A groundwater pollution monitoring method for surface pollution sources

Abstract

This invention provides a groundwater pollution monitoring method targeting surface pollution sources. A neural network model is trained based on a first dataset to obtain a water pollution monitoring model. The first dataset includes historical normal water resistivity characteristics of a groundwater monitoring zone, located downstream of the pollution source based on groundwater flow direction. Based on the water pollution monitoring model, abnormal data in a second dataset is identified, and potential pollution risk areas are marked according to the identified abnormal data. The second dataset includes real-time water resistivity characteristics of the groundwater monitoring zone. This invention's method achieves systematic and intelligent, accurate, and timely monitoring and early warning of groundwater pollution from surface pollution sources. In particular, it can identify and analyze large-scale local potential pollution risk areas and capture the dynamic migration process of pollution plumes.

Description

Technical Field

[0001] This invention relates to the field of environmental monitoring technology, and in particular to a method for monitoring groundwater pollution from surface pollution sources. Background Technology

[0002] One of the sources of groundwater pollution is leachate, which is complex in composition and highly toxic. Landfills typically produce leachate containing high concentrations of organic pollutants, heavy metals, ammonia nitrogen, and persistent chemicals during the long-term stabilization process. Once these pollutants breach the seepage barrier, they will invade the vadose zone and seep into the aquifer, causing irreversible pollution to groundwater resources.

[0003] Groundwater pollution caused by leachate is characterized by its insidious, delayed, and long-term nature, making remediation extremely difficult and costly, and directly threatening regional drinking water safety and ecosystem health. Therefore, actively monitoring for the presence of this type of groundwater pollution is more important than remediation.

[0004] Currently, the main method for monitoring groundwater pollution caused by leachate relies on setting up sparse monitoring wells around surface pollution sources such as landfills, and assessing water quality through regular manual sampling and laboratory analysis.

[0005] However, the biggest drawback of this traditional monitoring method is that it involves setting up sparse monitoring wells around surface pollution sources such as landfills and obtaining results through manual periodic sampling and analysis. This method lacks real-time capability and therefore cannot provide timely early warning for instantaneous leakage events. It may miss identifying pollution and cannot capture the dynamic migration process of pollution plumes, thus offering no auxiliary significance for post-pollution prevention and remediation. Summary of the Invention

[0006] This invention provides a groundwater pollution monitoring method for surface pollution sources. It addresses the shortcomings of existing technologies that rely on sparse monitoring wells around the pollution source and periodic manual sampling and laboratory analysis to assess water quality. These methods lack real-time capabilities and cannot capture the dynamic migration process of pollution plumes. By using high-frequency spherical physical method monitoring data across the entire downstream area of ​​the pollution source, a database is constructed and combined with neural network data analysis and training to identify abnormal groundwater resistivity characteristics. This enables real-time, accurate online monitoring and can identify the process of pollution plumes migrating and spreading with groundwater pollution.

[0007] This invention provides a method for monitoring groundwater pollution from surface pollution sources, comprising the following steps.

[0008] A neural network model is trained based on the first dataset to obtain a water pollution monitoring model; wherein, the first dataset includes historical normal water resistance characteristic data of the groundwater monitoring zone, and the groundwater monitoring zone is established downstream of the pollution source according to the groundwater flow direction; Based on the water pollution monitoring model, abnormal data in the second dataset are identified, and potential pollution risk areas are marked based on the identified abnormal data; wherein the second dataset includes real-time water resistance characteristic data of the groundwater monitoring zone.

[0009] By acquiring real-time water resistance characteristic data through high-density resistivity monitoring zones and combining it with neural network models for anomaly identification, immediate responses to groundwater pollution events can be achieved. This overcomes the shortcomings of traditional manual sampling, such as long cycles and high delays, and improves the real-time performance and sensitivity of monitoring. Utilizing a trained water pollution monitoring model to automatically identify abnormal data enables precise location of potential pollution risk areas within a large monitoring area, improving spatial resolution and the accuracy of pollution source location. Based on high-frequency monitoring data and model analysis, the dynamic process of pollution plumes migrating through groundwater over time can be captured, providing a basis for pollution diffusion prediction and emergency response.

