Water quality environment detection method and system based on 5G communication

Abstract

The invention provides a water quality environment detection method and system based on 5G communication, and the method comprises the steps: determining a target detection node through obtaining the spatial distribution data of a mobile detection node in a to-be-detected water area and the water area topographic feature data, and obtaining a detection data set based on the target detection node; heavy metal ion migration tracks in the detection data set are processed, a pollutant diffusion boundary prediction map is generated to simulate and generate a multi-scene diffusion envelope range, and an emergency management and control instruction set is generated based on the multi-scene diffusion envelope range; determining a pollution diffusion trend in combination with the emergency management and control instruction set and the environmental influence factor, and generating a water quality environment detection result based on the pollution diffusion trend; according to the technical scheme, the 5G communication technology and a traditional water quality detection method are effectively combined, automation, refinement and intelligentization of water quality environment detection are achieved, and the water quality management and protection capacity is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of environmental detection technology, and in particular to a water quality environment detection method and system based on 5G communication. Background Art

[0002] Changes in key indicators such as dissolved oxygen, turbidity, and heavy metal ions in current waters directly affect ecological health and quality of life.

[0003] At present, water quality testing mainly relies on fixed monitoring stations and regular manual sampling and analysis. The existing methods have limitations. For example, the spatial distribution density of existing fixed monitoring stations is limited, and testing activities cannot cover the entire water area; manual sampling cycles are long and costly, and it is difficult to achieve a rapid response to sudden pollution incidents. Summary of the Invention

[0004] The embodiments of the present invention provide a water quality environment detection method and system based on 5G communication, which is used to solve the problems in the existing technology that detection activities cannot cover the entire water area; manual sampling cycles are long and costly, and it is difficult to achieve a rapid response to sudden pollution incidents.

[0005] In a first aspect, an embodiment of the present invention provides a water quality environment detection method based on 5G communication, comprising:

[0006] Obtain spatial distribution data of mobile detection nodes and water area terrain feature data in the water area to be tested;

[0007] Determining a target detection node based on the spatial distribution data and the water area topographic feature data, and obtaining a detection data set based on the target detection node;

[0008] Processing the migration trajectories of heavy metal ions in the detection data set to generate a pollutant diffusion boundary prediction map to simulate and generate a multi-scenario diffusion envelope range, and generating an emergency control instruction set based on the multi-scenario diffusion envelope range;

[0009] In combination with the emergency control instruction set and environmental impact factors, the pollution diffusion trend is confirmed, and based on the pollution diffusion trend, the water quality environment detection results are generated.

[0010] Optionally, the heavy metal ion migration trajectories in the detection data set are processed to generate a pollutant diffusion boundary prediction map to simulate and generate a multi-scenario diffusion envelope range. Based on the multi-scenario diffusion envelope range, an emergency control instruction set is generated, including:

[0011] Based on the detection data set, a water quality abnormal diffusion model and a dissolved oxygen distribution map are constructed, and the turbulent diffusion effect of the turbidity gradient field is synergistically coupled using the dissolved oxygen distribution map and the water quality abnormal diffusion model to generate a pollutant migration probability distribution matrix;

[0012] Based on the pollutant migration probability distribution matrix, a three-dimensional hydrodynamic water quality model is constructed to reversely process the pollution source location and emission characteristics of the heavy metal ion migration trajectory and generate a pollutant diffusion boundary prediction map;

[0013] Based on the pollutant diffusion boundary prediction map, a scenario analysis method is used to perform a three-dimensional hydrodynamic coupling simulation of the preset pollution load gradient to obtain a multi-scenario diffusion envelope range. Based on the multi-scenario diffusion envelope range, an emergency control instruction set is generated.

[0014] Optionally, generating an emergency control instruction set based on the multi-scenario diffusion envelope range includes:

[0015] The ecological exposure risk weighted superposition algorithm was used to perform spatial analysis on the diffusion envelope range of the multiple scenarios and the ecological red line area, and the pollutant peak value and spatial coverage rate of sensitive waters under each scenario were obtained;

[0016] Calculate a hydrological cycle correction factor based on the deviation rate between the real-time flow monitoring data and the historical mean data for the same period; dynamically compare the pollutant peak value with the standard peak value of the corresponding pollutant in the surface water environmental quality standard based on the hydrological cycle correction factor to obtain a pollution comparison result;

[0017] When the pollution comparison result meets the preset composite conditions, the pollution source positioning model is triggered to fuse the pollutant migration probability distribution matrix with the real-time monitoring data stream to generate a pollution source confidence interval geo-fence. Based on the pollution source confidence interval geo-fence, an emergency control instruction set is generated. The preset composite conditions include the first condition that the spatial intersection area of the warning area and the drinking water source protection area exceeds the dynamic threshold and the second condition that the pollutant concentration mutation index in the real-time monitoring data stream exceeds the mutation threshold. The dynamic threshold is set according to the pollutant toxicity level and the water supply scale of the water source.

[0018] Optionally, when the pollution comparison result meets a preset composite condition, the pollution source location model is triggered to fuse the pollutant migration probability distribution matrix with the real-time monitoring data stream to generate a pollution source confidence interval geo-fence. Based on the pollution source confidence interval geo-fence, an emergency control instruction set is generated. The preset composite condition includes a first condition that the spatial intersection area ratio of the warning area and the drinking water source protection area exceeds a dynamic threshold and a second condition that the pollutant concentration mutation index in the real-time monitoring data stream exceeds a mutation threshold. The dynamic threshold is set according to the pollutant toxicity level and the water supply scale of the water source, including:

[0019] Using the pollutant toxicity level classification rules and the water source water supply scale classification standards, a dynamic threshold mapping table is constructed. Based on the dynamic threshold mapping table, the area proportion threshold corresponding to the combination is searched to generate a dynamic threshold set. Based on the dynamic threshold set, the spatial intersection area proportion of the warning area and the drinking water source protection area is calculated, where the combination includes the pollutant toxicity level and the water source water supply scale.

[0020] Based on the real-time monitoring data stream, a sliding time window mechanism is used to extract a pollutant concentration time series, so as to calculate a pollutant concentration mutation index based on the pollutant concentration time series;

[0021] If the proportion of the spatial intersection area exceeds the dynamic threshold of the corresponding pollutant toxicity level and the water supply scale of the water source, it is determined that the first condition is met; if the pollutant concentration mutation index exceeds the mutation threshold corresponding to the preset pollutant type, it is determined that the second condition is met;

[0022] When the spatial intersection area ratio satisfies both the first condition and the second condition, the pollution source location model is triggered to fuse the pollutant migration probability distribution matrix with the real-time monitoring data stream to generate a pollution source confidence interval geo-fence;

[0023] Based on the pollution source confidence interval geo-fence, an emergency control instruction set is generated.

[0024] Optionally, based on the pollution source confidence interval geo-fence, an emergency control instruction set is generated, including:

[0025] Generate a list of potential pollution sources within the fence based on the boundary coordinates of the pollution source confidence interval geo-fence, the dynamic threshold set, and pollution source historical data;

[0026] Based on the pollutant concentration mutation index and the water source service population size parameter, adjusting the existing instruction classification rules to obtain adjusted classification rules, and using the adjusted classification rules to generate a hierarchical control instruction set, the hierarchical control instruction set including shutdown instructions, production restriction instructions, and inspection instructions;

[0027] Based on the list of potential pollution sources within the fence and the hierarchical control instruction set, combined with the real-time monitoring data stream and historical risk data, a multi-objective optimization algorithm is used to match the pollution source feature vector with the instruction level to generate an emergency control instruction set. The pollution source feature vector includes an industry type vector and an emission intensity vector.

