技术领域Technical Field
本发明涉及数据处理领域，特别涉及一种用于土壤生态环境修复的数据处理方法及系统。The present invention relates to the field of data processing, and in particular to a data processing method and system for soil ecological environment restoration.
背景技术Background Art
土壤是地球生态系统的一个重要组成部分，其质量和生态环境状态对农业、生态保护和人类健康具有重要影响。然而，现代农业、工业和城市化进程导致土壤受到各种污染，包括化学物质和重金属的积累，以及土壤肥力和微生物多样性的损害。土壤生态环境修复是指利用物理、化学和生物的方法，转移、吸收、降解和转化土壤中的污染物，使其浓度降低到可接受水平，或将有毒有害的污染物转化为无害的物质。其目的在于阻断污染物进入食物链，防止对人体健康造成危害，同时促进土地资源的保护与可持续发展。Soil is an important part of the earth's ecosystem, and its quality and ecological environment have a significant impact on agriculture, ecological protection and human health. However, modern agriculture, industry and urbanization have led to various soil pollution, including the accumulation of chemicals and heavy metals, as well as damage to soil fertility and microbial diversity. Soil ecological environment restoration refers to the use of physical, chemical and biological methods to transfer, absorb, degrade and transform pollutants in the soil to reduce their concentration to an acceptable level, or to transform toxic and harmful pollutants into harmless substances. Its purpose is to block pollutants from entering the food chain, prevent harm to human health, and promote the protection and sustainable development of land resources.
现有技术中，土壤修复方法可以依靠人工经验，应用具体的修复技术和修复装置针对一块或多块土地进行不同程度的改良，但缺乏通用性的操作方案；由于没有统一的数据处理方法及系统作为支撑，修复方法的设定、实施和效果评估等等都在低效的水平下运行，并且成本高昂。In the existing technology, soil remediation methods can rely on manual experience and apply specific remediation techniques and remediation devices to improve one or more pieces of land to varying degrees, but there is a lack of universal operating plans; due to the lack of unified data processing methods and systems as support, the setting, implementation and effect evaluation of remediation methods are all operated at an inefficient level and are costly.
因此，需要提供一种用于土壤生态环境修复的数据处理方法及系统，用于提高土壤生态环境修复的质量。Therefore, it is necessary to provide a data processing method and system for soil ecological environment restoration to improve the quality of soil ecological environment restoration.
发明内容Summary of the invention
本发明提供一种用于土壤生态环境修复的数据处理系统，包括：土壤检测模块，用于获取待修复区域的多维土壤检测信息，其中，所述多维土壤检测信息至少包括多个位置的不同深度的无机污染物检测信息、有机污染物检测信息及土壤理化性质信息；特征提取模块，用于基于待修复区域的多维土壤检测信息，提取所述待修复区域的土壤污染物扩散特征；图谱建立模块，用于建立第一知识图谱、第二知识图谱和第三知识图谱，其中，所述第一知识图谱用于记载污染物与化学修复试剂之间的关联关系，所述第二知识图谱用于记载污染物与微生物之间的关联关系，所述第三知识图谱用于记载化学修复试剂与微生物之间的关联关系；方案生成模块，用于基于所述待修复区域的多维土壤检测信息、土壤污染物扩散特征、第一知识图谱、第二知识图谱和第三知识图谱，生成所述待修复区域的土壤修复方案；修复检测模块，用于获取在土壤修复过程中获取所述待修复区域的实时多维土壤修复信息，并基于所述待修复区域的实时多维土壤修复信息进行修复实时监测。The present invention provides a data processing system for soil ecological environment restoration, comprising: a soil detection module, used to obtain multidimensional soil detection information of an area to be restored, wherein the multidimensional soil detection information at least includes inorganic pollutant detection information, organic pollutant detection information and soil physical and chemical property information at different depths of multiple positions; a feature extraction module, used to extract soil pollutant diffusion characteristics of the area to be restored based on the multidimensional soil detection information of the area to be restored; a graph establishment module, used to establish a first knowledge graph, a second knowledge graph and a third knowledge graph, wherein the first knowledge graph is used to record the association relationship between pollutants and chemical restoration agents, the second knowledge graph is used to record the association relationship between pollutants and microorganisms, and the third knowledge graph is used to record the association relationship between chemical restoration agents and microorganisms; a scheme generation module, used to generate a soil restoration scheme for the area to be restored based on the multidimensional soil detection information of the area to be restored, the soil pollutant diffusion characteristics, the first knowledge graph, the second knowledge graph and the third knowledge graph; a restoration detection module, used to obtain real-time multidimensional soil restoration information of the area to be restored during the soil restoration process, and perform restoration real-time monitoring based on the real-time multidimensional soil restoration information of the area to be restored.
进一步地，所述土壤检测模块获取待修复区域的多维土壤检测信息，包括：将所述待修复区域分为多个子区域，基于所述多个子区域确定多个初始检测位置；获取每个所述初始检测位置的测试用多维土壤检测信息；基于每个所述初始检测位置的测试用多维土壤检测信息，确定所述待修复区域的多维土壤检测信息离散参数，基于所述待修复区域的多维土壤检测信息离散参数，确定所述待修复区域的多个目标检测位置；基于所述待修复区域的多个目标检测位置，获取所述待修复区域的多维土壤检测信息。Furthermore, the soil detection module obtains multidimensional soil detection information of the area to be repaired, including: dividing the area to be repaired into multiple sub-areas, and determining multiple initial detection positions based on the multiple sub-areas; obtaining multidimensional soil detection information for testing at each of the initial detection positions; determining discrete parameters of the multidimensional soil detection information of the area to be repaired based on the multidimensional soil detection information for testing at each of the initial detection positions, and determining multiple target detection positions of the area to be repaired based on the discrete parameters of the multidimensional soil detection information of the area to be repaired; and obtaining multidimensional soil detection information of the area to be repaired based on the multiple target detection positions of the area to be repaired.
进一步地，所述土壤检测模块基于每个所述初始检测位置的测试用多维土壤检测信息，确定所述待修复区域的多维土壤检测信息离散参数，基于所述待修复区域的多维土壤检测信息离散参数，确定所述待修复区域的多个目标检测位置，包括：基于每个所述初始检测位置的测试用多维土壤检测信息，确定所述待修复区域的无机污染物离散参数和有机污染物离散参数；基于所述待修复区域的无机污染物离散参数和有机污染物离散参数，判断是否新增检测位置；当判定新增检测位置时，基于每个所述初始检测位置的测试用多维土壤检测信息，对所述多个子区域进行聚类，确定多个聚类区域；对于每个所述聚类区域，基于所述聚类区域包括的每个所述初始检测位置的测试用多维土壤检测信息，判断所述聚类区域是否为目标聚类区域；对于每个所述目标聚类区域，基于所述聚类区域包括的每个所述初始检测位置的测试用多维土壤检测信息，确定所述目标聚类区域的检测位置密度，基于所述检测位置密度，确定所述目标聚类区域的多个目标检测位置。Further, the soil detection module determines the discrete parameters of the multidimensional soil detection information of the area to be repaired based on the multidimensional soil detection information for testing of each of the initial detection positions, and determines multiple target detection positions of the area to be repaired based on the discrete parameters of the multidimensional soil detection information of the area to be repaired, including: determining the discrete parameters of inorganic pollutants and the discrete parameters of organic pollutants in the area to be repaired based on the multidimensional soil detection information for testing of each of the initial detection positions; judging whether to add a new detection position based on the discrete parameters of inorganic pollutants and the discrete parameters of organic pollutants in the area to be repaired; when it is determined that a new detection position is added, clustering the multiple sub-areas based on the multidimensional soil detection information for testing of each of the initial detection positions to determine multiple clustering areas; for each of the clustering areas, judging whether the clustering area is a target clustering area based on the multidimensional soil detection information for testing of each of the initial detection positions included in the clustering area; for each of the target clustering areas, determining the detection position density of the target clustering area based on the multidimensional soil detection information for testing of each of the initial detection positions included in the clustering area, and determining multiple target detection positions of the target clustering area based on the detection position density.