[0010] According to the groundwater pollution monitoring method for surface pollution sources provided by the present invention, the first dataset further includes historical normal environmental data, and the second dataset further includes real-time environmental data.

[0011] According to the present invention, a groundwater pollution monitoring method for surface pollution sources is provided, wherein the environmental data includes groundwater hydrological data and precipitation data.

[0012] According to the present invention, a groundwater pollution monitoring method for surface pollution sources is provided, wherein the method for obtaining the water resistivity characteristic data is as follows: A monitoring time interval is set, and the groundwater monitoring zone is monitored using the high-density resistivity method according to the monitoring time interval to obtain groundwater resistance characteristic data.

[0013] According to the present invention, a groundwater pollution monitoring method for surface pollution sources is provided, wherein marking potential pollution risk areas based on abnormal data in a second dataset further includes: Based on the water pollution analysis model, the third dataset is analyzed to obtain the pollution plume model; wherein, the water pollution analysis model is trained by a neural network model, and the third dataset includes high-density resistivity data, water flow direction data, and water quality data of groundwater in potential pollution risk areas.

[0014] According to the groundwater pollution monitoring method for surface pollution sources provided by the present invention, the third dataset also includes environmental data of potential pollution risk areas, including groundwater hydrological data and precipitation data.

[0015] The present invention also provides a groundwater pollution monitoring device for surface pollution sources, comprising the following modules: The model training module is used to train a neural network model based on the first dataset to obtain a water pollution monitoring model; wherein, the first dataset includes historical normal water resistance characteristic data of the groundwater monitoring zone, and the groundwater monitoring zone is established downstream of the pollution source according to the groundwater flow direction; The identification module is used to identify abnormal data in the second dataset according to the water pollution monitoring model, and to mark potential pollution risk areas according to the identified abnormal data; wherein the second dataset includes real-time water resistance characteristic data of the groundwater monitoring zone.

[0016] The present invention also provides an electronic device, including 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 groundwater pollution monitoring method for surface pollution sources as described above.

[0017] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the groundwater pollution monitoring method for surface pollution sources as described above.

[0018] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the groundwater pollution monitoring method for surface pollution sources as described above.

[0019] This invention provides a groundwater pollution monitoring method for surface pollution sources. The method establishes a groundwater monitoring zone downstream of the pollution source based on groundwater flow direction; sets monitoring time intervals; and monitors the groundwater resistivity characteristics of the monitoring zone using the high-density resistivity method and the monitoring time intervals. A database is constructed based on the groundwater resistivity data. A neural network is used to identify abnormal groundwater resistivity data from the database, and potential pollution risk areas are marked based on the abnormal groundwater resistivity data. The potential pollution risk area is downstream of the pollution source corresponding to the abnormal groundwater resistivity data. This method achieves systematic and intelligent monitoring and timely early warning of groundwater pollution from surface pollution sources, especially capable of identifying and analyzing large-scale local potential pollution risk areas and capturing the dynamic migration process of pollution plumes. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 This is one of the flowcharts of the groundwater pollution monitoring method for surface pollution sources provided by the present invention.

[0022] Figure 2 This is a schematic diagram of the groundwater monitoring zone layout in the groundwater pollution monitoring method for surface pollution sources provided by the present invention.

[0023] Figure 3 This is a schematic diagram illustrating the application of the groundwater monitoring zone in the groundwater pollution monitoring method for surface pollution sources provided by this invention.

[0024] Figure 4 This is a schematic diagram of the process of an artificial intelligence-based groundwater pollution monitoring technology system for landfills, based on the groundwater pollution monitoring method for surface pollution sources provided by the present invention.

[0025] Figure 5 This is a schematic diagram of a one-way barrier, monitoring, and intelligent control system for groundwater pollution monitoring methods targeting surface pollution sources provided by the present invention.

[0026] Figure 6 This is a schematic diagram of the groundwater pollution monitoring device for surface pollution sources provided by the present invention.

[0027] Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0029] The following is combined Figures 1 to 7 This invention describes a groundwater pollution monitoring method for surface pollution sources.

