parameter adjustments and improving the consistency between the simulation and actual implementation of the remediation process.

[0045] In a preferred embodiment of the present invention, step 6 above may include: Step 6.1 involves comparing the actual feedback data with the preset control targets for the corresponding sub-regions item by item to obtain the comparison results of the degree of deviation. Specifically, this includes: first, clarifying the preset control targets for each sub-region. These targets need to be formulated in conjunction with the microenvironmental characteristics of the sub-region. The preset control targets for the northern loam sub-region include the temperature range, humidity range, pH range, oxygen concentration level, and pollutant degradation rate baseline for the suitable microbial activity. For the southern sandy loam sub-region, considering its tendency to lose moisture, a slightly higher humidity control limit and a target oxygen concentration that matches strong permeability are set. At the same time, the degradation effect requirements corresponding to the pollutant load in this region are clarified. Then, the actual feedback data of each sub-region is retrieved, and the actual data is compared with the preset control targets for the corresponding sub-regions item by item in the order of temperature, humidity, pH, oxygen concentration, and pollutant degradation progress. For example, the actual soil moisture in the northern sub-region is compared with the preset humidity range, and the actual microbial activity-related indicators in the southern sub-region are compared with the preset standards. The deviation of the actual value of each indicator from the target value is analyzed to determine whether it is a slight deviation, a significant deviation, or a serious deviation. Finally, a comparison result including the deviation of each indicator and the overall degree of deviation is obtained.

[0046] Step 6.2: Based on the comparison results, identify sub-regions that have not met the preset control targets and determine the key control parameters affecting the remediation effect. Specifically, this includes: summarizing the comparison results and screening out sub-regions where some indicators have not met the preset control targets. Considering the characteristics of the pesticide factory decommissioning site in the background, the southern sandy loam sub-region is prone to problems such as actual humidity being lower than the control target and insufficient microbial activity leading to delayed pollutant degradation due to its high permeability and rapid water loss. Therefore, this area is likely to be identified as a sub-region that has not met the target. If the northern loam sub-region has a low actual oxygen concentration, it will also be included in the sub-region that has not met the target. For the identified sub-regions that did not meet the standards, the key control parameters affecting the remediation effect were determined by combining their microenvironmental characteristics and the deviations in the comparison results. For the southern sandy loam sub-region, the actual humidity was much lower than the target and the microbial activity was poor. Considering the poor water retention of sandy loam, the key control parameters were determined to be the frequency of water and fertilizer regulation and soil aeration. The former directly affects soil moisture replenishment, while an excessive amount of the latter will aggravate water loss. For the northern loam sub-region, if the soil is too wet and oxygen is insufficient due to the shallow groundwater level, the key control parameter was determined to be soil aeration.

[0047] Step 6.3: Based on the key control parameters and the degree of deviation, the simulated parameter set of the sub-regions that did not meet the standards is dynamically adjusted using a preset parameter adjustment algorithm to obtain the optimized simulated parameter set. Specifically, the preset parameter adjustment algorithm is a set of targeted parameter optimization logic systems constructed in advance based on a large amount of industrial contaminated site remediation case data, environmental response patterns of different soil textures, and the correlation characteristics between microbial activity and parameters. The preset parameter adjustment algorithm is not a general formula, but rather a set of core rules for the microenvironment of each sub-region. For example, it pre-embeds the matching relationship between the characteristics of sandy loam soil with poor water retention and rapid water loss and the frequency of water and fertilizer regulation, as well as the linkage between the characteristics of loam soil with strong water retention and easy to become hypoxic due to excessive moisture and the ventilation volume. It can directly output the precise adjustment direction according to the type and degree of deviation of key control parameters.

