Space-time risk identification method and device for multiple types of potential pollution areas in industrial park, medium and product
By acquiring and processing multi-source heterogeneous data and using deep learning models for data interpretation and risk assessment, the shortcomings of traditional industrial park risk assessment methods in terms of efficiency, accuracy and long-term considerations are solved, and the rapid and efficient risk identification and evaluation of multiple types of potential polluted areas in industrial parks are achieved, providing technical support for park management.
Patent Information
- Application Number
- CN202411814923.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-11
- Publication Date
- 2025-04-04
AI Technical Summary
The traditional risk assessment method for potential pollution sources in industrial parks has defects in cost, efficiency, timeliness and accuracy, and lacks consideration of the superposition of long-term historical risks, which leads to insufficient guiding significance for the risk control work of specific potential pollution areas.
By acquiring and processing multi-source heterogeneous data, including long-term submeter-level remote sensing images, surrounding area point of interest data, environmental impact assessment reports of equipment and facilities, the data is interpreted using deep learning semantic segmentation models, and combining risk assessment index system and geographic information system software, the risk levels of multiple types of potential pollution areas in industrial parks are identified and evaluated.
It has achieved rapid and efficient identification and risk assessment of multiple types of potential polluted areas in the industrial park, and can conduct annual cumulative risk assessment, which will help analyze risk trend changes and provide technical support for the park management department to formulate targeted risk management plans.
Smart Images
Figure CN119761814A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of risk identification and management of industrial parks, and in particular to a method, equipment, medium and product for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park. Background Art
[0002] In recent years, soil and groundwater pollution in industrial parks has become increasingly serious. Therefore, rapid identification and accurate assessment of soil and groundwater pollution risks in industrial parks has become an important task in current pollution prevention and control work.
[0003] Traditional regional risk assessment of potential pollution sources mainly revolves around the collection and analysis of monitoring data, mainly based on invasive sampling-laboratory analysis-statistical analysis, and is highly dependent on the spatial distribution of sampling points. It does not make sufficient use of the multi-source heterogeneous environmental data accumulated by the industrial park over the years, and has defects in terms of survey cost, efficiency, timeliness and accuracy. In recent years, the assessment objects and indicators have been targeted at large-scale areas such as industrial parks and polluted plots, and the values of indicator calculations are mostly taken from the current or recent years. There is a lack of consideration of the superposition of long-term historical risks, and the assessment results are insufficient for guiding the risk control of specific potential pollution areas in industrial parks. Therefore, a method is needed to quickly identify multiple types of potential pollution areas and accurately assess their risk size, so as to provide a reference for pollution tracing and industrial park management departments to formulate specific risk control plans. Summary of the invention
[0004] The purpose of this application is to provide a method, equipment, medium and product for identifying the spatiotemporal risks of multiple types of potential pollution areas in an industrial park, which can quickly and efficiently identify the risk levels of multiple types of potential pollution areas in the park.
[0005] To achieve the above objectives, this application provides the following solutions:
[0006] In a first aspect, the present application provides a method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park, the method comprising:
[0007] Obtain multi-source heterogeneous data of the target industrial park; the multi-source heterogeneous data includes: long-term sub-meter remote sensing images, data of points of interest in the surrounding area, environmental impact assessment reports of equipment and facilities in multiple types of potential pollution areas, range vector data, and pollution-related report files;
[0008] Convert multi-source heterogeneous data into structured and unstructured data;
[0009] The structured data is processed in combination with the pollution risk factors of multiple types of potential pollution areas scattered in the target industrial park to obtain the risk attribute information of multiple types of potential pollution areas scattered in the target industrial park;
[0010] The unstructured data is processed in combination with the industry characteristics of the target industrial park to obtain the overall risk attribute information of the target industrial park;
[0011] Using the semantic segmentation model of deep learning, the long-term sub-meter remote sensing images of the target industrial park are interpreted to identify multiple types of potential pollution areas in the target industrial park;
[0012] According to the constructed risk assessment index system, risk attribute information of multiple types of potential pollution areas, overall risk attribute information of the target industrial park and identification results of multiple types of potential pollution areas, a risk assessment model is used to obtain the risk level; and the risk level is visualized through geographic information system software; the risk assessment model is used to take multiple types of potential pollution areas as risk assessment objects, combine the risk attribute information of multiple types of potential pollution areas and the overall risk attribute information of the target industrial park to determine the risks of soil and groundwater pollution and sensitive receptors being affected in multiple types of potential pollution areas, and determine the risk level according to the risk assessment index system; the sensitive receptors include people in the target industrial park and the surrounding environment.