[0028] Optionally, combining the emergency control instruction set and environmental impact factors to determine the pollution diffusion trend, and generating water quality environment detection results based on the pollution diffusion trend, including:

[0029] Comparing the pollutant diffusion boundary confidence level and the diffusion rate threshold in the emergency control instruction set to obtain a comparison result, and dynamically adjusting the sampling frequency of the target detection node based on the comparison result to obtain an adjusted detection node;

[0030] Using the adjusted detection node to perform spatiotemporal alignment processing on the real-time monitoring data stream to obtain a spatiotemporal feature tensor;

[0031] Performing multi-frequency cross-validation processing on the spatiotemporal feature tensor using a spatiotemporal convolutional neural network to generate a pollution diffusion confidence field;

[0032] Based on the pollution diffusion confidence field and environmental influencing factors, the pollution diffusion trend is confirmed to generate water quality detection results. The environmental influencing factors include water flow velocity influencing factors and temperature gradient influencing factors.

[0033] Optionally, determining a target detection node based on the spatial distribution data and the water area topographic feature data, and obtaining a detection data set based on the target detection node includes:

[0034] Based on the spatial distribution data and the water area terrain feature data, a preliminary detection path is generated, and adaptive topological adjustment is performed on the mobile detection nodes in the preliminary detection path to obtain a target detection node;

[0035] Based on the target detection node, collecting dissolved oxygen data, turbidity data and heavy metal concentration monitoring data;

[0036] Compensating for non-uniform sampling points in the dissolved oxygen data to generate a dissolved oxygen distribution map, enhancing the spatial gradient in the turbidity data to generate a turbidity gradient field, and performing particle tracking modeling on the migration trajectories in the heavy metal concentration monitoring data to generate heavy metal ion migration trajectories;

[0037] The dissolved oxygen distribution map, the turbidity gradient field, and the heavy metal ion migration trajectory are fused to generate a detection data set.

[0038] In a second aspect, an embodiment of the present invention provides a water quality environment detection system based on 5G communication, including:

[0039] An acquisition module is used to obtain spatial distribution data of mobile detection nodes and water area terrain feature data in the water area to be tested;

[0040] A determination module, configured to determine a target detection node based on the spatial distribution data and the water area topographic feature data, and obtain a detection data set based on the target detection node;

[0041] A construction module is used to process the migration trajectories of heavy metal ions in the detection data set to generate a pollutant diffusion boundary prediction map to simulate and generate a multi-scenario diffusion envelope range, and generate an emergency control instruction set based on the multi-scenario diffusion envelope range;

[0042] A generation module is used to combine the emergency control instruction set and environmental impact factors to confirm the pollution diffusion trend and generate water quality environment detection results based on the pollution diffusion trend.

[0043] In a third aspect, an embodiment of the present invention provides a computing device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a water quality environment detection method based on 5G communication as described in any one of the first aspects.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer storage medium having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, a water quality environment detection method based on 5G communication as described in any one of the first aspects is implemented.

[0045] In an embodiment of the present invention, spatial distribution data of mobile detection nodes and water area terrain characteristic data in the water area to be tested are obtained; based on the spatial distribution data and water area terrain characteristic data, the target detection node is determined, and based on the target detection node, a detection data set is obtained; the migration trajectory of heavy metal ions in the detection data set is processed to generate a pollutant diffusion boundary prediction map to simulate and generate a multi-scenario diffusion envelope range, and based on the multi-scenario diffusion envelope range, an emergency control instruction set is generated; combined with the emergency control instruction set and environmental influencing factors, the pollution diffusion trend is confirmed, and based on the pollution diffusion trend, a water quality environment detection result is generated. The technical solution provided by the present invention obtains the spatial distribution data of mobile monitoring nodes and the water area terrain feature data in the water area to be tested, and generates target detection nodes based on these data to ensure that the entire monitoring area can be covered, especially the blind spots under complex terrain; this improves the comprehensiveness and accuracy of water quality environment monitoring; at the same time, the layout of target detection nodes is more reasonable and efficient, thereby more accurately reflecting the changes in water quality conditions; based on the detection data set, a water quality abnormal diffusion model and a dissolved oxygen distribution map are constructed, which can dynamically analyze water quality changes in real time and predict pollutant diffusion trends; the pollution diffusion trend is confirmed according to the generated emergency control instruction set, and the water quality environment detection results are generated accordingly, which helps to take effective measures to control the spread of pollution in a timely manner and protect water resources safety. This method takes advantage of the advantages of 5G communication technology, ensures high speed and low latency of data transmission, and further enhances the speed and effectiveness of emergency response; at the same time, it helps to quickly confirm the specific trend of pollution diffusion, provide a scientific basis for formulating effective response strategies, and minimize the damage caused by pollution; through the analysis of the pollution diffusion trend, detailed water quality environment detection results are generated, which provides strong decision support for managers, helping them to formulate reasonable governance and prevention measures to protect water resources safety. Among them, the hydrological cycle correction factor is calculated by combining the deviation rate between real-time flow monitoring data and historical average data for the same period, and the pollutant peak value is dynamically compared with the standard peak value to ensure the accuracy and timeliness of water quality detection; the pollutant concentration time series is extracted and the pollutant concentration mutation index is calculated by combining the sliding time window mechanism to ensure the accuracy and timeliness of water quality monitoring; when the pollution comparison results meet the preset composite conditions, the system can quickly trigger the pollution source location model, generate the pollution source confidence interval geographic fence, and formulate an effective emergency control instruction set.

[0046] These and other aspects of the present invention will become more readily apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 A flow chart of a water quality environment detection method based on 5G communication provided in an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the structure of a water quality environment detection system based on 5G communication provided by an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0052] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit "first" and "second" to be different types.

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0054] Figure 1 A flow chart of a water quality environment detection method based on 5G communication is provided for an embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0055] Traditional water quality detection methods have been unable to meet the needs of comprehensive and real-time monitoring of complex water environments. Existing technical solutions cannot provide sufficient data support to deal with sudden pollution incidents and long-term ecological management. In order to solve these problems and improve the accuracy and coverage of water quality monitoring, a more intelligent and efficient detection solution is urgently needed. Based on this, the present invention provides a water quality environment detection method based on 5G communication, such as Figure 1 ,include:

[0056] Step 101: Acquire spatial distribution data of mobile detection nodes and water area terrain feature data in the water area to be measured;

[0057] In this step, mobile detection nodes refer to sensor devices that move freely within the water body to be measured, collecting real-time water quality parameters (such as dissolved oxygen, turbidity, and heavy metal ion concentrations). Spatial distribution data describes the location of the mobile detection nodes within the water body, including three-dimensional coordinates (x, y, z) and their relative positions. Water body topography data describes the bottom topography and surrounding environmental characteristics of the water body, including water depth, slope, and obstacle distribution.

[0058] In practice, multiple mobile detection nodes are first deployed in the water area to be measured. These nodes record their spatial distribution data using GPS or other positioning technologies, and use equipment such as sonar or lidar to obtain data on the water area's topographic characteristics. For example, in a lake, ten mobile detection nodes were deployed at different depths and locations, simultaneously using sonar equipment to scan the lake bottom terrain, generating precise spatial distribution and topographic characteristic data.