进一步地，所述特征提取模块基于待修复区域的多维土壤检测信息，提取所述待修复区域的土壤污染物扩散特征，包括：对于每个所述目标检测位置，基于待修复区域的多维土壤检测信息，生成所述目标检测位置的不同深度的无机污染变化曲线及有机污染变化曲线，对所述不同深度的无机污染变化曲线及有机污染变化曲线进行内涵模态分解，生成所述不同深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及所述不同深度的有机污染变化曲线对应的有机污染分量和有机污染残差；对于任意两个所述目标检测位置，基于两个所述目标检测位置的不同深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及所述不同深度的有机污染变化曲线对应的有机污染分量和有机污染残差，确定两个所述目标检测位置的水平扩散关联参数和垂直扩散关联参数，其中，所述待修复区域的土壤污染物扩散特征包括任意两个所述目标检测位置的水平扩散关联参数和垂直扩散关联参数。Furthermore, the feature extraction module extracts the soil pollutant diffusion characteristics of the area to be repaired based on the multidimensional soil detection information of the area to be repaired, including: for each of the target detection positions, based on the multidimensional soil detection information of the area to be repaired, generating the inorganic pollution change curve and the organic pollution change curve of different depths of the target detection position, performing intrinsic modal decomposition on the inorganic pollution change curve and the organic pollution change curve of different depths, and generating the inorganic pollution components and inorganic pollution residuals corresponding to the inorganic pollution change curves of different depths and the organic pollution components and organic pollution residuals corresponding to the organic pollution change curves of different depths; for any two of the target detection positions, based on the inorganic pollution components and inorganic pollution residuals corresponding to the inorganic pollution change curves of different depths of the two target detection positions and the organic pollution components and organic pollution residuals corresponding to the organic pollution change curves of different depths, determining the horizontal diffusion association parameters and vertical diffusion association parameters of the two target detection positions, wherein the soil pollutant diffusion characteristics of the area to be repaired include the horizontal diffusion association parameters and vertical diffusion association parameters of any two of the target detection positions.
进一步地，所述特征提取模块基于两个所述目标检测位置的不同深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及所述不同深度的有机污染变化曲线对应的有机污染分量和有机污染残差，确定两个所述目标检测位置的水平扩散关联参数，包括：对于每个所述深度，基于两个所述目标检测位置在所述深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及有机污染变化曲线对应的有机污染分量和有机污染残差，确定两个所述目标检测位置对应所述深度的单平面水平扩散关联参数；基于两个所述目标检测位置对应每个所述深度的单平面水平扩散关联参数，确定两个所述目标检测位置的水平扩散关联参数。Further, the feature extraction module determines the horizontal diffusion association parameters of the two target detection positions based on the inorganic pollution components and inorganic pollution residuals corresponding to the inorganic pollution change curves at different depths of the two target detection positions and the organic pollution components and organic pollution residuals corresponding to the organic pollution change curves at different depths, including: for each depth, determining the single-plane horizontal diffusion association parameters of the two target detection positions corresponding to the depth based on the inorganic pollution components and inorganic pollution residuals corresponding to the inorganic pollution change curves of the two target detection positions at the depth and the organic pollution components and organic pollution residuals corresponding to the organic pollution change curves; determining the horizontal diffusion association parameters of the two target detection positions based on the single-plane horizontal diffusion association parameters of the two target detection positions corresponding to each depth.
进一步地，所述特征提取模块基于两个所述目标检测位置的不同深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及所述不同深度的有机污染变化曲线对应的有机污染分量和有机污染残差，确定两个所述目标检测位置的垂直扩散关联参数，包括：对于每个所述目标检测位置，基于所述目标检测位置的不同深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及所述不同深度的有机污染变化曲线对应的有机污染分量和有机污染残差，确定所述目标检测位置的垂直扩散参数；基于两个所述目标检测位置对应的垂直扩散参数，确定两个所述目标检测位置的垂直扩散关联参数。Further, the feature extraction module determines the vertical diffusion association parameters of the two target detection positions based on the inorganic pollution components and inorganic pollution residuals corresponding to the inorganic pollution change curves at different depths of the two target detection positions and the organic pollution components and organic pollution residuals corresponding to the organic pollution change curves at different depths, including: for each target detection position, determining the vertical diffusion parameters of the target detection position based on the inorganic pollution components and inorganic pollution residuals corresponding to the inorganic pollution change curves at different depths of the target detection position and the organic pollution components and organic pollution residuals corresponding to the organic pollution change curves at different depths; determining the vertical diffusion association parameters of the two target detection positions based on the vertical diffusion parameters corresponding to the two target detection positions.
进一步地，所述方案生成模块基于所述待修复区域的多维土壤检测信息、土壤污染物扩散特征、第一知识图谱、第二知识图谱和第三知识图谱，生成所述待修复区域的土壤修复方案，包括：建立样本数据库，其中，所述样本数据库用于存储多个样本土壤的多维土壤检测信息、土壤污染物扩散特征及土壤修复方案；基于所述待修复区域的多维土壤检测信息及土壤污染物扩散特征，从所述多个样本土壤中确定目标样本土壤；通过方案生成模型基于所述目标样本土壤的土壤修复方案、所述待修复区域的多维土壤检测信息、土壤污染物扩散特征、第一知识图谱、第二知识图谱和第三知识图谱，生成所述待修复区域的土壤修复方案。Furthermore, the solution generation module generates a soil remediation solution for the area to be remediated based on the multidimensional soil detection information, soil pollutant diffusion characteristics, the first knowledge graph, the second knowledge graph and the third knowledge graph of the area to be remediated, including: establishing a sample database, wherein the sample database is used to store multidimensional soil detection information, soil pollutant diffusion characteristics and soil remediation solutions of multiple sample soils; determining a target sample soil from the multiple sample soils based on the multidimensional soil detection information and soil pollutant diffusion characteristics of the area to be remediated; and generating a soil remediation solution for the area to be remediated based on the soil remediation solution of the target sample soil, the multidimensional soil detection information, soil pollutant diffusion characteristics, the first knowledge graph, the second knowledge graph and the third knowledge graph of the area to be remediated through a solution generation model.
进一步地，所述修复检测模块基于所述待修复区域的实时多维土壤修复信息进行修复实时监测，包括：基于所述待修复区域的多维土壤检测信息、土壤污染物扩散特征和所述待修复区域的土壤修复方案，预测所述待修复区域在修复过程中的多个修复时间点的预测多维土壤修复信息；基于所述待修复区域的实时多维土壤修复信息和预测多维土壤修复信息，对所述土壤修复方案进行实时调整。Furthermore, the remediation detection module performs real-time monitoring of remediation based on the real-time multidimensional soil remediation information of the area to be remediated, including: predicting the predicted multidimensional soil remediation information of the area to be remediated at multiple remediation time points during the remediation process based on the multidimensional soil detection information of the area to be remediated, the diffusion characteristics of soil pollutants and the soil remediation plan of the area to be remediated; and adjusting the soil remediation plan in real time based on the real-time multidimensional soil remediation information and the predicted multidimensional soil remediation information of the area to be remediated.
进一步地，所述修复检测模块基于所述待修复区域的实时多维土壤修复信息和预测多维土壤修复信息，对所述土壤修复方案进行实时调整，包括：基于所述待修复区域的实时多维土壤修复信息和预测多维土壤修复信息，计算修复偏离参数；根据所述修复偏离参数判断是否对所述土壤修复方案进行实时调整。Furthermore, the remediation detection module adjusts the soil remediation scheme in real time based on the real-time multidimensional soil remediation information and the predicted multidimensional soil remediation information of the area to be remediated, including: calculating remediation deviation parameters based on the real-time multidimensional soil remediation information and the predicted multidimensional soil remediation information of the area to be remediated; and determining whether to adjust the soil remediation scheme in real time according to the remediation deviation parameters.
本发明提供一种用于土壤生态环境修复的数据处理方法，包括：获取待修复区域的多维土壤检测信息，其中，所述多维土壤检测信息至少包括多个位置的不同深度的无机污染物检测信息、有机污染物检测信息及土壤理化性质信息；基于待修复区域的多维土壤检测信息，提取所述待修复区域的土壤污染物扩散特征；建立第一知识图谱、第二知识图谱和第三知识图谱，其中，所述第一知识图谱用于记载污染物与化学修复试剂之间的关联关系，所述第二知识图谱用于记载污染物与微生物之间的关联关系，所述第三知识图谱用于记载化学修复试剂与微生物之间的关联关系；基于所述待修复区域的多维土壤检测信息、土壤污染物扩散特征、第一知识图谱、第二知识图谱和第三知识图谱，生成所述待修复区域的土壤修复方案；获取在土壤修复过程中获取所述待修复区域的实时多维土壤修复信息；基于所述待修复区域的实时多维土壤修复信息进行修复实时监测。The present invention provides a data processing method for soil ecological environment restoration, comprising: obtaining multidimensional soil detection information of an area to be restored, wherein the multidimensional soil detection information at least includes inorganic pollutant detection information, organic pollutant detection information and soil physical and chemical property information at different depths of multiple locations; extracting soil pollutant diffusion characteristics of the area to be restored based on the multidimensional soil detection information of the area to be restored; establishing a first knowledge graph, a second knowledge graph and a third knowledge graph, wherein the first knowledge graph is used to record the association relationship between pollutants and chemical restoration agents, the second knowledge graph is used to record the association relationship between pollutants and microorganisms, and the third knowledge graph is used to record the association relationship between chemical restoration agents and microorganisms; generating a soil restoration plan for the area to be restored based on the multidimensional soil detection information of the area to be restored, the soil pollutant diffusion characteristics, the first knowledge graph, the second knowledge graph and the third knowledge graph; obtaining real-time multidimensional soil restoration information of the area to be restored during the soil restoration process; and performing real-time restoration monitoring based on the real-time multidimensional soil restoration information of the area to be restored.