[0048] This algorithm is pre-integrated into the data processing system. The algorithm has separate computational logic modules adapted to northern loam and southern sandy loam, eliminating the need for temporary adjustment rules. For sub-regions that do not meet the standards, the identified key control parameters and their corresponding deviation levels are synchronously input into the pre-set algorithm. Taking the southern sandy loam sub-region as an example, if the key control parameters are water and fertilizer regulation frequency and ventilation, and the deviation level is significantly low humidity, the parameter adjustment algorithm will call its internal module adapted to sandy loam, combining it with pre-stored sandy loam moisture loss rate data to analyze the correlation between humidity deviation and water and fertilizer replenishment intervals, directly calculating the water and fertilizer regulation intervals that need to be shortened. Simultaneously, the parameter adjustment algorithm will also link oxygen concentration... Based on actual feedback data, if the oxygen concentration has reached the preset target, the algorithm, according to the pre-set constraint rule that excessive ventilation in sandy loam soil will exacerbate water loss, suggests maintaining the current ventilation volume or slightly reducing it to avoid causing new environmental imbalances. For the northern loam sub-region, if the key control parameter is ventilation volume and the deviation is a slight decrease in oxygen concentration, the algorithm activates the loam-adapted calculation module. Combining the pre-embedded logic that loam has strong water retention and that significantly increasing ventilation volume can easily lead to a sharp drop in humidity, the algorithm bypasses adjustment methods that may disrupt soil moisture balance and directly calculates the specific direction for slightly increasing ventilation volume. This ensures that while supplementing oxygen, a suitable humidity environment for microbial activity is maintained. Through this dynamic adjustment, the algorithm can accurately correct the parts of the initial simulation parameter set that do not match the real-time microenvironment of the sub-region, ultimately obtaining an optimized simulation parameter set. This ensures that the parameters accurately adapt to the current environmental state of the sub-region that has not met the target, avoiding the repair risks caused by blind adjustments.

[0049] In this embodiment of the invention, by employing a technical approach that compares the actual feedback data of each sub-region with the preset control target item by item to clarify the degree of deviation, identifies the sub-regions that fail to meet the target based on the comparison results and locates the key control parameters affecting the remediation effect, and then dynamically adjusts the simulation parameter group of the sub-regions in combination with the key control parameters and the degree of deviation through a preset algorithm, the invention overcomes the technical problems of traditional simulation parameter settings, such as lack of actual data feedback verification, inability to accurately locate parameter adaptation, and inability to optimize parameters in real time, which leads to the disconnect between simulation parameters and the dynamic microenvironment of the sub-regions and the continued poor remediation effect of the sub-regions. This achieves targeted optimization and dynamic adaptation of simulation parameters, allowing the parameters of the sub-regions to accurately match real-time environmental changes, ultimately improving the controllability of the soil bioremediation process, ensuring stable and satisfactory remediation results, and further reducing remediation costs and failure risks.

[0050] like Figure 2 As shown, embodiments of the present invention also provide a soil bioremediation process simulation parameter optimization system, comprising: The acquisition module is used to acquire spatial distribution data of the target repair area, convert the spatial distribution data into a discrete sampling point set, and construct a virtual reference surface based on the discrete sampling point set. The partitioning module is used to set a reference region on the virtual reference surface, process the discrete sampling point set, identify clusters with high spatial distribution density in the sampling point set, obtain the minimum bounding rectangle of the corresponding cluster based on the boundary extreme point of each cluster, and use the minimum bounding rectangle as the initial structural partition to partition the reference region to obtain multiple structural partitions. The optimization module is used to allocate the discrete sampling point set to the corresponding structural partitions, obtain the microenvironment adjustment factor based on the attribute information of the sampling points in each structural partition, optimize the microenvironment features of the boundary range and feature definition of the structural partitions based on the microenvironment adjustment factor, and use the optimized structural partitions as sub-regions with different microenvironment features. The configuration module is used to set an initial simulation parameter set that matches the microenvironment characteristics of each sub-region based on the optimized microenvironment characteristics of each sub-region. The monitoring module is used to independently simulate the soil bioremediation process in each sub-region based on the initial simulation parameter set, and obtain the predicted remediation effect of each sub-region within the simulation period; during the simulation period, it monitors and obtains the actual feedback data of key indicators affecting microbial activity in each sub-region. The feedback module compares the actual feedback data with the preset control target of the corresponding sub-region to obtain the comparison result. Based on the comparison result, it dynamically adjusts the parameters of the sub-regions that have not reached the preset control target to obtain the adjusted simulation parameter set. The above description is a preferred embodiment of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for optimizing simulation parameters of a soil bioremediation process, characterized in that, The method includes: Acquire spatial distribution data of the target repair area, convert the spatial distribution data into a discrete sampling point set, and construct a virtual reference surface based on the discrete sampling point set; A reference region is set on the virtual reference surface. The discrete sampling point set is processed to identify clusters with high spatial distribution density in the sampling point set. The minimum bounding rectangle of the corresponding cluster is obtained based on the boundary extreme point of each cluster. The minimum bounding rectangle is used as the initial structural partition to divide the reference region and obtain multiple structural partitions. The discrete sampling point set is assigned to the corresponding structural partition, and the microenvironment adjustment factor is obtained based on the attribute information of the sampling points in each structural partition. Based on the microenvironment adjustment factor, the boundary range and feature definition of the structural partition are optimized to optimize the microenvironment features, and the optimized structural partition is used as a sub-region with different microenvironment features. Based on the optimized microenvironment characteristics of each sub-region, an initial set of simulation parameters matching the microenvironment characteristics is set for each sub-region. Based on the initial simulation parameter set, the soil bioremediation process of each sub-region was simulated independently to obtain the predicted remediation effect of each sub-region during the simulation period; during the simulation period, the actual feedback data of key indicators affecting microbial activity in each sub-region were monitored and obtained. The actual feedback data is compared with the preset control target of the corresponding sub-region to obtain the comparison result. Based on the comparison result, the sub-regions that have not reached the preset control target are dynamically adjusted to obtain the adjusted simulation parameter set.

2. The method for optimizing simulation parameters of soil bioremediation process according to claim 1, characterized in that, Acquire spatial distribution data of the target repair area, convert the spatial distribution data into a discrete sampling point set, and construct a virtual reference surface based on the discrete sampling point set, including: Receive and store multi-source spatial distribution data of the target restoration area uploaded by remote sensing equipment and on-site sampling equipment; Multi-source spatially distributed data is processed to unify coordinates and standardize format, transforming it into a discrete set of sampling points that contains environmental attribute information corresponding to the spatial locations of all sampling points. Based on a discrete set of sampling points, a virtual reference surface covering the entire target repair area is obtained through spatial interpolation algorithms and gridding processing.

3. The method for optimizing simulation parameters of soil bioremediation process according to claim 2, characterized in that, A reference region is defined on the virtual reference surface. The discrete sampling point set is processed to identify clusters with high spatial distribution density within the sampling point set. Based on the boundary extreme points of each cluster, the minimum bounding rectangle of the corresponding cluster is obtained. The minimum bounding rectangle is used as the initial structural partition to divide the reference region, resulting in multiple structural partitions, including: Based on the virtual reference surface, the reference area is determined according to the overall boundary of the target repair area. Spatial density analysis is performed on the discrete sampling point set. Based on the preset density threshold, one or more clusters with high spatial distribution density in the sampling point set are identified. For each identified cluster, calculate the boundary extreme points of all sampling points of the cluster in spatial coordinates; Based on the boundary extreme points, construct a minimum bounding rectangle for each cluster that can completely contain all the sampling points of the cluster. Using the smallest bounding rectangle as the initial structural partition, the baseline region is spatially divided to obtain multiple structural partitions that do not overlap or partially overlap in space.

4. The method for optimizing simulation parameters of soil bioremediation process according to claim 3, characterized in that, The discrete sampling point set is assigned to the corresponding structural partition, and the microenvironment adjustment factor is obtained based on the attribute information of the sampling points in each structural partition. Microenvironment characteristics are optimized based on the boundary range and feature definition of structural partitions using microenvironment adjustment factors. The optimized structural partitions are then treated as sub-regions with different microenvironment characteristics, including: Each sampling point in the discrete sampling point set is assigned to the corresponding structural partition according to the spatial coordinates of the sampling point and the spatial position relationship between each structural partition; For each structural partition, based on the environmental attribute information of the sampling points assigned to the structural partition, the microenvironment adjustment factor of the structural partition is determined by calculating the statistical characteristic values ​​of the sampling point attribute data; By using microenvironment adjustment factors, the geometric boundary range of the corresponding structural partitions can be optimized by shrinking or expanding, and the microenvironment characteristic type of the partitions can be accurately defined. The structural partitions, after boundary optimization and precise feature definition, are defined as sub-regions with different microenvironmental characteristics.