[0059] Step 102: determining a target detection node based on the spatial distribution data and the water area terrain feature data, and obtaining a detection data set based on the target detection node;

[0060] In this step, the target detection node refers to the optimized and adjusted layout of mobile detection nodes to ensure coverage of the entire monitoring area and improve data collection efficiency. The detection dataset refers to the multi-dimensional water quality parameter data collected by the mobile detection nodes, including dissolved oxygen distribution maps, turbidity gradient fields, and heavy metal ion migration trajectories.

[0061] In this step, the system automatically generates an optimal layout of target detection nodes based on the acquired spatial distribution data and terrain characteristics. For example, algorithmic analysis revealed that certain areas require a denser distribution of monitoring points to cover complex terrain variations. Ultimately, five target detection nodes were identified, each responsible for collecting water quality parameters such as dissolved oxygen, turbidity, and heavy metal ion concentrations for a specific area, forming a complete detection dataset.

[0062] Step 103: Processing the heavy metal ion migration trajectories in the detection data set to generate a pollutant diffusion boundary prediction map to simulate and generate a multi-scenario diffusion envelope range, and generating an emergency control instruction set based on the multi-scenario diffusion envelope range;

[0063] In this step, the multi-scenario diffusion envelope range refers to the diffusion range under different scenarios obtained by simulating the pollutant diffusion under different pollution load conditions.

[0064] This step uses the migration trajectory data of heavy metal ions in the detection dataset, combined with a water quality anomaly diffusion model, to generate a pollutant diffusion boundary prediction map. For example, by using particle tracking modeling to model the migration paths of heavy metal ions in a river, a pollutant diffusion boundary prediction map is generated, and scenario analysis is used to simulate the diffusion range under different pollution loads. If the simulation results show that under high pollution load conditions, pollutants may spread to downstream residential areas, the system will automatically generate an emergency control instruction set, recommending the immediate closure of upstream pollution sources and the activation of emergency plans.

[0065] Step 104: Determine the pollution diffusion trend by combining the emergency control instruction set and the environmental impact factors, and generate a water quality environment detection result based on the pollution diffusion trend;

[0066] In this step, environmental impact factors include water flow velocity impact factors and temperature gradient impact factors, which affect the diffusion path and rate of pollutants.

[0067] This step combines the generated emergency control instruction set with environmental factors (such as water velocity and temperature gradient) to further confirm the actual spread of pollutants. For example, considering that increased water velocity may lead to faster downstream spread of pollutants, the system adjusts the monitoring frequency and updates the pollution spread prediction results. Ultimately, a detailed water quality and environmental monitoring report is generated, indicating the current water quality status, pollution spread trends, and corresponding response measures, providing scientific basis for management departments.

[0068] The embodiments of the present invention achieve efficient and comprehensive water quality monitoring by accurately acquiring and processing the spatial distribution data of mobile detection nodes and the terrain characteristics of the water area. Based on the generated target detection node layout and detection data set, it is possible to accurately simulate the diffusion path and range of pollutants and provide early warning of potential pollution incidents. In combination with environmental influencing factors, the accuracy of pollution diffusion trend prediction is further improved, ensuring the timely generation of effective emergency control instruction sets. This not only improves the accuracy and response speed of water quality monitoring, but also significantly enhances the ability to protect water resources, providing strong technical support for the realization of all-round, multi-level water quality management.

[0069] Traditional monitoring methods often lack the ability to comprehensively analyze multi-dimensional data, making it difficult to accurately predict the diffusion trend and impact range of pollutants. To improve the predictability and response speed of water quality monitoring, the present invention provides a specific embodiment, 103, which processes the migration trajectory of heavy metal ions in the detection data set to generate a pollutant diffusion boundary prediction map to simulate and generate a multi-scenario diffusion envelope range. Based on the multi-scenario diffusion envelope range, an emergency control instruction set is generated, which specifically includes the following steps:

[0070] Step 301: Based on the detection data set, construct a water quality abnormal diffusion model and a dissolved oxygen distribution map, and use the dissolved oxygen distribution map and the water quality abnormal diffusion model to perform a synergistic coupling process on the turbulent diffusion effect of the turbidity gradient field to generate a pollutant migration probability distribution matrix;

[0071] In this step, the dissolved oxygen distribution map reflects the spatial distribution of dissolved oxygen concentration in water and is a key indicator for assessing water quality. The turbulent diffusion effect refers to the diffusion of pollutants in water bodies caused by turbulent flow, which typically affects the migration path and velocity of pollutants. Synergistic coupling processing combines different types of water quality parameter data (such as dissolved oxygen and turbidity) to improve the accuracy of predicting pollutant diffusion paths. The pollutant migration probability distribution matrix represents the probability distribution of pollutant migration at different time and spatial locations and is used to further analyze pollutant diffusion trends.

[0072] In practice, the system first uses the detection dataset to construct a water quality anomaly diffusion model and generate a dissolved oxygen distribution map. For example, in a lake, the system generates a detailed dissolved oxygen distribution map based on the dissolved oxygen concentration data collected by multiple mobile detection nodes. This map is then used in conjunction with the water quality anomaly diffusion model to perform a synergistic coupling process on the turbulent diffusion effects in the turbidity gradient field. Assuming that the system discovers that pollutants diffuse more rapidly in certain areas due to turbulent water flow, the system generates a pollutant migration probability distribution matrix through synergistic coupling, showing the probability of pollutants migrating at different time and spatial locations.

[0073] Step 302: Based on the pollutant migration probability distribution matrix, a three-dimensional hydrodynamic water quality model is constructed to reversely process the pollution source location and emission characteristics of the heavy metal ion migration trajectory and generate a pollutant diffusion boundary prediction map;

[0074] In this step, reverse engineering of pollution source locations and emission characteristics involves inferring the location and emission characteristics of pollution sources based on pollutant migration trajectory data. Pollutant diffusion boundary prediction maps predict the boundaries of pollutant diffusion in water bodies, helping to identify potential areas of pollution.

[0075] In this step, the system uses the generated pollutant migration probability distribution matrix to construct a three-dimensional hydrodynamic water quality model, simulating the diffusion of pollutants in three-dimensional space. For example, in a river, the system reversely infers the location of the pollution source and its emission characteristics based on the migration trajectory data of heavy metal ions. Suppose the system identifies an upstream factory as the pollution source and generates a predicted pollutant diffusion boundary map, showing the range and path of the pollutant's spread over the next few hours.

[0076] Step 303: Based on the pollutant diffusion boundary prediction map, a scenario analysis method is used to perform a three-dimensional hydrodynamic coupling simulation on the preset pollution load gradient to obtain a multi-scenario diffusion envelope range, and based on the multi-scenario diffusion envelope range, an emergency control instruction set is generated;

[0077] In this step, based on the generated pollutant diffusion boundary prediction map, the system uses scenario analysis to simulate the diffusion of pollutants under different pollution load conditions. For example, under simulated high pollution load conditions, the system predicts that pollutants may spread to downstream residential areas. Through three-dimensional hydrodynamic coupling simulation, multi-scenario diffusion envelope ranges are generated to show the maximum diffusion range under different scenarios. Assume that the system generates diffusion envelope ranges under three scenarios, namely light, moderate and heavy pollution scenarios. Based on these scenarios, the system automatically generates an emergency control instruction set, recommending the immediate closure of upstream pollution sources and the activation of emergency plans, while strengthening monitoring and protection measures for downstream areas.