[0013] Optionally, the method for processing structured data specifically includes: spatial benchmark unification, key attribute extraction and data cleaning.
[0014] Optionally, contamination risk factors include: operating time, processing / production capacity, process, number of sealing points, and anti-seepage measures.
[0015] Optionally, the method for processing unstructured data specifically includes: cleaning non-demand data, and extracting pollution-related entities and attributes.
[0016] Optionally, the industry characteristics of the target industrial park include: industry category, emergency plan and management capabilities.
[0017] Optionally, the deep learning semantic segmentation model specifically includes: a UNet model or a DeepLab series model.
[0018] In a second aspect, the present application provides a device for identifying spatiotemporal risks of multiple types of potential contaminated areas in an industrial park, and the device for identifying spatiotemporal risks of multiple types of potential contaminated areas in an industrial park includes:
[0019] A data acquisition module is used to acquire multi-source heterogeneous data of the target industrial park; the multi-source heterogeneous data includes: long-term sub-meter remote sensing images, data of points of interest in the surrounding area, environmental impact assessment reports of equipment and facilities in multiple types of potential pollution areas, range vector data, and pollution-related report files;
[0020] Data conversion module, used to convert multi-source heterogeneous data into structured data and unstructured data;
[0021] The first data processing module is used to process the structured data in combination with the pollution risk factors of multiple types of potential pollution areas dispersed in the target industrial park to obtain risk attribute information of multiple types of potential pollution areas dispersed in the target industrial park;
[0022] The second data processing module is used to process the unstructured data in combination with the industry characteristics of the target industrial park to obtain the overall risk attribute information of the target industrial park;
[0023] The recognition module is used to interpret the long-term sub-meter remote sensing images of the target industrial park using the semantic segmentation model of deep learning, and identify multiple types of potential pollution areas in the target industrial park;
[0024] The risk level determination module is used to obtain the risk level by using the risk assessment model according to the constructed risk assessment index system, the risk attribute information of multiple types of potential pollution areas, the overall risk attribute information of the target industrial park and the identification results of multiple types of potential pollution areas; and visualize the risk level through geographic information system (GIS) software; the risk assessment model is used to take multiple types of potential pollution areas as risk assessment objects, combine the risk attribute information of multiple types of potential pollution areas and the overall risk attribute information of the target industrial park to determine the risk of soil and groundwater pollution and sensitive receptors being affected in multiple types of potential pollution areas, and determine the risk level according to the risk assessment index system.
[0025] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park.
[0026] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park.
[0027] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park.
[0028] According to the specific embodiments provided in this application, this application has the following technical effects:
[0029] The present application provides a method, equipment, medium and product for identifying the spatiotemporal risks of multiple types of potential pollution areas in an industrial park. The method improves the value density of the data by fully mining the multi-source heterogeneous data accumulated over many years in the target industrial park, converting it into structured and unstructured data and processing them separately. The semantic segmentation model based on deep learning is used to intelligently interpret the long-term sub-meter remote sensing images of the target industrial park, so as to realize the rapid identification of historical and existing multiple types of potential pollution areas in the park. A risk assessment model is established for the identified multiple types of potential pollution areas, and the risks of soil and groundwater pollution and sensitive receptors being affected in multiple types of potential pollution areas are obtained for the processed multi-source heterogeneous data and the constructed risk assessment index system, and the risk level is determined according to the risk assessment index system. The present application can quickly and efficiently identify the risk levels of multiple types of potential pollution areas in the park, realize the cumulative risk assessment of multiple types of potential pollution areas year by year, help analyze the changes in risk trends, and provide technical support for the park management department to formulate targeted risk control plans. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0031] Figure 1 This is a schematic diagram of a flow chart of a method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park in one embodiment of the present application;
[0032] Figure 2 This is a schematic diagram of the interpretation results of the local multi-type potential pollution areas in a certain industrial park in the embodiment of the present application;
[0033] Figure 3 This is a schematic diagram of the risk classification results of multiple types of potential pollution areas in a certain industrial park in the embodiment of the present application. DETAILED DESCRIPTION
[0034] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0035] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.