[0030] Figure 1 This is one of the flowcharts illustrating the groundwater pollution monitoring method for surface pollution sources provided by this invention, such as... Figure 1As shown, the method includes the following: Step 101: Train a neural network model based on the first dataset to obtain a water pollution monitoring model; wherein, the first dataset includes historical normal water resistance characteristic data of the groundwater monitoring zone, and the groundwater monitoring zone is established downstream of the pollution source according to the groundwater flow direction; Step 102: Based on the water pollution monitoring model, identify abnormal data in the second dataset, and mark potential pollution risk areas based on the identified abnormal data; wherein the second dataset includes real-time water resistance characteristic data of the groundwater monitoring zone.

[0031] This invention provides a groundwater pollution monitoring method for surface pollution sources. The method establishes a groundwater monitoring zone downstream of the pollution source based on groundwater flow direction. A monitoring time interval is set, and groundwater resistivity characteristics of the monitoring zone are monitored using a high-density resistivity method and the monitoring time interval. A database is constructed based on the groundwater resistivity data. A neural network is used to identify abnormal groundwater resistivity data from the database, and potential pollution risk areas are marked based on these abnormal groundwater resistivity data. The potential pollution risk area is downstream of the pollution source corresponding to the abnormal groundwater resistivity data. This method achieves systematic and intelligent, accurate, and timely monitoring and early warning of groundwater pollution from surface pollution sources, especially capable of identifying and analyzing large-scale local potential pollution risk areas and capturing the dynamic migration process of pollution plumes.

[0032] Optionally, in another embodiment of the groundwater pollution monitoring method for surface pollution sources provided by the present invention, the first dataset further includes historical normal environmental data, and the second dataset further includes real-time environmental data.

[0033] By incorporating historical and real-time environmental data, the robustness of the model to complex environmental changes is enhanced, misjudgments caused by fluctuations in natural conditions are reduced, and the model's environmental adaptability is improved. By combining environmental factors and water resistance data, the multidimensional impact mechanism of pollution migration is more comprehensively reflected, thereby improving the accuracy and reliability of early warning.

[0034] Optionally, in another embodiment of the groundwater pollution monitoring method for surface pollution sources provided by the present invention, the environmental data in the second dataset includes groundwater hydrological data and precipitation data.

[0035] By explicitly including groundwater hydrological data and precipitation data as environmental factors, the model can better reflect actual hydrogeological conditions, improve the realism and predictive ability of pollution migration simulation, and refine environmental impact parameters. The driving effect of external events such as precipitation on groundwater pollution can be considered to achieve more sensitive pollution event early warning and dynamic monitoring, and enhance the system's response capability.

[0036] Optionally, in another embodiment of the groundwater pollution monitoring method for surface pollution sources provided by the present invention, the method for obtaining the water resistivity characteristic data is as follows: A monitoring time interval is set, and the groundwater monitoring zone is monitored using the high-density resistivity method according to the monitoring time interval to obtain groundwater resistance characteristic data.

[0037] By setting monitoring time intervals and using the high-density resistivity method, the system can achieve automated, high-frequency data acquisition, significantly improving monitoring efficiency and data continuity, and realizing high-frequency automated monitoring. Automated monitoring reduces reliance on manual sampling, lowers long-term monitoring costs, and improves the spatiotemporal resolution of the data.

[0038] Optionally, in another embodiment of the groundwater pollution monitoring method for surface pollution sources provided by the present invention, the step of marking potential pollution risk areas based on abnormal data in the second dataset further includes: Based on the water pollution analysis model, the third dataset is analyzed to obtain the pollution plume model; wherein, the water pollution analysis model is trained by a neural network model, and the third dataset includes high-density resistivity data, water flow direction data, and water quality data of groundwater in potential pollution risk areas.

[0039] After identifying potential pollution risk areas, a pollution plume model is further constructed through a water pollution analysis model to intuitively display the spatial distribution and migration path of pollutants, thus realizing pollution plume modeling and visualization. The pollution plume model can provide a scientific basis for pollution source control and remediation projects, support the whole-chain management from monitoring to treatment, and support refined control decisions.

[0040] Optionally, in another embodiment of the groundwater pollution monitoring method for surface pollution sources provided by the present invention, the third dataset further includes environmental data of potential pollution risk areas, including groundwater hydrological data and precipitation data.