[0078] The embodiments of the present invention accurately simulate the diffusion path and range of pollutants in water bodies by constructing a water quality abnormal diffusion model and a dissolved oxygen distribution map; utilize a collaborative coupling processing method to improve the prediction accuracy of pollutant diffusion paths; through a three-dimensional hydrodynamic water quality model, it can accurately infer the location of pollution sources and their emission characteristics, and generate a detailed pollutant diffusion boundary prediction map; adopt a scenario analysis method to simulate the diffusion situation under different pollution load conditions, generate a multi-scenario diffusion envelope range, and ensure the timely generation of an effective emergency control instruction set.

[0079] When faced with complex water pollution incidents, accurately assessing the spread and impact of pollutants is key to developing effective emergency response measures. Traditional monitoring methods typically provide only limited data support and struggle to fully cover the pollutant diffusion paths and boundaries under multiple scenarios. Based on this, the present invention provides a specific embodiment, 303, for generating an emergency control instruction set based on the multi-scenario diffusion envelope range, specifically comprising the following steps:

[0080] Step 311: Using the ecological exposure risk weighted overlay algorithm, perform spatial analysis on the multi-scenario diffusion envelope and ecological red line area to obtain the pollutant peak and spatial coverage rate of sensitive waters under each scenario;

[0081] In this step, the pollutant peak and spatial coverage rate indicate the area with the highest pollutant concentration and its coverage area ratio under a specific scenario.

[0082] In practice, the system first uses a weighted overlay algorithm for ecological exposure risk to perform a spatial analysis of the diffusion envelopes and ecological redline areas under multiple scenarios. For example, in a river system, the system uses the diffusion envelopes generated under different pollution load conditions (light, moderate, and heavy pollution scenarios) and combines them with the river's ecological redline area to calculate the peak pollutant levels and spatial coverage of sensitive waters under each scenario. For example, under the heavy pollution scenario, the system finds that the peak pollutant level in a certain section of the river is 5 mg / L and covers 30% of the ecological redline area.

[0083] Step 312: Calculate a hydrological cycle correction factor based on the deviation rate between the real-time flow monitoring data and the historical mean data for the same period. Based on the hydrological cycle correction factor, dynamically compare the pollutant peak value with the standard peak value of the corresponding pollutant in the surface water environmental quality standard to obtain a pollution comparison result.

[0084] In this step, real-time flow monitoring data refers to data such as water velocity and flow rate collected in real time by sensors and is used to dynamically monitor hydrological changes. Historical mean data refers to the average flow rate data for the same time period in the past and serves as a benchmark. Pollution comparison results refer to the results of a dynamic comparison of pollutant peaks with standard peaks, which are used to determine whether emergency measures are necessary.

[0085] In this step, the system calculates the hydrological cycle correction factor based on the deviation rate between the real-time flow monitoring data and the historical average data for the same period. For example, if the real-time flow monitoring data shows that the current water flow rate is 20% faster than the historical average data for the same period, the calculated hydrological cycle correction factor is 1.2. Next, based on this correction factor, the system dynamically compares the peak value of the pollutant (e.g., 5 mg / L) with the standard peak value of the corresponding pollutant in the surface water environmental quality standard (e.g., 3 mg / L) to obtain the pollution comparison result. Assuming that the corrected pollutant peak value is 6 mg / L, which is higher than the standard peak value, it indicates that the current water quality has exceeded the standard and emergency measures are required.

[0086] Step 313: When the pollution comparison result meets a preset composite condition, the pollution source location model is triggered to fuse the pollutant migration probability distribution matrix with the real-time monitoring data stream to generate a pollution source confidence interval geo-fence. Based on the pollution source confidence interval geo-fence, an emergency control instruction set is generated. The preset composite condition includes a first condition that the spatial intersection area ratio of the warning area and the drinking water source protection area exceeds a dynamic threshold and a second condition that the pollutant concentration mutation index in the real-time monitoring data stream exceeds a mutation threshold. The dynamic threshold is set according to the pollutant toxicity level and the water supply scale of the water source.

[0087] In this step, the pollution source confidence interval geofence refers to the area where the possible pollution source is located, determined by model inversion, and is used to locate potential pollution sources. The warning area refers to the area where the peak concentration of pollutants exceeds the threshold.

[0088] When the pollution comparison results meet the preset composite conditions (such as the spatial intersection area of the early warning area and the drinking water source protection area exceeds the dynamic threshold, and the pollutant concentration mutation index in the real-time monitoring data stream exceeds the mutation threshold), the system triggers the pollution source location model. For example, in the above example, suppose the system finds that the spatial intersection area of the early warning area and the drinking water source protection area accounts for 35%, and the pollutant concentration mutation index in the real-time monitoring data stream is 1.5 (exceeding the set mutation threshold of 1.2). The system fuses the pollutant migration probability distribution matrix with the real-time monitoring data stream to generate a pollution source confidence interval geo-fence. Assume that the system determines that a factory upstream is the source of pollution and generates an emergency control instruction set, recommending that the factory be shut down immediately and the emergency plan be activated, while strengthening monitoring and protection measures for downstream areas.

[0089] The embodiment of the present invention uses an ecological exposure risk weighted superposition algorithm to accurately assess the impact of pollutant diffusion on sensitive waters under different scenarios, thereby improving the ability to identify ecological risks; combines the deviation rate between real-time flow monitoring data and historical mean data for the same period to calculate the hydrological cycle correction factor, and dynamically compares pollutant peaks with standard peaks to ensure the accuracy and timeliness of water quality testing; when the pollution comparison results meet the preset composite conditions, the system can quickly trigger the pollution source location model, generate a pollution source confidence interval geo-fence, and formulate an effective emergency control instruction set.

[0090] In the emergency response process of water pollution incidents, quickly and accurately locating the pollution source and generating an effective emergency control instruction set are the key to ensuring water resource security. However, traditional monitoring methods are often difficult to achieve accurate pollution source positioning and timely emergency response in complex environments. To this end, based on this, the present invention provides a specific embodiment, step 313, when the pollution comparison result meets the preset composite conditions, the pollution source positioning model is triggered to fuse the pollutant migration probability distribution matrix with the real-time monitoring data stream to generate a pollution source confidence interval geo-fence, and based on the pollution source confidence interval geo-fence, an emergency control instruction set is generated. The preset composite conditions include the first condition that the spatial intersection area of the warning area and the drinking water source protection area exceeds the dynamic threshold and the second condition that the pollutant concentration mutation index in the real-time monitoring data stream exceeds the mutation threshold. The dynamic threshold is set according to the pollutant toxicity level and the water supply scale of the water source, and specifically includes the following steps:

[0091] Step 321: Using the pollutant toxicity level classification rules and the water source water supply scale classification standards, a dynamic threshold mapping table is constructed. Based on the dynamic threshold mapping table, the area ratio threshold corresponding to the combination is searched to generate a dynamic threshold set. Based on the dynamic threshold set, the spatial intersection area ratio of the warning area and the drinking water source protection area is calculated, where the combination includes the pollutant toxicity level and the water source water supply scale.