[0036] In an exemplary embodiment, Figure 1 As shown, a method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park is provided, and the method includes the following S101 to S106. Among them:
[0037] S101, obtaining multi-source heterogeneous data of the target industrial park; the multi-source heterogeneous data includes: long-term sub-meter remote sensing images, data of points of interest in the surrounding area, environmental impact assessment reports of equipment and facilities in multiple types of potential pollution areas, range vector data, and pollution-related report files;
[0038] S101 specifically includes:
[0039] Obtain long-term sub-meter remote sensing images of the target industrial park through the China Resources Satellite Application Center;
[0040] Obtaining Point of Interest (POI) data in the surrounding area of the target industrial park through the online map service API; the POI data in the surrounding area includes the name and location information of the surrounding sensitive receptors;
[0041] Obtain environmental impact assessment reports of equipment and facilities in various types of potential pollution areas in the target industrial park through the public information on the official website of the park;
[0042] Through communication with the management departments and local environmental protection bureaus in the target industrial parks, on-site investigations, and personnel interviews, we obtained pollution-related report documents such as the target industrial park scope vector data, soil pollution status survey reports in key industrial areas, multi-year soil and groundwater pollution status survey reports, pollution source survey reports, and annual reports on pollutant discharge permits.
[0043] S102, converting multi-source heterogeneous data into structured data and unstructured data;
[0044] Among the multi-source heterogeneous data, data with fixed formats such as POI data, range vector data, soil and groundwater monitoring data in environmental impact assessment reports and pollution-related report files, and pollution risk-related attribute information corresponding to potential pollution areas such as tanks, pools, devices and storage yards are converted into structured data, and text information in report files is converted into unstructured data.
[0045] S103, processing the structured data in combination with the pollution risk factors of multiple types of potential pollution areas dispersed in the target industrial park to obtain risk attribute information of the multiple types of potential pollution areas dispersed in the target industrial park; the pollution risk factors include but are not limited to: operating time, processing / production capacity, process, number of sealing points and anti-seepage measures; the structured data includes vector data and table data;
[0046] The specific methods for processing structured data include: spatial benchmark unification, key attribute extraction and data cleaning.
[0047] The specific process of processing structured data is as follows:
[0048] For range vector data, the spatial reference of the range vector data is unified according to the coordinate system of the acquired remote sensing image.
[0049] For the attribute information of multiple types of potential pollution areas in the table data, based on the pollution risk factors that may be involved in potential pollution areas such as tanks, pools, equipment and yards scattered in the park, the attribute data that are not related to the soil and groundwater pollution risks are eliminated.
[0050] Import POI data, monitoring data and attribute information of multiple types of potential pollution areas into the relational database system, clean missing data, erroneous data and duplicate data through command operations contained in the database, and automatically match, complete and merge multiple data tables containing different attribute information of the same potential pollution areas into one table to form a database of risk-related attribute information of multiple types of potential pollution areas.
[0051] In this embodiment, since the monitoring data includes multiple soil and groundwater monitoring indicators, the soil and water quality indicators are screened according to relevant policy standards and industry pollution characteristics, and the monitoring data are spatially interpolated to increase data density.
[0052] S104, processing the unstructured data in combination with the industry characteristics of the target industrial park to obtain the overall risk attribute information of the target industrial park; the industry characteristics of the target industrial park include but are not limited to: industry category, emergency plan and management capabilities.
[0053] The methods for processing unstructured data specifically include: cleaning non-demand data and extracting pollution-related entities and attributes.
[0054] For the text information in the environmental impact assessment report and pollution-related report documents, combined with the pollution-related characteristics of the industry to which the target industrial park belongs, including industry category, emergency plan, management capabilities, etc., non-demand data cleaning is carried out, and the soil and groundwater pollution-related entities and their attributes in the text are extracted. Then, the correlation of similar attributes of the entities is verified and the attribute domains of some entities are discretized. Finally, the characteristic attributes of some entities are extracted to obtain the attribute information related to the overall risk of the target industrial park.