[0041] By integrating environmental data with multi-source monitoring data, the pollution plume model can more comprehensively reflect the multi-factor impact of pollution migration, thereby improving the accuracy of model predictions and its practical application value.

[0042] Specifically, Figure 2 This is a schematic diagram of the groundwater monitoring zone layout in the groundwater pollution monitoring method for surface pollution sources provided by this invention. Figure 3 This is a schematic diagram illustrating the application of the groundwater monitoring zone in the groundwater pollution monitoring method for surface pollution sources provided by this invention.

[0043] according to Figure 2 and Figure 3 The groundwater pollution monitoring method for surface pollution sources provided by this invention, in practical application, includes two stages, wherein: The first phase includes: (1) Based on the groundwater flow direction, a groundwater monitoring zone is established downstream of the pollution source and groundwater environmental electrical monitoring equipment is installed. This groundwater environmental electrical monitoring equipment is used to monitor groundwater resistance characteristics data. First, high-density resistivity monitoring is conducted every hour to build a background database; second, semi-daily high-density resistivity monitoring is conducted to build a monitoring database. (2) Using neural network processing artificial intelligence technology, integrating environmental data, background database and monitoring database, we can identify areas with abnormal groundwater resistivity data, and preliminarily identify potential pollution risk areas by integrating monitoring data; (3) Construct groundwater monitoring wells in areas with potential pollution risks, install water level monitoring equipment, flow velocity and direction monitoring equipment and on-site rapid water quality screening equipment, and coordinate with high-density resistivity testing and monitoring to collect diverse data; (4) Again, neural network processing artificial intelligence technology is used to further couple high-density resistivity data, groundwater flow direction data, and water quality data to train a model that can identify abnormal groundwater electrical properties of monitoring sections caused by pollution plumes following groundwater flow direction under the influence of environmental factors.

[0044] The second phase includes: High-frequency, high-density resistivity method monitoring is carried out, and artificial intelligence technology is used to process the response to achieve efficient and timely monitoring of groundwater pollution in landfill sites.

[0045] In the first phase, the monitoring frequency can be adjusted rationally based on changes in environmental data and monitoring results, and a database can be built.

[0046] Specifically, Figure 4 This is a schematic diagram of a landfill artificial intelligence-based groundwater pollution monitoring method for surface pollution sources, provided by the present invention, comprising: High-frequency monitoring of groundwater electrical properties of pollution sources and identification of risk zones; Basic database construction and identification of artificial intelligence risk areas; Optimize the construction of groundwater monitoring well networks based on risk zones; Simultaneously conduct high-frequency monitoring of hydrological conditions, high-frequency monitoring of electrical properties, rapid water quality monitoring, and routine testing; A multi-evidence coupling method was used to construct an artificial intelligence identification model for groundwater pollution migration.

[0047] Figure 5This is a schematic diagram of a one-way barrier, monitoring, and intelligent control system for groundwater pollution monitoring of surface pollution sources provided by the present invention. In this system, sparse monitoring wells represent the flow direction of groundwater, and the identification of potential pollution is entrusted to the electrical anomaly characterization of high-density electrical resistivity tomography, which is verified in conjunction with actual water quality test results. Finally, machine learning is used to achieve the effect of accurately and efficiently identifying the occurrence of pollution by comprehensively considering the correlation between changes in the electrical properties of water quality and the direction of water flow from the pollution source.

[0048] Combination Figure 5 The one-way barrier, monitoring and intelligent control system constructs a groundwater pollution risk assessment system by monitoring water quality on both sides of the barrier facility and on the outside of the barrier facility.

[0049] More specifically, this groundwater pollution risk assessment system outputs three different risk warnings based on different monitoring results: high risk, low risk, and no risk.

[0050] The different monitoring results include: (1) The water level within the barrier facility is higher than that outside.

[0051] (2) The groundwater quality test results were within acceptable limits during the period, but the water level within the barrier facility was much lower than that outside, causing groundwater to seep into the control area.

[0052] (3) The water level within the barrier facility is slightly lower than that outside, causing polluted groundwater to seep into the control area.