相比于现有技术，本发明提供的一种用于土壤生态环境修复的数据处理方法及系统，至少具备以下有益效果：Compared with the prior art, the data processing method and system for soil ecological environment restoration provided by the present invention have at least the following beneficial effects:
1、获取待修复区域的多维土壤检测信息，可以精确识别污染物的种类、浓度和分布，从而针对性地选择和使用化学修复试剂和微生物，提高修复效率，同时，建立第一知识图谱、第二知识图谱和第三知识图谱，为土壤修复方案的生成提供数据支持，提高生成的土壤修复方案的准确度，并且，化学修复试剂能够快速降低土壤中污染物的浓度和毒性，为微生物提供一个更适宜的生长和降解环境，微生物通过其特有的代谢途径，能够持续降解污染物至无害物质，实现长期的土壤修复效果，微生物修复是自然过程的强化，最终产物通常不会形成二次污染，对环境友好。相较于单一的物理或化学修复方法，联合修复技术能够减少化学试剂的使用量，降低对环境的潜在风险。实现了土壤修复方案确定的自动化，对待修复区域的实时多维土壤修复信息进行修复实时监测，确保土壤修复方案的有效性，提高了土壤生态环境修复的质量。1. Obtaining multidimensional soil detection information of the area to be repaired can accurately identify the type, concentration and distribution of pollutants, so as to select and use chemical remediation agents and microorganisms in a targeted manner to improve the remediation efficiency. At the same time, the first knowledge graph, the second knowledge graph and the third knowledge graph are established to provide data support for the generation of soil remediation plans and improve the accuracy of the generated soil remediation plans. In addition, chemical remediation agents can quickly reduce the concentration and toxicity of pollutants in the soil, providing a more suitable growth and degradation environment for microorganisms. Microorganisms can continuously degrade pollutants to harmless substances through their unique metabolic pathways to achieve long-term soil remediation effects. Microbial remediation is an enhancement of natural processes, and the final product usually does not form secondary pollution and is environmentally friendly. Compared with a single physical or chemical remediation method, the combined remediation technology can reduce the use of chemical reagents and reduce potential risks to the environment. The automation of soil remediation plan determination is realized, and the real-time multidimensional soil remediation information of the area to be repaired is repaired and monitored in real time to ensure the effectiveness of the soil remediation plan and improve the quality of soil ecological environment remediation.
2、通过确定待修复区域的土壤污染物扩散特征包括任意两个目标检测位置的水平扩散关联参数和垂直扩散关联参数，确定了污染物在待修复区域的土壤中的迁移路径和分布规律，为生成待修复区域的土壤修复方案提供了更高维度的信息，提高了土壤修复方案的有效性，进一步提高了土壤修复效率。2. By determining the diffusion characteristics of soil pollutants in the area to be repaired, including the horizontal diffusion correlation parameters and vertical diffusion correlation parameters of any two target detection positions, the migration path and distribution pattern of pollutants in the soil of the area to be repaired are determined, which provides higher-dimensional information for generating soil remediation plans for the area to be repaired, improves the effectiveness of soil remediation plans, and further improves soil remediation efficiency.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
本说明书将以示例性实施例的方式进一步说明，这些示例性实施例将通过附图进行详细描述。这些实施例并非限制性的，在这些实施例中，相同的编号表示相同的结构，其中：This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:
图1是根据本说明书一些实施例所示的一种用于土壤生态环境修复的数据处理系统的模块示意图；FIG1 is a module schematic diagram of a data processing system for soil ecological environment restoration according to some embodiments of this specification;
图2是根据本说明书一些实施例所示的第一知识图谱的示意图；FIG2 is a schematic diagram of a first knowledge graph according to some embodiments of this specification;
图3是根据本说明书一些实施例所示的第二知识图谱的示意图；FIG3 is a schematic diagram of a second knowledge graph according to some embodiments of this specification;
图4是根据本说明书一些实施例所示的第三知识图谱的示意图；FIG4 is a schematic diagram of a third knowledge graph according to some embodiments of this specification;
图5是根据本说明书一些实施例所示的一种用于土壤生态环境修复的数据处理方法的流程示意图。FIG5 is a flow chart of a data processing method for soil ecological environment restoration according to some embodiments of this specification.
具体实施方式DETAILED DESCRIPTION
为了更清楚地说明本说明书实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单的介绍。显而易见地，下面描述中的附图仅仅是本说明书的一些示例或实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图将本说明书应用于其它类似情景。除非从语言环境中显而易见或另做说明，图中相同标号代表相同结构或操作。In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.
图1是根据本说明书一些实施例所示的一种用于土壤生态环境修复的数据处理系统的模块示意图，如图1所示，一种用于土壤生态环境修复的数据处理系统可以包括土壤检测模块、特征提取模块、图谱建立模块、方案生成模块及修复检测模块。Figure 1 is a module schematic diagram of a data processing system for soil ecological environment restoration according to some embodiments of this specification. As shown in Figure 1, a data processing system for soil ecological environment restoration may include a soil detection module, a feature extraction module, a map establishment module, a solution generation module and a restoration detection module.
土壤检测模块可以用于获取待修复区域的多维土壤检测信息。The soil detection module can be used to obtain multi-dimensional soil detection information of the area to be repaired.
其中，多维土壤检测信息至少包括多个位置的不同深度的含量超标的无机污染物（例如，汞、铬、铅、铜、锌等）检测信息、有机污染物（例如，有机氯和有机磷类农药、酚、石油、3,4-苯并芘、三氯乙醛、多氯联苯等）检测信息及土壤理化性质信息（例如，pH值、全氮、有效磷、钾元素、微量元素等）。Among them, the multidimensional soil detection information at least includes detection information of inorganic pollutants (for example, mercury, chromium, lead, copper, zinc, etc.) with excessive content at different depths in multiple locations, detection information of organic pollutants (for example, organochlorine and organophosphorus pesticides, phenols, petroleum, 3,4-benzopyrene, trichloroacetaldehyde, polychlorinated biphenyls, etc.) and soil physical and chemical properties information (for example, pH value, total nitrogen, available phosphorus, potassium, trace elements, etc.).
在一些实施例中，土壤检测模块获取待修复区域的多维土壤检测信息，包括：In some embodiments, the soil detection module obtains multi-dimensional soil detection information of the area to be repaired, including:
将待修复区域分为多个子区域，基于多个子区域确定多个初始检测位置；Divide the area to be repaired into multiple sub-areas, and determine multiple initial detection positions based on the multiple sub-areas;
获取每个初始检测位置的测试用多维土壤检测信息；Obtaining multi-dimensional soil test information for testing at each initial test location;
基于每个初始检测位置的测试用多维土壤检测信息，确定待修复区域的多维土壤检测信息离散参数，基于待修复区域的多维土壤检测信息离散参数，确定待修复区域的多个目标检测位置；Determine the discrete parameters of the multidimensional soil detection information of the area to be repaired based on the multidimensional soil detection information of each initial detection position, and determine multiple target detection positions of the area to be repaired based on the discrete parameters of the multidimensional soil detection information of the area to be repaired;
基于待修复区域的多个目标检测位置，获取待修复区域的多维土壤检测信息。Based on multiple target detection positions of the area to be repaired, multi-dimensional soil detection information of the area to be repaired is obtained.
例如，可以将待修复区域均分为多个子区域，在每个子区域内确定一个初始检测位置。For example, the area to be repaired may be divided into a plurality of sub-areas, and an initial detection position may be determined in each sub-area.