[0092] In this step, the dynamic threshold mapping table, constructed based on pollutant toxicity levels and water source supply scale, is used to find corresponding area ratio thresholds to generate a dynamic threshold set. The area ratio threshold refers to the maximum allowable ratio of the spatial intersection area between the warning area and the drinking water source protection area, set based on the pollutant toxicity level and water source supply scale. The dynamic threshold set refers to a set of area ratio thresholds for different combinations of pollutant toxicity levels and water source supply scales.

[0093] In practice, a dynamic threshold mapping table is first constructed based on the pollutant toxicity classification rules (such as low, medium, and high) and the water source water supply scale classification standards (such as small, medium, and large). For example, in a river system, suppose the pollutant is heavy metal lead, its toxicity level is high, and the water source water supply scale is medium. Based on the dynamic threshold mapping table, the system finds the corresponding area percentage threshold for this combination: 20%. Next, the system calculates the spatial intersection area percentage of the warning area and the drinking water source protection area. Assume that the calculated result is 25%, which exceeds the set threshold of 20%.

[0094] Step 322: extracting a pollutant concentration time series based on the real-time monitoring data stream using a sliding time window mechanism, and calculating a pollutant concentration mutation index based on the pollutant concentration time series;

[0095] In this step, the pollutant concentration time series refers to the data series of pollutant concentration changes over time extracted from the real-time monitoring data stream using a sliding time window mechanism. The pollutant concentration mutation index is an indicator that measures the severity of changes in pollutant concentration over a short period of time and is used to determine whether abnormal fluctuations have occurred.

[0096] In this step, the system extracts pollutant concentration time series from the real-time monitoring data stream and processes them using a sliding time window mechanism. For example, in a particular river, the system sets a sliding time window of 1 hour, sliding every 10 minutes, and extracts time series data on lead concentrations over the past hour. Assuming the extracted data is [0.01mg / L, 0.02mg / L, 0.05mg / L, 0.1mg / L], the system calculates a pollutant concentration mutation index of 1.5 (indicating a 15-fold increase in concentration), far exceeding the preset mutation threshold of 1.2.

[0097] Step 323: If the spatial intersection area ratio exceeds the dynamic threshold corresponding to the pollutant toxicity level and the water supply scale of the water source, it is determined that the first condition is met. If the pollutant concentration mutation index exceeds the preset mutation threshold corresponding to the pollutant type, it is determined that the second condition is met.

[0098] Based on the calculation results of step 322, the system determines whether the preset composite conditions are met. Assume that the spatial intersection area is 25%, exceeding the dynamic threshold of 20%, meeting the first condition; and the pollutant concentration mutation index is 1.5, exceeding the mutation threshold of 1.2, meeting the second condition.

[0099] Step 324: When the spatial intersection area ratio satisfies both the first and second conditions, triggering the pollution source location model to fuse the pollutant migration probability distribution matrix with the real-time monitoring data stream to generate a pollution source confidence interval geo-fence;

[0100] When both the first and second conditions are met, the system triggers the pollution source location model. For example, in the example above, the system integrates the pollutant migration probability distribution matrix with the real-time monitoring data stream to generate a pollution source confidence interval geofence. Suppose the system identifies an upstream factory as the pollution source and generates a pollution source confidence interval geofence around the factory.

[0101] Step 325: Generate an emergency control instruction set based on the pollution source confidence interval geo-fence;

[0102] Finally, the system develops a specific set of emergency control instructions based on the generated confidence interval geofences for the pollution source. For example, the system recommends the immediate closure of upstream pollution source factories and the activation of emergency response plans, strengthening monitoring and protective measures in downstream areas to ensure timely and effective measures to control the spread of pollution.

[0103] The embodiment of the present invention improves the ability to identify ecological risks by constructing a dynamic threshold mapping table to accurately evaluate the spatial intersection area ratio of warning areas and drinking water source protection areas under different pollutant toxicity levels and water source water supply scales; combines the sliding time window mechanism to extract pollutant concentration time series and calculate the pollutant concentration mutation index, ensuring the accuracy and timeliness of water quality monitoring; when the preset composite conditions are met, the system can quickly trigger the pollution source location model, generate the pollution source confidence interval geo-fence, and formulate an effective emergency control instruction set.

[0104] After accurately locating the pollution source and determining its impact range, how to quickly generate an effective emergency control instruction set becomes a key step in ensuring water quality safety. Traditional emergency response methods often rely on manual judgment and experience, resulting in slow response speed, imprecise instructions, and difficulty in responding to complex and changing pollution incidents. To this end, based on this, the present invention provides a specific embodiment, step 325, based on the pollution source confidence interval geo-fence, generating an emergency control instruction set, specifically including the following steps:

[0105] Step 331: Generate a list of potential pollution sources within the fence based on the boundary coordinates of the pollution source confidence interval geo-fence, the dynamic threshold set, and pollution source historical data;

[0106] In this step, the boundary coordinates of the pollution source confidence interval geofence refer to the geographic boundary coordinates of the area where the possible pollution source is located, determined by reverse engineering the pollution source location model. This is used to locate potential pollution sources. Historical pollution source data refers to data that records the location, emissions, and pollution events of each pollution source in history. This data is used to assist in analyzing the likelihood of current pollution sources.

[0107] In practice, the system first uses the boundary coordinates of the pollution source confidence interval geofence, the dynamic threshold set, and historical pollution source data to generate a list of potential pollution sources within the fence. For example, in a river system, suppose the system has determined a pollution source confidence interval geofence with boundary coordinates [(x1,y1),(x2,y2),...]. Combining the dynamic threshold set and historical data, the system identifies three potential pollution sources within the area: upstream plant A, midstream plant B, and downstream plant C, and generates a list of potential pollution sources.

[0108] Step 332: Based on the pollutant concentration mutation index and the water source service population size parameter, adjust the existing instruction classification rules to obtain adjusted classification rules, and use the adjusted classification rules to generate a hierarchical control instruction set, wherein the hierarchical control instruction set includes a shutdown instruction, a production restriction instruction, and an inspection instruction.

[0109] In this step, the water source population size parameter represents the number of people served by the water source and is used to assess the impact of pollution on public health. The directive grading rules refer to different levels of emergency response measures, such as shutdowns, production restrictions, and inspections, set based on the severity of the pollution.

[0110] In this step, the system adjusts the existing command classification rules based on the pollutant concentration mutation index and the population size of the water source. For example, assuming the pollutant concentration mutation index is 1.5 and the water source serves a population of 500,000, the system adjusts the command classification rules based on these parameters, increasing the emergency response to areas with high concentration mutations and large water supply. The adjusted classification rules generate a hierarchical control command set, specifically: for areas with high concentration mutations and large populations, it is recommended to immediately shut down the pollution source; for areas with medium concentration mutations, it is recommended to limit production; and for areas with low concentration mutations, it is recommended to strengthen inspections. For example, for upstream plant A (high concentration mutation), a shutdown order is generated; for midstream plant B (medium concentration mutation), a production restriction order is generated; and for downstream plant C (low concentration mutation), an inspection order is generated.

[0111] Step 333: Based on the list of potential pollution sources within the fence and the hierarchical control instruction set, combined with the real-time monitoring data stream and historical risk data, a multi-objective optimization algorithm is used to match pollution source feature vectors with instruction levels to generate an emergency control instruction set. The pollution source feature vector includes an industry type vector and an emission intensity vector.

[0112] In this step, the real-time monitoring data stream refers to water quality parameter data collected in real time by sensors, which is used to dynamically monitor changes in water quality. Historical risk data refers to data recording past pollution incidents and their treatment outcomes, which is used to assess the risk level of the current pollution incident. Pollution source feature vectors are vectors that describe the characteristics of pollution sources. They typically include industry type vectors and emission intensity vectors, which are used to distinguish different types of pollution sources.