[0053] (4) The water level within the barrier facility is higher than the required safe groundwater level for the building facility.

[0054] (5) The water level within the barrier facility is much lower than that outside, causing polluted groundwater to seep into the control area.

[0055] Furthermore, the risk warnings output for different monitoring results are as follows: Monitoring results (1) show no risk. Monitoring results (2) and monitoring results (3) output low risk; The monitoring results (4) and (5) indicate a high risk.

[0056] Furthermore, different control measures are set up for different monitoring results, including: Based on the monitoring results (4), and in conjunction with the requirements of the building foundation and the water level outside the barrier zone, the uncontaminated groundwater in the barrier zone is discharged to the downstream flow outside through the one-way barrier facility.

[0057] Based on monitoring results (2), (3) and (5), the rainwater collection facility replenishes groundwater in the barrier area through the infiltration system until the groundwater level within the barrier facility is higher than that outside, preventing groundwater from seeping into the control area.

[0058] This artificial intelligence-based groundwater pollution monitoring method for landfills is a systematic and intelligent approach to achieve accurate and timely early warning of groundwater pollution in landfills and to efficiently and rapidly identify the extent of groundwater pollution over large areas. It integrates high-frequency geophysical monitoring data from the downstream areas of typical pollution sources within the landfill, groundwater flow velocity and direction monitoring data from key local areas, data on meteorological and climatic factors affecting groundwater quality, and groundwater quality monitoring data to construct a large database. Through AI data analysis and training, including multidimensional decomposition, component extraction, and cluster analysis, a groundwater pollution migration and diffusion identification model is built. Timely warnings are issued for situations with high pollution levels and risks, enabling accurate and timely daily management of landfill leakage and groundwater pollution.

[0059] The following describes a groundwater pollution monitoring device for surface pollution sources provided by the present invention. The groundwater pollution monitoring device for surface pollution sources described below and the groundwater pollution monitoring method for surface pollution sources described above can be referred to in correspondence.

[0060] Figure 6 This is a schematic diagram of the groundwater pollution monitoring device for surface pollution sources provided by the present invention, as shown below. Figure 6 As shown, the device includes: The model training module 201 is used to train a neural network model based on the first dataset to obtain a water pollution monitoring model; wherein, the first dataset includes historical normal water resistance characteristic data of the groundwater monitoring zone, and the groundwater monitoring zone is established downstream of the pollution source according to the groundwater flow direction; The identification module 202 is used to identify abnormal data in the second dataset according to the water pollution monitoring model, and to mark potential pollution risk areas according to the identified abnormal data; wherein the second dataset includes real-time water resistance characteristic data of the groundwater monitoring zone.

[0061] This invention relates to a groundwater pollution monitoring device for surface pollution sources. It establishes a groundwater monitoring zone downstream of the pollution source based on the groundwater flow direction; sets a monitoring time interval; and monitors the groundwater resistivity characteristics of the monitoring zone using the high-density resistivity method and the monitoring time interval. A database is constructed based on the groundwater resistivity data. A neural network is used to identify abnormal groundwater resistivity data based on the database, and potential pollution risk areas are marked according to the abnormal groundwater resistivity data. The potential pollution risk area is downstream of the pollution source corresponding to the abnormal groundwater resistivity data. This device achieves systematic and intelligent, accurate, and timely monitoring and early warning of groundwater pollution from surface pollution sources, especially capable of identifying and analyzing large-scale local potential pollution risk areas and capturing the dynamic migration process of pollution plumes.

[0062] Optionally, the groundwater pollution monitoring device for surface pollution sources provided by the present invention further includes a groundwater environmental electrical monitoring module, a groundwater level and flow velocity and direction monitoring module, and a water quality analysis module.

[0063] Optionally, the groundwater pollution monitoring device for surface pollution sources provided by the present invention further includes an early warning module, which is used to issue an early warning when abnormal groundwater resistance characteristic data is identified.

[0064] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include: a processor 810, a communications interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communications interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute a groundwater pollution monitoring method targeting surface pollution sources, the method including: A neural network model is trained based on the first dataset to obtain a water pollution monitoring model; wherein, the first dataset includes historical normal water resistance characteristic data of the groundwater monitoring zone, and the groundwater monitoring zone is established downstream of the pollution source according to the groundwater flow direction; Based on the water pollution monitoring model, abnormal data in the second dataset are identified, and potential pollution risk areas are marked based on the identified abnormal data; wherein the second dataset includes real-time water resistance characteristic data of the groundwater monitoring zone.