在一些实施例中，土壤检测模块基于每个初始检测位置的测试用多维土壤检测信息，确定待修复区域的多维土壤检测信息离散参数，基于待修复区域的多维土壤检测信息离散参数，确定待修复区域的多个目标检测位置，包括：In some embodiments, the soil detection module determines the discrete parameters of the multidimensional soil detection information of the area to be repaired based on the multidimensional soil detection information of each initial detection position, and determines multiple target detection positions of the area to be repaired based on the discrete parameters of the multidimensional soil detection information of the area to be repaired, including:
基于每个初始检测位置的测试用多维土壤检测信息，确定待修复区域的无机污染物离散参数和有机污染物离散参数；Determine the discrete parameters of inorganic pollutants and organic pollutants in the area to be remediated based on the multidimensional soil test information for each initial test location;
基于待修复区域的无机污染物离散参数和有机污染物离散参数，判断是否新增检测位置；Based on the discrete parameters of inorganic pollutants and organic pollutants in the area to be repaired, determine whether to add a new detection location;
当判定新增检测位置时，基于每个初始检测位置的测试用多维土壤检测信息，对多个子区域进行聚类，确定多个聚类区域；When determining a newly added detection location, clustering the multiple sub-areas based on the multi-dimensional soil detection information for testing at each initial detection location to determine multiple clustering areas;
对于每个聚类区域，基于聚类区域包括的每个初始检测位置的测试用多维土壤检测信息，判断聚类区域是否为目标聚类区域；For each clustering area, judging whether the clustering area is a target clustering area based on the test multi-dimensional soil detection information of each initial detection position included in the clustering area;
对于每个目标聚类区域，基于聚类区域包括的每个初始检测位置的测试用多维土壤检测信息，确定目标聚类区域的检测位置密度，基于检测位置密度，确定目标聚类区域的多个目标检测位置。For each target clustering area, the detection position density of the target clustering area is determined based on the test multidimensional soil detection information of each initial detection position included in the clustering area, and based on the detection position density, multiple target detection positions of the target clustering area are determined.
具体的，可以基于以下公式计算某种无机污染物离散参数：Specifically, the discrete parameters of a certain inorganic pollutant can be calculated based on the following formula:
其中，为第i种无机污染物对应的无机污染物离散参数，为第n个初始检测位置的第i种无机污染物的含量均值，可以为第n个位置的不同深度的第i种无机污染物的含量的平均值，为初始检测位置的总数。in, is the inorganic pollutant discrete parameter corresponding to the ith inorganic pollutant, is the mean value of the content of the ith inorganic pollutant at the nth initial detection position, It can be the average value of the content of the ith inorganic pollutant at different depths at the nth position, is the total number of initial detection positions.
可以基于以下公式计算某种有机污染物离散参数：The discrete parameters of a certain organic pollutant can be calculated based on the following formula:
其中，为第j种有机污染物对应的无机污染物离散参数，为第n个初始检测位置的第j种有机污染物的含量均值，可以为第n个位置的不同深度的第j种有机污染物的含量的平均值。in, is the discrete parameter of inorganic pollutants corresponding to the jth organic pollutant, is the mean value of the content of the jth organic pollutant at the nth initial detection position, It can be the average value of the content of the j-th organic pollutant at different depths at the n-th position.
当待修复区域的某种无机污染物离散参数大于第一预设无机污染物离散参数阈值和/或某种有机污染物离散参数大于第一预设有机污染物离散参数阈值时，判定新增检测位置。When a discrete parameter of a certain inorganic pollutant in the area to be repaired is greater than a first preset discrete parameter threshold of an inorganic pollutant and/or a discrete parameter of a certain organic pollutant is greater than a first preset discrete parameter threshold of an organic pollutant, a new detection position is determined.
对于任意两个初始检测位置，计算两个初始检测位置的测试用多维土壤检测信息的余弦距离，可以通过K均值聚类算法基于任意两个初始检测位置的测试用多维土壤检测信息的余弦距离，对多个子区域进行聚类，确定多个聚类区域。For any two initial detection positions, the cosine distance of the multidimensional soil detection information for testing at the two initial detection positions is calculated. The K-means clustering algorithm can be used to cluster multiple sub-areas based on the cosine distance of the multidimensional soil detection information for testing at any two initial detection positions to determine multiple clustering areas.
对于每个聚类区域，基于聚类区域包括的每个初始检测位置的测试用多维土壤检测信息，计算该聚类区域的无机污染物离散参数和有机污染物离散参数，当聚类区域的某种无机污染物离散参数大于第二预设无机污染物离散参数阈值和/或某种有机污染物离散参数大于第二预设有机污染物离散参数阈值时，判定该聚类区域为目标聚类区域。For each clustering area, the inorganic pollutant discrete parameters and organic pollutant discrete parameters of the clustering area are calculated based on the test multidimensional soil detection information of each initial detection position included in the clustering area. When a certain inorganic pollutant discrete parameter of the clustering area is greater than a second preset inorganic pollutant discrete parameter threshold and/or a certain organic pollutant discrete parameter is greater than a second preset organic pollutant discrete parameter threshold, the clustering area is determined to be a target clustering area.
基于以下公式计算确定目标聚类区域的检测位置密度：The detection location density of the target cluster area is determined based on the following formula:
其中，为第k个目标聚类区域的检测位置密度，为预设标准检测位置密度，为第k个目标聚类区域的第i种无机污染物对应的无机污染物离散参数，为第k个目标聚类区域的第j种有机污染物对应的无机污染物离散参数，为预设参数，且大于0。in, is the detection location density of the kth target cluster area, To preset the standard detection position density, is the inorganic pollutant discrete parameter corresponding to the i-th inorganic pollutant in the k-th target cluster area, is the discrete parameter of inorganic pollutants corresponding to the jth organic pollutant in the kth target cluster area, is the preset parameter, and Greater than 0.
特征提取模块可以用于基于待修复区域的多维土壤检测信息，提取待修复区域的土壤污染物扩散特征。The feature extraction module can be used to extract the diffusion characteristics of soil pollutants in the area to be repaired based on the multi-dimensional soil detection information of the area to be repaired.
在一些实施例中，特征提取模块基于待修复区域的多维土壤检测信息，提取待修复区域的土壤污染物扩散特征，包括：In some embodiments, the feature extraction module extracts soil pollutant diffusion characteristics of the area to be remediated based on multi-dimensional soil detection information of the area to be remediated, including:
对于每个目标检测位置，基于待修复区域的多维土壤检测信息，生成目标检测位置的不同深度的无机污染变化曲线及有机污染变化曲线，对不同深度的无机污染变化曲线及有机污染变化曲线进行内涵模态分解，生成不同深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及不同深度的有机污染变化曲线对应的有机污染分量和有机污染残差；For each target detection location, based on the multidimensional soil detection information of the area to be repaired, the inorganic pollution change curve and the organic pollution change curve of the target detection location at different depths are generated, and the inorganic pollution change curve and the organic pollution change curve at different depths are subjected to intrinsic modal decomposition to generate the inorganic pollution components and inorganic pollution residuals corresponding to the inorganic pollution change curves at different depths and the organic pollution components and organic pollution residuals corresponding to the organic pollution change curves at different depths;
对于任意两个目标检测位置，基于两个目标检测位置的不同深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及不同深度的有机污染变化曲线对应的机污染分量和有机污染残差，确定两个目标检测位置的水平扩散关联参数和垂直扩散关联参数，其中，待修复区域的土壤污染物扩散特征包括任意两个目标检测位置的水平扩散关联参数和垂直扩散关联参数。For any two target detection positions, the horizontal diffusion association parameters and vertical diffusion association parameters of the two target detection positions are determined based on the inorganic pollution components and inorganic pollution residuals corresponding to the inorganic pollution change curves at different depths of the two target detection positions and the organic pollution components and organic pollution residuals corresponding to the organic pollution change curves at different depths, wherein the soil pollutant diffusion characteristics of the area to be remediated include the horizontal diffusion association parameters and vertical diffusion association parameters of any two target detection positions.
具体的，可以包括以下步骤：Specifically, the following steps may be included:
S11、确定信号的上下极值点：根据变化曲线的上下极值点，分别确定局部极大值点和局部极小值点。S11. Determine the upper and lower extreme points of the signal: According to the upper and lower extreme points of the variation curve, determine the local maximum point and the local minimum point respectively.
S12、构造上下包络线：通过插值或其他方法，根据局部极大值点构造上包络线（上线包络信号）。同样地，根据局部极小值点构造下包络线（下线包络信号）。S12, constructing upper and lower envelopes: constructing an upper envelope (upper envelope signal) based on the local maximum points by interpolation or other methods. Similarly, constructing a lower envelope (lower envelope signal) based on the local minimum points.