[0055] The non-demand data cleaning operation in this embodiment deletes text information with little relevance to soil and groundwater pollution risks, such as sampling plans and quality control, water intake and use plans, and atmospheric control plan descriptions; extracts entities such as hydrogeology, leakage detection, maintenance and repair, and their corresponding detailed values, phrases, or overall summary descriptions; performs correlation verification on similar attributes of entities to check whether the information they express is consistent; divides the attribute domain of some entities into several sub-intervals, places the values, phrases, or overviews in the attributes into corresponding sub-intervals, divides the attribute domain into several levels, and converts continuous variables into discrete variables. Specifically, for the prevention and control measures of a certain device, its attribute value is the construction of cofferdams, diversion ditches, accident emergency pools, and roof coverage, and the attribute value is divided into the sub-interval of complete prevention and control facilities; for entities such as hydrogeology, the attributes contained therein include soil layer soil quality, aeration zone soil quality, saturated zone soil quality, etc., first assign values to the sub-intervals after the above attribute domains are discretized, and then perform dimensionality reduction through principal component analysis to avoid attribute redundancy, and finally obtain attribute information related to the overall risk of the park.
[0056] S105, using the semantic segmentation model of deep learning, interpret the long-term sub-meter remote sensing images of the target industrial park to identify multiple types of potential pollution areas in the target industrial park; the semantic segmentation model of deep learning specifically includes: UNet model or DeepLab series model.
[0057] Obtain long-term sub-meter remote sensing images of the target industrial park, and then include:
[0058] Perform pre-processing of remote sensing images such as radiation calibration, orthorectification and image fusion.
[0059] The remote sensing images are batch-cropped into 512×512 pixels with a sliding window and an overlap rate of 10%, and pictures with clear target areas and obvious features are screened out to facilitate model training.
[0060] Perform data enhancement on the segmented images; data enhancement includes operations such as mirroring, rotation, and blurring.
[0061] Potentially contaminated areas such as tanks, pools, equipment and storage yards in the image are labeled to create a sample set, of which 80% is used as a training set, 10% as a validation set, and 10% as a test set.
[0062] Based on the PyTorch 1.7 deep learning framework, the training set was input into the UNet semantic segmentation model for model training, and the model hyperparameter settings were optimized through the validation set. Finally, the model results were evaluated on the test set through overall accuracy, average intersection-over-union ratio, and F1 score. Figure 2As shown in the figure, the spatial location distribution and boundaries of potential pollution areas such as tanks and devices are obtained. By comparing the recognition results of long-term remote sensing images, the changes in potential pollution areas can be obtained and the evolution of the production layout of the park can be analyzed.
[0063] S106, based on the constructed risk assessment index system, the risk attribute information of multiple types of potential pollution areas, the overall risk attribute information of the target industrial park, and the identification results of multiple types of potential pollution areas, a risk assessment model is used to obtain the risk level; and the risk level is visualized through geographic information system software; the risk assessment model is used to take multiple types of potential pollution areas as risk assessment objects, and combine the risk attribute information of multiple types of potential pollution areas and the overall risk attribute information of the target industrial park to determine the risk of soil and groundwater pollution in multiple types of potential pollution areas and the risk of sensitive receptors being affected, and determine the risk level according to the risk assessment index system. The sensitive receptors are not limited to personnel and surrounding environment in the target industrial park;
[0064] The risk assessment index system is constructed based on "source-pathway-receptor"; based on the three elements of "source-pathway-receptor" risk, the first-level indicators of the risk assessment index system include the risk of leakage of equipment and facilities, the difficulty of pollutant migration and transformation, and the vulnerability of risk receptors. The second-level indicators of the risk assessment index system are determined as the existence years, the number of annual failures, the risk of reaction process, anti-corrosion and anti-seepage measures, the ratio of the total amount of hazardous materials to the critical amount, the frequency of maintenance and repair, the number of sealing points, the number of environmental pollution accidents and chemical leakages, the surface coverage, the prevention and control of environmental pollution, the persistence of potential pollutants, the volatility of potential pollutants, the mobility of potential pollutants, the distance from the nearest sensitive point, the harmful effects of potential pollutants on human health, the number of equipment and facility operation and maintenance managers, the industry category, the natural anti-seepage performance of the site, the implementation rate of clean production audits, the standardization of environmental protection records, the perfection of environmental management capabilities, and the perfection of the construction of environmental risk prevention and control systems.
[0065] In this embodiment, in order to further screen out representative secondary indicators, the secondary indicators are determined by cluster analysis, principal component analysis and other methods. The quantitative indicators include years of existence, annual number of failures, number of sealing points, mobility of potential pollutants, distance from the nearest sensitive point, harmful effects of potential pollutants on human health, and number of equipment and facility operation and maintenance managers. The qualitative indicators include anti-corrosion and anti-seepage measures, surface coverage, environmental pollution prevention and control, industry category, natural anti-seepage performance of the site, and the degree of perfection of environmental management capabilities.