[0065] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0066] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program that can be stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, the computer is able to execute the groundwater pollution monitoring method for surface pollution sources provided by the above methods, the method comprising: A neural network model is trained based on the first dataset to obtain a water pollution monitoring model; wherein, the first dataset includes historical normal water resistance characteristic data of the groundwater monitoring zone, and the groundwater monitoring zone is established downstream of the pollution source according to the groundwater flow direction; Based on the water pollution monitoring model, abnormal data in the second dataset are identified, and potential pollution risk areas are marked based on the identified abnormal data; wherein the second dataset includes real-time water resistance characteristic data of the groundwater monitoring zone.

[0067] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the groundwater pollution monitoring method for surface pollution sources provided by the methods described above, the method comprising: A neural network model is trained based on the first dataset to obtain a water pollution monitoring model; wherein, the first dataset includes historical normal water resistance characteristic data of the groundwater monitoring zone, and the groundwater monitoring zone is established downstream of the pollution source according to the groundwater flow direction; Based on the water pollution monitoring model, abnormal data in the second dataset are identified, and potential pollution risk areas are marked based on the identified abnormal data; wherein the second dataset includes real-time water resistance characteristic data of the groundwater monitoring zone.

[0068] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0069] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring groundwater pollution from surface pollution sources, characterized in that, include: A neural network model is trained based on the first dataset to obtain a water pollution monitoring model; wherein, the first dataset includes historical normal water resistance characteristic data of the groundwater monitoring zone, and the groundwater monitoring zone is established downstream of the pollution source according to the groundwater flow direction; Based on the water pollution monitoring model, abnormal data in the second dataset are identified, and potential pollution risk areas are marked based on the identified abnormal data; wherein the second dataset includes real-time water resistance characteristic data of the groundwater monitoring zone.

2. The groundwater pollution monitoring method for surface pollution sources according to claim 1, characterized in that, The first dataset also includes historical normal environmental data, and the second dataset also includes real-time environmental data.

3. The groundwater pollution monitoring method for surface pollution sources according to claim 2, characterized in that, The environmental data includes groundwater hydrological data and precipitation data.

4. The groundwater pollution monitoring method for surface pollution sources according to claim 1, characterized in that, The method for obtaining the water resistance characteristic data is as follows: A monitoring time interval is set, and the groundwater monitoring zone is monitored using the high-density resistivity method according to the monitoring time interval to obtain groundwater resistance characteristic data.

5. A method for monitoring groundwater pollution from surface pollution sources according to claim 1, characterized in that, The step of marking potential contamination risk areas based on anomalous data in the second dataset further includes: Based on the water pollution analysis model, the third dataset is analyzed to obtain the pollution plume model; wherein, the water pollution analysis model is trained by a neural network model, and the third dataset includes high-density resistivity data, water flow direction data, and water quality data of groundwater in potential pollution risk areas.

6. A method for monitoring groundwater pollution from surface pollution sources according to claim 5, characterized in that, The third dataset also includes environmental data for potential pollution risk areas, including groundwater hydrological data and precipitation data.

7. A groundwater pollution monitoring device for surface pollution sources, characterized in that, include: The model training module is used to train a neural network model based on the first dataset to obtain a water pollution monitoring model; wherein, the first dataset includes historical normal water resistance characteristic data of the groundwater monitoring zone, and the groundwater monitoring zone is established downstream of the pollution source according to the groundwater flow direction; The identification module is used to identify abnormal data in the second dataset according to the water pollution monitoring model, and to mark potential pollution risk areas according to the identified abnormal data; wherein the second dataset includes real-time water resistance characteristic data of the groundwater monitoring zone.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements a groundwater pollution monitoring method for surface pollution sources as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements a groundwater pollution monitoring method for surface pollution sources as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements a groundwater pollution monitoring method for surface pollution sources as described in any one of claims 1 to 6.

Images