S13、计算均值包络线：对上包络线和下包络线求均值，得到均值包络线（均值包络信号）。S13. Calculate the mean envelope: average the upper envelope and the lower envelope to obtain the mean envelope (mean envelope signal).
S14、提取中间信号：将原始信号减去均值包络线，得到中间信号（残余信号）。判断中间信号是否满足内涵模态分量（IMF）的条件：检查中间信号是否满足两个约束条件：极值点的个数和过零点的个数必须相等或相差最多不能超过一个。在任意时刻，由局部极大值点形成的上包络线和由局部极小值点形成的下包络线的平均值为零（即上、下包络线关于时间轴局部轴对称）。如果满足条件，则中间信号就是一个IMF分量。S14. Extract the intermediate signal: subtract the mean envelope from the original signal to obtain the intermediate signal (residual signal). Determine whether the intermediate signal meets the conditions of the intrinsic modal component (IMF): Check whether the intermediate signal meets two constraints: the number of extreme points and the number of zero-crossing points must be equal or the difference cannot exceed one at most. At any time, the average value of the upper envelope formed by the local maximum point and the lower envelope formed by the local minimum point is zero (that is, the upper and lower envelopes are symmetrical about the local axis of the time axis). If the conditions are met, the intermediate signal is an IMF component.
S15、迭代处理：如果中间信号不满足IMF的条件，则以该中间信号为基础，重复步骤1至5，直到满足条件为止。S15, iterative processing: if the intermediate signal does not meet the IMF condition, then based on the intermediate signal, repeat steps 1 to 5 until the condition is met.
S16、得到所有IMF分量：每次迭代得到的IMF分量都代表原始信号的一个固有模态。重复上述步骤，直到剩余的信号（即原信号减去所有已提取的IMF分量后的结果）满足终止条件（如剩余信号变得非常小或单调等）.S16, get all IMF components: each IMF component obtained in each iteration represents an intrinsic mode of the original signal. Repeat the above steps until the remaining signal (i.e. the result after subtracting all the extracted IMF components from the original signal) meets the termination condition (such as the remaining signal becomes very small or monotonic, etc.).
S17、残差处理：最后的剩余信号通常被视为残差，它可能包含噪声或一些非模态信息。S17. Residual processing: The final remaining signal is usually regarded as a residual, which may contain noise or some non-modal information.
分离出来的第一个内涵模态分量可以称为一阶分量，分离出来的第二个内涵模态分量可以称为二阶分量等。The first separated intrinsic modal component can be called a first-order component, the second separated intrinsic modal component can be called a second-order component, and so on.
在一些实施例中，特征提取模块基于两个目标检测位置的不同深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及不同深度的有机污染变化曲线对应的有机污染分量和有机污染残差，确定两个目标检测位置的水平扩散关联参数，包括：In some embodiments, the feature extraction module determines the horizontal diffusion correlation parameters of the two target detection positions based on the inorganic pollution components and inorganic pollution residuals corresponding to the inorganic pollution change curves at different depths of the two target detection positions and the organic pollution components and organic pollution residuals corresponding to the organic pollution change curves at different depths, including:
对于每个深度，基于两个目标检测位置在该深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及有机污染变化曲线对应的有机污染分量和有机污染残差，确定两个目标检测位置对应深度的单平面水平扩散关联参数；For each depth, based on the inorganic pollution component and inorganic pollution residual corresponding to the inorganic pollution change curve of the two target detection positions at the depth and the organic pollution component and organic pollution residual corresponding to the organic pollution change curve, determine the single-plane horizontal diffusion correlation parameters at the depth corresponding to the two target detection positions;
基于两个目标检测位置对应每个深度的单平面水平扩散关联参数，确定两个目标检测位置的水平扩散关联参数。Based on the single-plane horizontal diffusion correlation parameters corresponding to each depth of the two target detection positions, the horizontal diffusion correlation parameters of the two target detection positions are determined.
具体的，对于每种无机污染物，可以计算该无机污染物的无机污染变化曲线对应的每一阶无机污染分量对应的含量均值和无机污染物离散参数以及无机污染残差对应的无机污染物含量均值和无机污染物离散参数。对于每种有机污染物，可以计算该有机污染物的有机污染变化曲线对应的每一阶有机污染分量对应的含量均值和有机污染物离散参数以及有机污染残差对应的有机污染物含量均值和有机污染物离散参数。Specifically, for each inorganic pollutant, the content mean and discrete parameters of each order of inorganic pollution components corresponding to the inorganic pollution change curve of the inorganic pollutant, as well as the content mean and discrete parameters of inorganic pollutants corresponding to the inorganic pollution residuals can be calculated. For each organic pollutant, the content mean and discrete parameters of each order of organic pollution components corresponding to the organic pollution change curve of the organic pollutant, as well as the content mean and discrete parameters of organic pollutants corresponding to the organic pollution residuals can be calculated.
两个目标检测位置的水平扩散关联参数可以包括无机污染物水平扩散关联参数和有机污染物水平扩散关联参数。The horizontal diffusion correlation parameters of the two target detection positions may include inorganic pollutant horizontal diffusion correlation parameters and organic pollutant horizontal diffusion correlation parameters.
基于以下公式计算两个目标检测位置对应某个深度的无机污染物水平扩散关联参数：The horizontal diffusion correlation parameters of inorganic pollutants at a certain depth at two target detection locations are calculated based on the following formula:
其中，为第e个目标检测位置和第f个目标检测位置之间的无机污染物水平扩散关联参数，为第e个目标检测位置和第f个目标检测位置对应第i种无机污染物的无机污染物水平扩散关联参数，为第e个目标检测位置对应第i种无机污染物的无机污染变化曲线的第g阶无机污染分量对应的含量均值，为第f个目标检测位置对应第i种无机污染物的无机污染变化曲线的第g阶无机污染分量对应的含量均值，为第e个目标检测位置对应第i种无机污染物的无机污染变化曲线的第g阶无机污染分量对应的无机污染物离散参数，为第f个目标检测位置对应第i种无机污染物的无机污染变化曲线的第g阶无机污染分量对应的无机污染物离散参数，为第e个目标检测位置对应第i种无机污染物的无机污染变化曲线的无机污染残差对应的无机污染物含量均值，为第f个目标检测位置对应第i种无机污染物的无机污染变化曲线的无机污染残差对应的无机污染物含量均值，为第e个目标检测位置对应第i种无机污染物的无机污染变化曲线的无机污染残差对应的无机污染物离散参数，为第f个目标检测位置对应第i种无机污染物的无机污染变化曲线的无机污染残差对应的无机污染物离散参数，和均为预设参数，且和均大于0。in, is the inorganic pollutant horizontal diffusion correlation parameter between the e-th target detection position and the f-th target detection position, is the inorganic pollutant horizontal diffusion correlation parameter corresponding to the i-th inorganic pollutant at the e-th target detection position and the f-th target detection position, is the content mean value corresponding to the g-th order inorganic pollution component of the inorganic pollution change curve corresponding to the i-th inorganic pollutant at the e-th target detection position, is the content mean value corresponding to the g-th order inorganic pollution component of the inorganic pollution change curve corresponding to the i-th inorganic pollutant at the f-th target detection position, is the inorganic pollutant discrete parameter corresponding to the g-th order inorganic pollution component of the inorganic pollution change curve corresponding to the i-th inorganic pollutant at the e-th target detection position, is the inorganic pollutant discrete parameter corresponding to the g-th order inorganic pollution component of the inorganic pollution change curve corresponding to the i-th inorganic pollutant at the f-th target detection position, is the mean value of the inorganic pollutant content corresponding to the inorganic pollution residual of the inorganic pollution change curve of the i-th inorganic pollutant at the e-th target detection position, is the mean value of the inorganic pollutant content corresponding to the inorganic pollution residual of the inorganic pollution change curve of the i-th inorganic pollutant at the f-th target detection position, is the inorganic pollutant discrete parameter corresponding to the inorganic pollution residual of the inorganic pollution change curve of the i-th inorganic pollutant at the e-th target detection position, is the inorganic pollutant discrete parameter corresponding to the inorganic pollution residual of the inorganic pollution change curve of the i-th inorganic pollutant at the f-th target detection position, and are all preset parameters, and and Both are greater than 0.