[0113] In this step, the system combines the list of potential pollution sources within the fence with the hierarchical control instruction set, utilizes real-time monitoring data streams and historical risk data, and employs a multi-objective optimization algorithm to match the pollution source feature vectors with the instruction level to generate the final emergency control instruction set. For example, in the above example, the system matches the feature vectors of upstream factory A (high emission intensity), midstream factory B (medium emission intensity), and downstream factory C (low emission intensity) with the instruction level. Through the multi-objective optimization algorithm, the system generates a specific emergency control instruction set: it recommends the immediate closure of upstream factory A, production restrictions at midstream factory B, and increased inspection frequency at downstream factory C. At the same time, the system recommends strengthening water quality monitoring in downstream residential areas to ensure that effective measures are taken in a timely manner to control the spread of pollution.

[0114] The embodiment of the present invention comprehensively utilizes the boundary coordinates, dynamic threshold set and historical data of the pollution source confidence interval geographic fence to accurately generate a list of potential pollution sources within the fence, thereby improving the ability to identify potential pollution sources; combined with the pollutant concentration mutation index and the population size parameter of the water source service area, the instruction classification rules are adjusted to ensure the pertinence and effectiveness of emergency response measures; through a multi-objective optimization algorithm, the pollution source feature vector and the instruction level are matched to generate a detailed emergency control instruction set, which not only improves the warning and response capabilities for sudden water pollution incidents, but also significantly enhances the effect of water resource protection.

[0115] In the process of water quality and environmental monitoring, accurately identifying pollution diffusion trends and generating detailed detection results are key to formulating effective response measures. Based on this, the present invention provides a specific embodiment, step 104, combining the emergency control instruction set and environmental impact factors to identify pollution diffusion trends and generate water quality and environmental detection results based on the pollution diffusion trends, specifically including the following steps:

[0116] Step 401: Compare the pollutant diffusion boundary confidence level and the diffusion rate threshold in the emergency control instruction set to obtain a comparison result, and dynamically adjust the sampling frequency of the target detection node based on the comparison result to obtain an adjusted detection node;

[0117] In this step, the pollutant diffusion boundary confidence level indicates the accuracy of the water quality anomaly diffusion model's prediction of the pollutant diffusion boundary, typically expressed as a probability or confidence interval. The diffusion rate threshold refers to a pre-set upper limit on the pollutant diffusion rate and is used to determine whether the monitoring strategy needs to be adjusted. The comparison result, obtained by comparing the pollutant diffusion boundary confidence level with the diffusion rate threshold, is used to determine whether the sampling frequency of the target detection node should be adjusted.

[0118] In actual operation, the system first obtains the confidence level of the pollutant diffusion boundary from the emergency control instruction set and compares it with the preset diffusion rate threshold. For example, suppose the confidence level of the pollutant diffusion boundary in a river is 85%, and the diffusion rate threshold is 0.5mg / L / h. If the confidence level is higher than the threshold, it indicates that the current monitoring frequency may not be sufficient to capture the rapidly changing water quality conditions. Therefore, the system will dynamically adjust the sampling frequency of the target detection node and increase the number of sampling times. For example, the original sampling frequency of once an hour is adjusted to once every half an hour to ensure timely acquisition of the latest water quality data.

[0119] Step 402: Using the adjusted detection nodes, perform spatiotemporal alignment processing on the real-time monitoring data stream to obtain a spatiotemporal feature tensor;

[0120] In this step, the spatiotemporal feature tensor refers to a multidimensional data structure formed by aligning data at different time points and spatial positions, which facilitates subsequent analysis.

[0121] In this step, the target detection nodes begin collecting water quality data in real time based on the adjusted sampling frequency and perform spatiotemporal alignment. For example, in a lake, multiple detection nodes collect dissolved oxygen, turbidity, and heavy metal concentration data at different time points and spatial locations. The system aligns this data by time and spatial location, forming a three-dimensional spatiotemporal feature tensor. This tensor contains water quality parameter information for each node at different times and locations, facilitating subsequent analysis.

[0122] Step 403: performing multi-frequency cross-validation processing on the spatiotemporal feature tensor using a spatiotemporal convolutional neural network to generate a pollution diffusion confidence field;

[0123] In this step, the pollution diffusion confidence field refers to the data processed by the spatiotemporal convolutional neural network, which represents the diffusion probability distribution of pollutants at different time and spatial locations.

[0124] In this step, the system uses a spatiotemporal convolutional neural network to process the spatiotemporal feature tensor. For example, the spatiotemporal feature tensor generated above is fed into the spatiotemporal convolutional neural network. Through multiple cross-validations (e.g., five-fold cross-validation), the system extracts a probability distribution map of pollutant diffusion, known as the pollution diffusion confidence field. This confidence field displays the probability of pollutant diffusion at different temporal and spatial locations, helping to predict future pollutant diffusion trends. For example, the model predicts that pollutants will diffuse to a specific range in the downstream area within the next two hours.

[0125] Step 404: Based on the pollution diffusion confidence field and environmental impact factors, confirm the pollution diffusion trend to generate water quality detection results, wherein the environmental impact factors include water flow velocity impact factor and temperature gradient impact factor;

[0126] In this step, the system combines the pollution diffusion confidence field with environmental factors (such as water velocity and temperature gradient) to further confirm the actual diffusion trend of pollutants. For example, if the water velocity and temperature are high, it may cause pollutants to spread faster downstream. The system integrates these factors to generate detailed water quality test results, indicating the current water quality status, pollutant diffusion trends, and corresponding countermeasures. For example, it recommends immediately initiating emergency response plans, shutting down upstream pollution sources, and strengthening monitoring of downstream areas.

[0127] The embodiment of the present invention compares the pollutant diffusion boundary confidence level with the diffusion rate threshold and dynamically adjusts the sampling frequency of the target detection node, thereby ensuring the efficiency and accuracy of real-time monitoring. By utilizing the spatiotemporal feature tensor and spatiotemporal convolutional neural network, the system can extract complex spatiotemporal features and generate a high-quality pollution diffusion confidence field. In combination with environmental influencing factors, the accuracy of pollution diffusion trend prediction is further improved. The water quality test results finally generated not only provide a scientific basis, but also support management departments in formulating effective emergency response measures.

[0128] In complex water environments, traditional fixed monitoring stations have difficulty achieving comprehensive coverage and efficient monitoring, resulting in many areas becoming monitoring blind spots and unable to detect abnormal changes in water quality in a timely manner. In order to overcome this challenge, a solid data foundation is provided for water quality environment monitoring. Based on this, the present invention provides a specific embodiment, step 102, based on the spatial distribution data and water area terrain feature data, determining the target detection node, and obtaining a detection data set based on the target detection node, specifically including the following steps:

[0129] Step 201: generating a preliminary detection path based on the spatial distribution data and the water area terrain feature data, and performing adaptive topological adjustment on the mobile detection nodes in the preliminary detection path to obtain a target detection node;

[0130] In this step, adaptive topology adjustment refers to dynamically adjusting the location and layout of mobile detection nodes according to actual monitoring needs and water characteristics to optimize monitoring efficiency and coverage.