5. The method for optimizing simulation parameters of soil bioremediation process according to claim 4, characterized in that, Based on the optimized microenvironment characteristics of each sub-region, an initial set of simulation parameters matching the microenvironment characteristics is set for each sub-region, including: The optimized microenvironmental characteristics of each sub-region were extracted, and the key characteristic indicators of each sub-region were analyzed based on the pollutant concentration data and soil environmental parameters of the sampling points in each sub-region. Use key feature indicators as query conditions to match the corresponding basic parameter templates from the preset parameter mapping relationship; Based on the basic parameter template and key feature indicators, the simulation parameters of each sub-region are numerically calibrated to obtain an initial simulation parameter set that accurately matches the microenvironment characteristics of each sub-region.

6. The method for optimizing simulation parameters of soil bioremediation process according to claim 5, characterized in that, Based on the initial simulation parameter set, the soil bioremediation process in each sub-region was independently simulated to obtain the predicted remediation effect of each sub-region during the simulation period. During the simulation period, actual feedback data of key indicators affecting microbial activity in each sub-region were monitored and acquired, including: Input the initial set of simulation parameters into the soil bioremediation process simulation model, and start independent simulation calculations for each sub-region. Run the simulation calculation until the end of the set simulation period, and output the pollutant concentration change curves of each sub-region during the simulation period and the final remediation effect prediction data; During the simulation period, a sensor network deployed in each sub-region monitors and collects key indicator data affecting microbial activity in real time, including dynamic changes in temperature, humidity, pH value and oxygen concentration, in order to obtain actual feedback data.

7. The method for optimizing simulation parameters of soil bioremediation process according to claim 6, characterized in that, The actual feedback data is compared with the preset control target of the corresponding sub-region to obtain the comparison result. Based on the comparison result, the sub-regions that have not met the preset control target are dynamically adjusted to obtain the adjusted simulation parameter set, including: The actual feedback data is compared and analyzed item by item with the preset control targets of the corresponding sub-regions to obtain the comparison results of the degree of deviation. Based on the comparison results, sub-regions that did not meet the preset control targets were identified, and key control parameters affecting the repair effect were determined. Based on the key control parameters and the degree of deviation, a preset parameter adjustment algorithm is used to dynamically adjust the simulation parameter set of the sub-regions that do not meet the standards, so as to obtain the optimized simulation parameter set.

8. A soil bioremediation process simulation parameter optimization system, wherein the system implements the method as described in any one of claims 1 to 7, characterized in that, include: The acquisition module is used to acquire spatial distribution data of the target repair area, convert the spatial distribution data into a discrete sampling point set, and construct a virtual reference surface based on the discrete sampling point set. The partitioning module is used to set a reference region on the virtual reference surface, process the discrete sampling point set, identify clusters with high spatial distribution density in the sampling point set, obtain the minimum bounding rectangle of the corresponding cluster based on the boundary extreme point of each cluster, and use the minimum bounding rectangle as the initial structural partition to partition the reference region to obtain multiple structural partitions. The optimization module is used to allocate the discrete sampling point set to the corresponding structural partitions and obtain the microenvironment adjustment factor based on the attribute information of the sampling points in each structural partition. Based on the microenvironment adjustment factor, the boundary range and feature definition of the structural partition are optimized to improve the microenvironment characteristics. The optimized structural partition is then used as a sub-region with different microenvironment characteristics. The configuration module is used to set an initial simulation parameter set that matches the microenvironment characteristics of each sub-region based on the optimized microenvironment characteristics of each sub-region. The monitoring module is used to independently simulate the soil bioremediation process in each sub-region based on the initial simulation parameter set, and obtain the predicted remediation effect of each sub-region within the simulation period; during the simulation period, it monitors and obtains the actual feedback data of key indicators affecting microbial activity in each sub-region. The feedback module is used to compare the actual feedback data with the preset control target of the corresponding sub-region, obtain the comparison result, and dynamically adjust the parameters of the sub-region that has not reached the preset control target based on the comparison result, so as to obtain the adjusted simulation parameter set.

9. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images