有机污染物水平扩散关联参数的计算方式与无机污染物水平扩散关联参数的计算方式相似，此处不再赘述。The calculation method of the horizontal diffusion correlation parameters of organic pollutants is similar to that of inorganic pollutants and will not be repeated here.
在一些实施例中，特征提取模块基于两个目标检测位置的不同深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及不同深度的有机污染变化曲线对应的有机污染分量和有机污染残差，确定两个目标检测位置的垂直扩散关联参数，包括：In some embodiments, the feature extraction module determines the vertical diffusion correlation parameters of the two target detection positions based on the inorganic pollution components and inorganic pollution residuals corresponding to the inorganic pollution change curves at different depths of the two target detection positions and the organic pollution components and organic pollution residuals corresponding to the organic pollution change curves at different depths, including:
对于每个目标检测位置，基于目标检测位置的不同深度的无机污染变化曲线对应的无机污染分量和无机污染残差以及不同深度的有机污染变化曲线对应的有机污染分量和有机污染残差，确定目标检测位置的垂直扩散参数；For each target detection position, based on the inorganic pollution component and inorganic pollution residual corresponding to the inorganic pollution change curve at different depths of the target detection position and the organic pollution component and organic pollution residual corresponding to the organic pollution change curve at different depths, determine the vertical diffusion parameter of the target detection position;
基于两个目标检测位置对应的垂直扩散参数，确定两个目标检测位置的垂直扩散关联参数。Based on the vertical diffusion parameters corresponding to the two target detection positions, vertical diffusion association parameters of the two target detection positions are determined.
具体的，对于每种无机污染物，可以提取同一目标检测位置的每个深度的无机污染变化曲线对应的无机污染分量的时域特征和频域特征和无机污染残差的时域特征和频域特征，通过扩散参数确定模型基于同一目标检测位置的每个深度的无机污染变化曲线对应的无机污染分量的时域特征和频域特征和无机污染残差的时域特征和频域特征，确定无机污染物该在目标检测位置的垂直扩散参数。其中，扩散参数确定模型可以为卷积神经网络（Convolutional Neural Network,CNN）模型。Specifically, for each inorganic pollutant, the time domain characteristics and frequency domain characteristics of the inorganic pollution component and the time domain characteristics and frequency domain characteristics of the inorganic pollution residual corresponding to the inorganic pollution change curve at each depth of the same target detection position can be extracted, and the vertical diffusion parameters of the inorganic pollutant at the target detection position can be determined by the diffusion parameter determination model based on the time domain characteristics and frequency domain characteristics of the inorganic pollution component and the time domain characteristics and frequency domain characteristics of the inorganic pollution residual corresponding to the inorganic pollution change curve at each depth of the same target detection position. The diffusion parameter determination model can be a Convolutional Neural Network (CNN) model.
对于每个目标检测位置，基于每种无机污染物对应的垂直扩散参数，生成无机污染物垂直扩散参数序列。For each target detection position, an inorganic pollutant vertical diffusion parameter sequence is generated based on the vertical diffusion parameter corresponding to each inorganic pollutant.
同样的，对于每种有机污染物，可以提取同一目标检测位置的每个深度的有机污染变化曲线对应的有机污染分量的时域特征和频域特征和有机污染残差的时域特征和频域特征，通过扩散参数确定模型基于同一目标检测位置的每个深度的有机污染变化曲线对应的有机污染分量的时域特征和频域特征和有机污染残差的时域特征和频域特征，确定有机污染物该在目标检测位置的垂直扩散参数。Similarly, for each organic pollutant, the time domain characteristics and frequency domain characteristics of the organic pollution component corresponding to the organic pollution change curve at each depth of the same target detection position and the time domain characteristics and frequency domain characteristics of the organic pollution residual can be extracted. The vertical diffusion parameters of the organic pollutant at the target detection position can be determined by the diffusion parameter determination model based on the time domain characteristics and frequency domain characteristics of the organic pollution component corresponding to the organic pollution change curve at each depth of the same target detection position and the time domain characteristics and frequency domain characteristics of the organic pollution residual.
对于每个目标检测位置，基于每种无机污染物对应的垂直扩散参数，生成有机污染物垂直扩散参数序列。For each target detection position, a vertical diffusion parameter sequence of organic pollutants is generated based on the vertical diffusion parameter corresponding to each inorganic pollutant.
对于任意两个目标检测位置，可以计算两个目标检测位置对应的无机污染物垂直扩散参数序列之间的第一余弦相似度，计算两个目标检测位置对应的有机污染物垂直扩散参数序列之间的第二余弦相似度，对第一余弦相似度和第二余弦相似度进行加权求和，确定两个目标检测位置的垂直扩散关联参数。For any two target detection positions, the first cosine similarity between the vertical diffusion parameter sequences of inorganic pollutants corresponding to the two target detection positions can be calculated, and the second cosine similarity between the vertical diffusion parameter sequences of organic pollutants corresponding to the two target detection positions can be calculated. The first cosine similarity and the second cosine similarity are weightedly summed to determine the vertical diffusion association parameters of the two target detection positions.
图谱建立模块可以用于建立第一知识图谱、第二知识图谱和第三知识图谱。The graph building module can be used to build a first knowledge graph, a second knowledge graph, and a third knowledge graph.
其中，第一知识图谱用于记载污染物与化学修复试剂之间的关联关系，图2是根据本说明书一些实施例所示的第一知识图谱的示意图，如图2所示，作为示例的，石油烃可以高锰酸盐、过氧化氢、芬顿试剂降解，铜可以被磷酸盐、硅酸盐降解。Among them, the first knowledge graph is used to record the association between pollutants and chemical remediation reagents. Figure 2 is a schematic diagram of the first knowledge graph shown in some embodiments of this specification. As shown in Figure 2, as an example, petroleum hydrocarbons can be degraded by permanganate, hydrogen peroxide, and Fenton's reagent, and copper can be degraded by phosphate and silicate.
第二知识图谱用于记载污染物与微生物之间的关联关系。图3是根据本说明书一些实施例所示的第二知识图谱的示意图，如图3所示，作为示例的，石油类污染物可以被假单胞菌、棒杆菌、节杆菌、黄杆菌降解，重金属污染物可以被硫酸盐还原菌降解。The second knowledge graph is used to record the association between pollutants and microorganisms. Figure 3 is a schematic diagram of the second knowledge graph shown in some embodiments of this specification. As shown in Figure 3, as an example, petroleum pollutants can be degraded by Pseudomonas, Corynebacterium, Arthrobacter, and Flavobacterium, and heavy metal pollutants can be degraded by sulfate-reducing bacteria.
第三知识图谱用于记载化学修复试剂与微生物之间的关联关系，具体的，记载化学修复试剂互补的微生物，图4是根据本说明书一些实施例所示的第三知识图谱的示意图，如图4所示，作为示例的，假单胞菌可以与氮、磷、钾等无机盐类、有机酸、表面活性剂、过硫酸钠、过氧化氢互补，提高石油类污染物的降解效率等。The third knowledge graph is used to record the association between chemical remediation reagents and microorganisms. Specifically, it records the microorganisms that complement the chemical remediation reagents. Figure 4 is a schematic diagram of the third knowledge graph shown in some embodiments of the present specification. As shown in Figure 4, as an example, Pseudomonas can complement inorganic salts such as nitrogen, phosphorus, and potassium, organic acids, surfactants, sodium persulfate, and hydrogen peroxide to improve the degradation efficiency of petroleum pollutants.
具体的，图谱建立模块可以获取污染土壤的微生物修复及化学修复试剂实例，提取实例中的实体及实体之间关系利用知识图卷积神经网络构建第一知识图谱、第二知识图谱和第三知识图谱。Specifically, the graph building module can obtain examples of microbial remediation and chemical remediation reagents for contaminated soil, extract entities in the examples and the relationships between entities, and use the knowledge graph convolutional neural network to construct the first knowledge graph, the second knowledge graph, and the third knowledge graph.
方案生成模块可以用于基于待修复区域的多维土壤检测信息、土壤污染物扩散特征、第一知识图谱、第二知识图谱和第三知识图谱，生成待修复区域的土壤修复方案。The solution generation module can be used to generate a soil remediation solution for the area to be remediated based on the multidimensional soil detection information of the area to be remediated, the soil pollutant diffusion characteristics, the first knowledge graph, the second knowledge graph and the third knowledge graph.