[0066] This embodiment calculates, grades and assigns points to each secondary indicator according to relevant literature and standard specifications, as shown in Table 1.
[0067] Table 1 Calculation, classification and scoring method of risk assessment index of potential contaminated area in the embodiment
[0068]
[0069]
[0070]
[0071]
[0072] The indicator weights are calculated by analytic hierarchy process and entropy weight method respectively, and the mean is taken to determine the weight of each indicator.
[0073] Through the weighted summation method, risk scores are calculated for various types of potential pollution areas such as tank areas, pools, equipment and yards in the target industrial park. The higher the score, the greater the risk. The risk levels are divided into high, medium and low levels according to the distribution of risk scores.
[0074] In this embodiment, the risk score interval is divided into three levels using the equal interval method, divided into high, medium and low risk levels, and the risk classification results of potential pollution areas in some areas of the park are obtained.
[0075] In order to verify the accuracy of the risk assessment results of this application, the total excess multiples of pollutants in the soil and groundwater of each potential pollution area are divided into three levels using the equal interval method, namely high, medium and low risk levels, which are compared with the risk level results of this application to verify the accuracy of the assessment.
[0076] In the GIS software, select the appropriate color band and output the calculated risk scores of potential contaminated areas such as tank areas, pools, equipment and storage yards in the form of a map; Figure 3 In order to obtain the risk scores of different potential pollution areas in a certain industrial park through this application, the GIS software is used to visualize the risk value distribution diagram.
[0077] The method provided in the embodiment of the present application realizes the rapid identification of historical and existing multi-type potential pollution areas in the industrial park by combining multi-source heterogeneous data and deep learning models in the industrial park. It comprehensively considers the overall risk of the park and the soil and groundwater pollution risks of various small-scale potential pollution areas in the park, and this method can be applied to the long time scale, which can realize the year-on-year cumulative and refined risk assessment of equipment and facilities that may have the risk of pollution leakage. It is helpful for the analysis of risk trend changes and provides technical support for the park management department to formulate targeted risk control plans.
[0078] Based on the same inventive concept, the embodiment of the present application also provides a device for identifying the spatiotemporal risks of multiple types of potential contaminated areas in an industrial park for implementing the method for identifying the spatiotemporal risks of multiple types of potential contaminated areas in an industrial park mentioned above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the device for identifying the spatiotemporal risks of multiple types of potential contaminated areas in one or more industrial parks provided below can be referred to the limitations of the method for identifying the spatiotemporal risks of multiple types of potential contaminated areas in an industrial park above, and will not be repeated here.
[0079] In an exemplary embodiment, a device for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park is provided, including:
[0080] A data acquisition module is used to acquire multi-source heterogeneous data of the target industrial park; the multi-source heterogeneous data includes: long-term sub-meter remote sensing images, data of points of interest in the surrounding area, environmental impact assessment reports of equipment and facilities in multiple types of potential pollution areas, range vector data, and pollution-related report files;
[0081] Data conversion module, used to convert multi-source heterogeneous data into structured data and unstructured data;
[0082] The first data processing module is used to process the structured data in combination with the pollution risk factors of multiple types of potential pollution areas scattered in the industrial park to obtain risk attribute information of multiple types of potential pollution areas scattered in the target industrial park;
[0083] The second data processing module is used to process the unstructured data in combination with the industry characteristics of the target industrial park to obtain the overall risk attribute information of the target industrial park;
[0084] The recognition module is used to interpret the long-term sub-meter remote sensing images of the target industrial park using the semantic segmentation model of deep learning, and identify multiple types of potential pollution areas in the target industrial park;
[0085] The risk level determination module is used to obtain the risk level by using the risk assessment model according to the constructed risk assessment index system, the risk attribute information of multiple types of potential pollution areas, the overall risk attribute information of the target industrial park and the identification results of multiple types of potential pollution areas; and visualize the risk level through geographic information system software; the risk assessment model is used to take multiple types of potential pollution areas as risk assessment objects, combine the risk attribute information of multiple types of potential pollution areas and the overall risk attribute information of the target industrial park to determine the risk of soil and groundwater pollution and sensitive receptors being affected in multiple types of potential pollution areas, and determine the risk level according to the risk assessment index system.
[0086] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park is implemented.