[0131] In practice, the system first generates a preliminary detection path using acquired spatial distribution data and water area topographical characteristics. For example, within a lake, the system generates a preliminary path covering key topographical features based on GPS positioning data and sonar scans. The system then adaptively adjusts the topology of the mobile detection nodes within the preliminary path based on actual monitoring needs and water area characteristics. Suppose the system discovers that certain areas require a denser concentration of monitoring points to cover complex terrain variations. Ultimately, the system identifies five target detection nodes, distributed at varying depths and locations to ensure comprehensive coverage of the monitoring area.

[0132] Step 202: Based on the target detection node, collect dissolved oxygen data, turbidity data and heavy metal concentration monitoring data;

[0133] In this step, the target detection node refers to the optimal mobile detection node layout after adaptive topology adjustment, ensuring coverage of the entire monitoring area and improving data collection efficiency.

[0134] In this step, each node begins collecting water quality parameter data based on the generated target detection node layout. For example, target detection node A, located deep in the center of the lake, collects a dissolved oxygen concentration of 6 mg / L; node B, located near the shore, collects a turbidity value of 20 NTU; and node C, located at the river entrance, collects a heavy metal ion (such as lead) concentration of 0.01 mg / L. Together, these data constitute the multi-dimensional foundation for water quality monitoring.

[0135] Step 203: Compensating for non-uniform sampling points in the dissolved oxygen data to generate a dissolved oxygen distribution map, enhancing the spatial gradient in the turbidity data to generate a turbidity gradient field, and performing particle tracking modeling on the migration trajectories in the heavy metal concentration monitoring data to generate heavy metal ion migration trajectories;

[0136] In this step, dissolved oxygen data refers to the dissolved oxygen concentration in the water collected by the sensor, a key indicator of water quality. Turbidity data refers to the turbidity of the water collected by the sensor, reflecting the content of suspended particulate matter in the water. Heavy metal concentration monitoring data refers to the heavy metal ion concentration in the water collected by the sensor, used to assess water pollution.

[0137] For non-uniform sampling points in dissolved oxygen data, the system uses an interpolation algorithm to compensate and generate a continuous dissolved oxygen distribution map. For example, by interpolating the unsampled area between node A and node B, a complete dissolved oxygen distribution map is generated. For turbidity data, the system uses spatial gradient enhancement processing to enhance its spatial variation characteristics and generate a detailed turbidity gradient field. For example, by calculating the turbidity difference between node B and the surrounding nodes, a clear turbidity gradient field is generated. For heavy metal concentration monitoring data, the system uses particle tracking modeling methods to simulate the migration trajectory of heavy metal ions in water flow. For example, by simulating the process of lead ions diffusing from the river entrance to the downstream, a detailed migration trajectory of heavy metal ions is generated.

[0138] Step 204: fusing the dissolved oxygen distribution map, the turbidity gradient field, and the heavy metal ion migration trajectory to generate a detection data set;

[0139] In this step, the detection data set refers to a multi-dimensional water quality parameter data set including a dissolved oxygen distribution map, a turbidity gradient field, and a heavy metal ion migration trajectory.

[0140] The system integrates the generated dissolved oxygen distribution map, turbidity gradient field, and heavy metal ion migration trajectories to form a comprehensive detection data set. For example, the system combines the generated dissolved oxygen distribution map, turbidity gradient field, and heavy metal ion migration trajectories to generate a comprehensive data set containing all water quality parameters. This data set can be used to further analyze water quality and provide basic data support for the subsequent construction of water quality abnormal diffusion models.

[0141] The embodiment of the present invention achieves an efficient and comprehensive water quality monitoring layout by accurately generating preliminary detection paths and adaptively adjusting the topology of mobile detection nodes. Based on the generated target detection nodes, the system can accurately collect multi-dimensional water quality parameter data such as dissolved oxygen, turbidity, and heavy metal concentrations. Through compensation processing, spatial gradient enhancement processing, and particle tracking modeling, it generates high-quality dissolved oxygen distribution maps, turbidity gradient fields, and heavy metal ion migration trajectories. The detection data set generated through fusion processing not only improves the accuracy and coverage of water quality monitoring, but also provides a solid data foundation for subsequent water quality anomaly diffusion prediction and emergency response. This significantly enhances the ability to protect water resources and provides strong technical support for achieving all-round and multi-level water quality management.

[0142] Figure 2 The present invention provides a structural diagram of a water quality environment detection system based on 5G communication, as shown in FIG. Figure 2 As shown, the system includes:

[0143] An acquisition module 21 is used to acquire spatial distribution data of mobile detection nodes and water area terrain feature data in the water area to be measured;

[0144] A determination module 22 is configured to determine a target detection node based on the spatial distribution data and the water area topographic feature data, and obtain a detection data set based on the target detection node;

[0145] A construction module 23 is configured to process the migration trajectories of heavy metal ions in the detection data set to generate a pollutant diffusion boundary prediction map to simulate and generate a multi-scenario diffusion envelope range, and generate an emergency control instruction set based on the multi-scenario diffusion envelope range;

[0146] The generation module 24 is used to combine the emergency control instruction set and the environmental impact factors to confirm the pollution diffusion trend and generate water quality environment detection results based on the pollution diffusion trend.

[0147] Figure 2 The water quality environment detection system based on 5G communication can perform Figure 1The implementation principle and technical effects of the water quality environment detection method based on 5G communication described in the embodiment shown will not be repeated here. The specific manner in which each module and unit performs operations in the water quality environment detection system based on 5G communication in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0148] In one possible design, Figure 2 A water quality environment detection system based on 5G communication in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0149] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0150] The processing component 32 is used to: obtain the spatial distribution data of mobile detection nodes and the water area terrain characteristic data in the water area to be tested; determine the target detection node based on the spatial distribution data and the water area terrain characteristic data, and obtain the detection data set based on the target detection node; process the migration trajectory of heavy metal ions in the detection data set to generate a pollutant diffusion boundary prediction map to simulate and generate a multi-scenario diffusion envelope range, and generate an emergency control instruction set based on the multi-scenario diffusion envelope range; combine the emergency control instruction set and environmental impact factors to confirm the pollution diffusion trend, and generate water quality environment detection results based on the pollution diffusion trend.

[0151] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0152] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0153] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0154] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0155] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0156] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0157] The embodiment of the present invention further provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 A water quality environment detection method based on 5G communication in the illustrated embodiment.

[0158] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0159] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0160] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion 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, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0161] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A water quality environment detection method based on 5G communication, characterized in that: include: Obtain spatial distribution data of mobile detection nodes and water area terrain feature data in the water area to be tested; Determining a target detection node based on the spatial distribution data and the water area topographic feature data, and obtaining a detection data set based on the target detection node; Processing the migration trajectories of heavy metal ions in the detection data set to generate a pollutant diffusion boundary prediction map to simulate and generate a multi-scenario diffusion envelope range, and generating an emergency control instruction set based on the multi-scenario diffusion envelope range; In combination with the emergency control instruction set and environmental impact factors, the pollution diffusion trend is confirmed, and based on the pollution diffusion trend, the water quality environment detection results are generated.