在一些实施例中，方案生成模块基于待修复区域的多维土壤检测信息、土壤污染物扩散特征、第一知识图谱、第二知识图谱和第三知识图谱，生成待修复区域的土壤修复方案，包括：In some embodiments, the solution generation module generates a soil remediation solution for the area to be remediated based on the multidimensional soil detection information of the area to be remediated, the soil pollutant diffusion characteristics, the first knowledge graph, the second knowledge graph, and the third knowledge graph, including:
建立样本数据库，其中，样本数据库用于存储多个样本土壤的多维土壤检测信息、土壤污染物扩散特征及土壤修复方案；Establishing a sample database, wherein the sample database is used to store multi-dimensional soil detection information, soil pollutant diffusion characteristics and soil remediation plans of multiple sample soils;
基于待修复区域的多维土壤检测信息及土壤污染物扩散特征，从多个样本土壤中确定目标样本土壤；Based on the multi-dimensional soil detection information and soil pollutant diffusion characteristics of the area to be remediated, the target sample soil is determined from multiple sample soils;
通过方案生成模型基于目标样本土壤的土壤修复方案、待修复区域的多维土壤检测信息、土壤污染物扩散特征、第一知识图谱、第二知识图谱和第三知识图谱，生成待修复区域的土壤修复方案，其中，方案生成模型可以为生成对抗网络（Generative AdversarialNetworks）模型，待修复区域的土壤修复方案可以包括待修复区域的多个位置在多个修复时间点的化学修复试剂使用信息和微生物添加信息。A soil remediation scheme for the area to be remediated is generated through a scheme generation model based on the soil remediation scheme of the target sample soil, the multidimensional soil detection information of the area to be remediated, the diffusion characteristics of soil pollutants, the first knowledge graph, the second knowledge graph and the third knowledge graph. The scheme generation model can be a Generative Adversarial Networks model, and the soil remediation scheme for the area to be remediated may include chemical remediation reagent usage information and microbial addition information at multiple locations in the area to be remediated and at multiple remediation time points.
修复检测模块可以用于获取在土壤修复过程中获取待修复区域的实时多维土壤修复信息，并基于待修复区域的实时多维土壤修复信息进行修复实时监测。The remediation detection module can be used to obtain real-time multi-dimensional soil remediation information of the area to be remediated during the soil remediation process, and to perform real-time monitoring of remediation based on the real-time multi-dimensional soil remediation information of the area to be remediated.
实时多维土壤修复信息可以待修复区域的多个位置的不同深度的无机污染物检测信息、有机污染物检测信息、土壤理化性质信息、化学修复试剂含量信息和微生物含量信息。Real-time multi-dimensional soil remediation information can include inorganic pollutant detection information, organic pollutant detection information, soil physical and chemical properties information, chemical remediation agent content information and microbial content information at different depths in multiple locations in the area to be remediated.
在一些实施例中，修复检测模块基于待修复区域的实时多维土壤修复信息进行修复实时监测，包括：In some embodiments, the remediation detection module performs real-time remediation monitoring based on real-time multi-dimensional soil remediation information of the area to be remediated, including:
基于待修复区域的多维土壤检测信息、土壤污染物扩散特征和待修复区域的土壤修复方案，预测待修复区域在修复过程中的多个修复时间点的预测多维土壤修复信息；Based on the multidimensional soil detection information of the area to be repaired, the diffusion characteristics of soil pollutants and the soil remediation plan of the area to be repaired, the predicted multidimensional soil remediation information of the area to be repaired at multiple remediation time points during the remediation process is predicted;
基于待修复区域的实时多维土壤修复信息和预测多维土壤修复信息，对土壤修复方案进行实时调整。Based on the real-time multi-dimensional soil remediation information and predicted multi-dimensional soil remediation information of the area to be remediated, the soil remediation plan is adjusted in real time.
在一些实施例中，修复检测模块基于待修复区域的实时多维土壤修复信息和预测多维土壤修复信息，对土壤修复方案进行实时调整，包括：In some embodiments, the remediation detection module adjusts the soil remediation scheme in real time based on the real-time multi-dimensional soil remediation information and the predicted multi-dimensional soil remediation information of the area to be remediated, including:
基于待修复区域的实时多维土壤修复信息和预测多维土壤修复信息，计算修复偏离参数；Calculate the restoration deviation parameter based on the real-time multi-dimensional soil restoration information and the predicted multi-dimensional soil restoration information of the area to be restored;
根据修复偏离参数判断是否对土壤修复方案进行实时调整。Determine whether to make real-time adjustments to the soil remediation plan based on the remediation deviation parameters.
可以计算待修复区域的实时多维土壤修复信息和预测多维土壤修复信息在多个历史修复时间点的差值，对多个历史修复时间点的差值进行累加，确定修复偏离参数。当修复偏离参数大于预设修复偏离参数阈值时，判定对土壤修复方案进行实时调整。The difference between the real-time multi-dimensional soil remediation information of the area to be remediated and the predicted multi-dimensional soil remediation information at multiple historical remediation time points can be calculated, and the difference between multiple historical remediation time points can be accumulated to determine the remediation deviation parameter. When the remediation deviation parameter is greater than the preset remediation deviation parameter threshold, it is determined that the soil remediation plan should be adjusted in real time.
可以通过方案调整模型基于目标样本土壤的土壤修复方案、待修复区域的多维土壤检测信息、土壤污染物扩散特征、第一知识图谱、第二知识图谱、第三知识图谱、土壤修复方案以及待修复区域的实时多维土壤修复信息和预测多维土壤修复信息在多个历史修复时间点的差值，生成调整后的土壤修复方案，其中，方案调整模型可以为生成对抗网络（Generative Adversarial Networks）模型。The scheme adjustment model can be used to generate an adjusted soil remediation scheme based on the soil remediation scheme of the target sample soil, the multidimensional soil detection information of the area to be remediated, the diffusion characteristics of soil pollutants, the first knowledge graph, the second knowledge graph, the third knowledge graph, the soil remediation scheme, and the real-time multidimensional soil remediation information of the area to be remediated and the difference between the predicted multidimensional soil remediation information at multiple historical remediation time points. The scheme adjustment model can be a Generative Adversarial Networks model.
图5是根据本说明书一些实施例所示的一种用于土壤生态环境修复的数据处理方法的流程示意图，如图5所示，一种用于土壤生态环境修复的数据处理方法可以包括以下步骤。FIG5 is a flow chart of a data processing method for soil ecological environment restoration according to some embodiments of this specification. As shown in FIG5 , a data processing method for soil ecological environment restoration may include the following steps.
步骤510，获取待修复区域的多维土壤检测信息，其中，多维土壤检测信息至少包括多个位置的不同深度的无机污染物检测信息、有机污染物检测信息及土壤理化性质信息；Step 510, obtaining multi-dimensional soil detection information of the area to be remediated, wherein the multi-dimensional soil detection information at least includes inorganic pollutant detection information, organic pollutant detection information and soil physical and chemical property information at different depths at multiple locations;
步骤520，基于待修复区域的多维土壤检测信息，提取待修复区域的土壤污染物扩散特征；Step 520, extracting soil pollutant diffusion characteristics of the area to be remediated based on the multi-dimensional soil detection information of the area to be remediated;
步骤530，建立第一知识图谱、第二知识图谱和第三知识图谱，其中，第一知识图谱用于记载污染物与化学修复试剂之间的关联关系，第二知识图谱用于记载污染物与微生物之间的关联关系，第三知识图谱用于记载化学修复试剂与微生物之间的关联关系；Step 530, establishing a first knowledge graph, a second knowledge graph, and a third knowledge graph, wherein the first knowledge graph is used to record the association relationship between pollutants and chemical remediation agents, the second knowledge graph is used to record the association relationship between pollutants and microorganisms, and the third knowledge graph is used to record the association relationship between chemical remediation agents and microorganisms;
步骤540，基于待修复区域的多维土壤检测信息、土壤污染物扩散特征、第一知识图谱、第二知识图谱和第三知识图谱，生成待修复区域的土壤修复方案；Step 540, generating a soil remediation plan for the area to be remediated based on the multidimensional soil detection information of the area to be remediated, the soil pollutant diffusion characteristics, the first knowledge graph, the second knowledge graph, and the third knowledge graph;
步骤550，获取在土壤修复过程中获取待修复区域的实时多维土壤修复信息；Step 550, obtaining real-time multi-dimensional soil remediation information of the area to be remediated during the soil remediation process;
步骤560，基于待修复区域的实时多维土壤修复信息进行修复实时监测。Step 560: Perform real-time monitoring of restoration based on the real-time multi-dimensional soil restoration information of the area to be restored.