[0087] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0088] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0089] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0090] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0091] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.
[0092] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.
[0093] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0094] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. A method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park, characterized in that: The method for identifying spatiotemporal risks of multiple types of potential pollution areas in the industrial park includes: Obtain multi-source heterogeneous data of the target industrial park; the multi-source heterogeneous data includes: long-term sub-meter remote sensing images, data of points of interest in the surrounding area, environmental impact assessment reports of equipment and facilities in multiple types of potential pollution areas, range vector data, and pollution-related report files; Convert multi-source heterogeneous data into structured and unstructured data; The structured data is processed in combination with the pollution risk factors of multiple types of potential pollution areas scattered in the target industrial park to obtain the risk attribute information of multiple types of potential pollution areas scattered in the target industrial park; The unstructured data is processed in combination with the industry characteristics of the target industrial park to obtain the overall risk attribute information of the target industrial park; Using the semantic segmentation model of deep learning, the long-term sub-meter remote sensing images of the target industrial park are interpreted to identify multiple types of potential pollution areas in the target industrial park; According to the constructed risk assessment index system, risk attribute information of multiple types of potential pollution areas, overall risk attribute information of the target industrial park and identification results of multiple types of potential pollution areas, a risk assessment model is used to obtain the risk level; and the risk level is visualized through geographic information system software; the risk assessment model is used to take multiple types of potential pollution areas as risk assessment objects, combine the risk attribute information of multiple types of potential pollution areas and the overall risk attribute information of the target industrial park to determine the risks of soil and groundwater pollution and sensitive receptors being affected in multiple types of potential pollution areas, and determine the risk level according to the risk assessment index system; the sensitive receptors include people in the target industrial park and the surrounding environment.
2. The method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park according to claim 1 is characterized in that: The processing of structured data specifically includes: spatial benchmark unification, key attribute extraction and data cleaning.
3. The method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park according to claim 1 is characterized in that: Contamination risk factors include: operating time, processing / production capacity, process, number of sealing points and anti-seepage measures.
4. The method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park according to claim 1 is characterized in that: The processing of unstructured data specifically includes: cleaning of non-required data and extraction of pollution-related entities and attributes.
5. The method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park according to claim 1 is characterized in that: The industry characteristics of the target industrial park include: industry category, emergency plan and management capabilities.
6. The method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park according to claim 1 is characterized in that: The semantic segmentation models of deep learning specifically include: UNet model or DeepLab series model.
7. A device for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park, characterized in that: The equipment for identifying the spatiotemporal risks of various types of potential pollution areas in the industrial park includes: A data acquisition module is used to acquire multi-source heterogeneous data of the target industrial park; the multi-source heterogeneous data includes: long-term sub-meter remote sensing images, data of points of interest in the surrounding area, environmental impact assessment reports of equipment and facilities in multiple types of potential pollution areas, range vector data, and pollution-related report files; Data conversion module, used to convert multi-source heterogeneous data into structured data and unstructured data; The first data processing module is used to process the structured data in combination with the pollution risk factors of multiple types of potential pollution areas dispersed in the target industrial park to obtain risk attribute information of multiple types of potential pollution areas dispersed in the target industrial park; The second data processing module is used to process the unstructured data in combination with the industry characteristics of the target industrial park to obtain the overall risk attribute information of the target industrial park; The recognition module is used to interpret the long-term sub-meter remote sensing images of the target industrial park using the semantic segmentation model of deep learning, and identify multiple types of potential pollution areas in the target industrial park; The risk level determination module is used to obtain the risk level by using the risk assessment model according to the constructed risk assessment index system, the risk attribute information of multiple types of potential pollution areas, the overall risk attribute information of the target industrial park and the identification results of multiple types of potential pollution areas; and visualize the risk level through geographic information system software; the risk assessment model is used to take multiple types of potential pollution areas as risk assessment objects, combine the risk attribute information of multiple types of potential pollution areas and the overall risk attribute information of the target industrial park to determine the risk of soil and groundwater pollution and sensitive receptors being affected in multiple types of potential pollution areas, and determine the risk level according to the risk assessment index system.
8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the spatiotemporal risk identification method for multiple types of potential pollution areas in an industrial park as described in any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park described in any one of claims 1 to 6 is implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for identifying spatiotemporal risks of multiple types of potential pollution areas in an industrial park described in any one of claims 1 to 6 is implemented.