2. The method according to claim 1, characterized in that The heavy metal ion migration trajectories in the detection data set are processed to generate a pollutant diffusion boundary prediction map to simulate and generate a multi-scenario diffusion envelope range. Based on the multi-scenario diffusion envelope range, an emergency control instruction set is generated, including: Based on the detection data set, a water quality abnormal diffusion model and a dissolved oxygen distribution map are constructed, and the turbulent diffusion effect of the turbidity gradient field is synergistically coupled using the dissolved oxygen distribution map and the water quality abnormal diffusion model to generate a pollutant migration probability distribution matrix; Based on the pollutant migration probability distribution matrix, a three-dimensional hydrodynamic water quality model is constructed to reversely process the pollution source location and emission characteristics of the heavy metal ion migration trajectory and generate a pollutant diffusion boundary prediction map; Based on the pollutant diffusion boundary prediction map, a scenario analysis method is used to perform a three-dimensional hydrodynamic coupling simulation of the preset pollution load gradient to obtain a multi-scenario diffusion envelope range. Based on the multi-scenario diffusion envelope range, an emergency control instruction set is generated.

3. The method according to claim 2, characterized in that Based on the multi-scenario diffusion envelope, an emergency control instruction set is generated, including: The ecological exposure risk weighted superposition algorithm was used to perform spatial analysis on the diffusion envelope range of the multiple scenarios and the ecological red line area, and the pollutant peak value and spatial coverage rate of sensitive waters under each scenario were obtained; Calculate a hydrological cycle correction factor based on the deviation rate between the real-time flow monitoring data and the historical mean data for the same period; dynamically compare the pollutant peak value with the standard peak value of the corresponding pollutant in the surface water environmental quality standard based on the hydrological cycle correction factor to obtain a pollution comparison result; When the pollution comparison result meets the preset composite conditions, the pollution source positioning model is triggered to fuse the pollutant migration probability distribution matrix with the real-time monitoring data stream to generate a pollution source confidence interval geo-fence. Based on the pollution source confidence interval geo-fence, an emergency control instruction set is generated. The preset composite conditions include the first condition that the spatial intersection area of the warning area and the drinking water source protection area exceeds the dynamic threshold and the second condition that the pollutant concentration mutation index in the real-time monitoring data stream exceeds the mutation threshold. The dynamic threshold is set according to the pollutant toxicity level and the water supply scale of the water source.

4. The method according to claim 3, characterized in that When the pollution comparison result meets the preset composite conditions, the pollution source location model is triggered to fuse the pollutant migration probability distribution matrix with the real-time monitoring data stream to generate a pollution source confidence interval geo-fence. Based on the pollution source confidence interval geo-fence, an emergency control instruction set is generated. The preset composite conditions include a first condition that the spatial intersection area ratio of the warning area and the drinking water source protection area exceeds a dynamic threshold and a second condition that the pollutant concentration mutation index in the real-time monitoring data stream exceeds a mutation threshold. The dynamic threshold is set according to the pollutant toxicity level and the water supply scale of the water source, including: Using the pollutant toxicity level classification rules and the water source water supply scale classification standards, a dynamic threshold mapping table is constructed. Based on the dynamic threshold mapping table, the area proportion threshold corresponding to the combination is searched to generate a dynamic threshold set. Based on the dynamic threshold set, the spatial intersection area proportion of the warning area and the drinking water source protection area is calculated, where the combination includes the pollutant toxicity level and the water source water supply scale. Based on the real-time monitoring data stream, a sliding time window mechanism is used to extract a pollutant concentration time series, so as to calculate a pollutant concentration mutation index based on the pollutant concentration time series; If the proportion of the spatial intersection area exceeds the dynamic threshold of the corresponding pollutant toxicity level and the water supply scale of the water source, it is determined that the first condition is met; if the pollutant concentration mutation index exceeds the mutation threshold corresponding to the preset pollutant type, it is determined that the second condition is met; When the spatial intersection area ratio satisfies both the first condition and the second condition, the pollution source location model is triggered to fuse the pollutant migration probability distribution matrix with the real-time monitoring data stream to generate a pollution source confidence interval geo-fence; Based on the pollution source confidence interval geo-fence, an emergency control instruction set is generated.

5. The method according to claim 4, characterized in that Based on the pollution source confidence interval geo-fence, an emergency control instruction set is generated, including: Generate a list of potential pollution sources within the fence based on the boundary coordinates of the pollution source confidence interval geo-fence, the dynamic threshold set, and pollution source historical data; Based on the pollutant concentration mutation index and the water source service population size parameter, adjusting the existing instruction classification rules to obtain adjusted classification rules, and using the adjusted classification rules to generate a hierarchical control instruction set, the hierarchical control instruction set including shutdown instructions, production restriction instructions, and inspection instructions; Based on the list of potential pollution sources within the fence and the hierarchical control instruction set, combined with the real-time monitoring data stream and historical risk data, a multi-objective optimization algorithm is used to match the pollution source feature vector with the instruction level to generate an emergency control instruction set. The pollution source feature vector includes an industry type vector and an emission intensity vector.

6. The method according to claim 1, characterized in that Combining the emergency control instruction set and environmental impact factors, confirming the pollution diffusion trend, and generating water quality environment detection results based on the pollution diffusion trend, including: Comparing the pollutant diffusion boundary confidence level and the diffusion rate threshold in the emergency control instruction set to obtain a comparison result, and dynamically adjusting the sampling frequency of the target detection node based on the comparison result to obtain an adjusted detection node; Using the adjusted detection node to perform spatiotemporal alignment processing on the real-time monitoring data stream to obtain a spatiotemporal feature tensor; Performing multi-frequency cross-validation processing on the spatiotemporal feature tensor using a spatiotemporal convolutional neural network to generate a pollution diffusion confidence field; Based on the pollution diffusion confidence field and environmental influencing factors, the pollution diffusion trend is confirmed to generate water quality detection results. The environmental influencing factors include water flow velocity influencing factors and temperature gradient influencing factors.

7. The method according to claim 1, characterized in that Determining a target detection node based on the spatial distribution data and the water area terrain feature data, and obtaining a detection data set based on the target detection node, including: Based on the spatial distribution data and the water area terrain feature data, a preliminary detection path is generated, and adaptive topological adjustment is performed on the mobile detection nodes in the preliminary detection path to obtain a target detection node; Based on the target detection node, collecting dissolved oxygen data, turbidity data and heavy metal concentration monitoring data; Compensating for non-uniform sampling points in the dissolved oxygen data to generate a dissolved oxygen distribution map, enhancing the spatial gradient in the turbidity data to generate a turbidity gradient field, and performing particle tracking modeling on the migration trajectories in the heavy metal concentration monitoring data to generate heavy metal ion migration trajectories; The dissolved oxygen distribution map, the turbidity gradient field, and the heavy metal ion migration trajectory are fused to generate a detection data set.

8. A water quality environment detection system based on 5G communication, characterized in that: include: An acquisition module is used to obtain spatial distribution data of mobile detection nodes and water area terrain feature data in the water area to be tested; A determination module, configured to determine a target detection node based on the spatial distribution data and the water area topographic feature data, and obtain a detection data set based on the target detection node; A construction module is used to process the migration trajectories of heavy metal ions in the detection data set to generate a pollutant diffusion boundary prediction map to simulate and generate a multi-scenario diffusion envelope range, and generate an emergency control instruction set based on the multi-scenario diffusion envelope range; A generation module is used to combine the emergency control instruction set and environmental impact factors to confirm the pollution diffusion trend and generate water quality environment detection results based on the pollution diffusion trend.

9. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a water quality environment detection method based on 5G communication as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, a water quality environment detection method based on 5G communication as described in any one of claims 1 to 7 is implemented.

Images