一种用于土壤生态环境修复的数据处理方法可以由一种用于土壤生态环境修复的数据处理系统执行，关于一种用于土壤生态环境修复的数据处理方法的更多描述可以参见一种用于土壤生态环境修复的数据处理系统的相关描述，此处不再赘述。A data processing method for soil ecological environment restoration can be executed by a data processing system for soil ecological environment restoration. For more descriptions of a data processing method for soil ecological environment restoration, please refer to the relevant description of a data processing system for soil ecological environment restoration, which will not be repeated here.
最后，应当理解的是，本说明书中所述实施例仅用以说明本说明书实施例的原则。其他的变形也可能属于本说明书的范围。因此，作为示例而非限制，本说明书实施例的替代配置可视为与本说明书的教导一致。相应地，本说明书的实施例不仅限于本说明书明确介绍和描述的实施例。Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411307088.1ACN118824413B (en) | 2024-09-19 | 2024-09-19 | Data processing method and system for restoring ecological environment of soil |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411307088.1ACN118824413B (en) | 2024-09-19 | 2024-09-19 | Data processing method and system for restoring ecological environment of soil |
| Publication Number | Publication Date |
|---|---|
| CN118824413Atrue CN118824413A (en) | 2024-10-22 |
| CN118824413B CN118824413B (en) | 2024-11-29 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411307088.1AActiveCN118824413B (en) | 2024-09-19 | 2024-09-19 | Data processing method and system for restoring ecological environment of soil |
| Country | Link |
|---|---|
| CN (1) | CN118824413B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119418824A (en)* | 2024-10-28 | 2025-02-11 | 生态环境部土壤与农业农村生态环境监管技术中心 | Groundwater pollution source analysis and ecological restoration decision support system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5398756A (en)* | 1992-12-14 | 1995-03-21 | Monsanto Company | In-situ remediation of contaminated soils |
| RU2443001C1 (en)* | 2010-08-05 | 2012-02-20 | Сергей Петрович Алексеев | Method for the region's ecological state data collection and an automated system of ecological monitoring and emergency monitoring of the regional environment |
| CN115007634A (en)* | 2022-06-22 | 2022-09-06 | 浙江大学 | A machine learning-based method for remediation of organically polluted soil |
| WO2023101773A1 (en)* | 2021-11-30 | 2023-06-08 | Microsoft Technology Licensing, Llc. | Pollutant sensor placement |
| CN117035454A (en)* | 2023-08-11 | 2023-11-10 | 上海亚新城市建设有限公司 | Soil pollution repair model training method, system, electronic equipment and medium |
| CN117171223A (en)* | 2023-11-02 | 2023-12-05 | 北京建工环境修复股份有限公司 | Microorganism culture scheme recommendation method and system in microorganism repair process |
| CN117172993A (en)* | 2023-11-02 | 2023-12-05 | 北京建工环境修复股份有限公司 | Pollution site assessment method and system based on microorganism dynamic analysis |
| CN117171678A (en)* | 2023-11-02 | 2023-12-05 | 北京建工环境修复股份有限公司 | Soil microbial flora regulation and control method and system in microbial remediation process |
| CN117172994A (en)* | 2023-11-02 | 2023-12-05 | 北京建工环境修复股份有限公司 | Microorganism combined restoration scheme recommendation method and system for polluted soil |
| CN118464716A (en)* | 2024-07-12 | 2024-08-09 | 陕西省环境监测中心站 | A soil environmental pollution online detection method and detection device |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5398756A (en)* | 1992-12-14 | 1995-03-21 | Monsanto Company | In-situ remediation of contaminated soils |
| RU2443001C1 (en)* | 2010-08-05 | 2012-02-20 | Сергей Петрович Алексеев | Method for the region's ecological state data collection and an automated system of ecological monitoring and emergency monitoring of the regional environment |
| WO2023101773A1 (en)* | 2021-11-30 | 2023-06-08 | Microsoft Technology Licensing, Llc. | Pollutant sensor placement |
| CN115007634A (en)* | 2022-06-22 | 2022-09-06 | 浙江大学 | A machine learning-based method for remediation of organically polluted soil |
| CN117035454A (en)* | 2023-08-11 | 2023-11-10 | 上海亚新城市建设有限公司 | Soil pollution repair model training method, system, electronic equipment and medium |
| CN117171223A (en)* | 2023-11-02 | 2023-12-05 | 北京建工环境修复股份有限公司 | Microorganism culture scheme recommendation method and system in microorganism repair process |
| CN117172993A (en)* | 2023-11-02 | 2023-12-05 | 北京建工环境修复股份有限公司 | Pollution site assessment method and system based on microorganism dynamic analysis |
| CN117171678A (en)* | 2023-11-02 | 2023-12-05 | 北京建工环境修复股份有限公司 | Soil microbial flora regulation and control method and system in microbial remediation process |
| CN117172994A (en)* | 2023-11-02 | 2023-12-05 | 北京建工环境修复股份有限公司 | Microorganism combined restoration scheme recommendation method and system for polluted soil |
| CN118464716A (en)* | 2024-07-12 | 2024-08-09 | 陕西省环境监测中心站 | A soil environmental pollution online detection method and detection device |
| Title |
|---|
| LUO NA 等: "Estimation and analysis system for soil heavy metal pollution based on spatial interpolation", JOURNAL OF FOOD SAFETY AND QUALITY, vol. 7, no. 2, 31 December 2016 (2016-12-31), pages 497 - 504* |
| 唐柜彪: "农业用地土壤重金属样本点数据精化方法研究", 中国优秀硕士学位论文全文数据库 工程科技I辑, no. 02, 15 February 2022 (2022-02-15), pages 027 - 408* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119418824A (en)* | 2024-10-28 | 2025-02-11 | 生态环境部土壤与农业农村生态环境监管技术中心 | Groundwater pollution source analysis and ecological restoration decision support system |
| Publication number | Publication date |
|---|---|
| CN118824413B (en) | 2024-11-29 |
| Publication | Publication Date | Title |
|---|---|---|
| CN118824413A (en) | A data processing method and system for soil ecological environment restoration | |
| Cattle et al. | Kriging method evaluation for assessing the spatial distribution of urban soil lead contamination | |
| Davy et al. | Colonization of a newly developing salt marsh: disentangling independent effects of elevation and redox potential on halophytes | |
| CN117172994B (en) | Microorganism combined restoration scheme recommendation method and system for polluted soil | |
| García‐Carreras et al. | An empirical link between the spectral colour of climate and the spectral colour of field populations in the context of climate change | |
| Sorichetta et al. | A Comparison of Data‐Driven Groundwater Vulnerability Assessment Methods | |
| CN119418824A (en) | Groundwater pollution source analysis and ecological restoration decision support system | |
| Banik et al. | Optimal placement of water quality monitoring stations in sewer systems: An information theory approach | |
| CN117172996B (en) | Microbial activity identification monitoring method and system for ecological environment restoration | |
| CN114266404B (en) | An early warning system for site pollution in a chemical industry park | |
| Wu et al. | Optimal selection and placement of green infrastructure in urban watersheds for PCB control | |
| CN117909913A (en) | Agricultural non-point source pollution data management method, system, equipment and medium | |
| CN118169348A (en) | An AI-based intelligent assessment method and system for groundwater pollution | |
| Yang et al. | An effective multi-objective optimization approach for groundwater remediation considering the coexisting uncertainties of aquifer parameters | |
| Englund et al. | Conditional simulation: practical application for sampling design optimization | |
| Sabzipour et al. | Evaluation and optimal redesigning of river water-quality monitoring networks (RWQMN) using geostatistics approach (case study: Karun, Iran) | |
| Leichombam et al. | New hybrid optimization methodology to identify pollution sources considering the source locations and source flux as unknown | |
| CN102992417A (en) | Decision-making method for in-situ remediation of oil-contaminated underground water | |
| CN118228606A (en) | Online quick pollution prediction method for polluted land block based on machine learning, electronic equipment and storage medium | |
| Liu et al. | Assessment of the effects of total emission control policies on surface water quality in China: 2004 to 2014 | |
| CN117670063A (en) | Indirect index-based organic pollutant online monitoring method | |
| Wu et al. | A Markov‐based model for predicting the development trend of soil microbial communities in saline‐alkali land in Wudi County | |
| Zhou et al. | A framework for spatial correlations between industrial pollution sources and groundwater vulnerabilities based on machine learning and spatial cluster analysis: Implications for risk control | |
| Hagedorn et al. | Assessing risk of groundwater pollution exposure from sea level rise in California | |
| Agarwal et al. | An inflated probability model for the adult male migrants |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |