Big data method for emergency response and disposal of water pollution accidents

Abstract

The invention discloses a big data method for emergency response and disposal of water pollution accidents. The method comprises the following steps: deploying various types of sensor networks in a pollution-prone area; transmitting the real-time data acquired by the sensor to a cloud storage system; monitoring a real-time event mode in the environmental data by using a complex event processing technology, and generating a real-time environmental data model; a machine learning technology and a geographic information system are used to analyze real-time environment data to predict a diffusion path and an influence range of pollutants, and a pollution source position is rapidly positioned; and intelligent emergency response measures are implemented through the intelligent decision support system. A real-time data stream processing technology and complex event processing are used, environmental data can be monitored in real time, emergencies can be quickly responded, the response time can be greatly shortened due to the real-time performance, pollution events can be found and processed earlier, and therefore environmental damage and influences of a water purification system are reduced.

Description

Technical Field

[0001] The present invention relates to the field of environmental protection, and in particular to a big data method for emergency response and disposal of water pollution accidents. Background Art

[0002] Water pollution accidents refer to unexpected events that occur in water bodies, resulting in water pollution or damage. Such accidents may be caused by various factors, including accidental industrial discharges, ship accidents, chemical leaks, agricultural pollution, and natural disasters such as floods and storms. Water pollution accidents may have serious impacts on the environment and ecosystems, and may also threaten human health and the sustainable use of water resources. Water pollution accidents, such as oil spills and hazardous chemical leaks, pose a serious threat to the environment and public safety. The timeliness and effectiveness of emergency response and disposal are crucial to reducing the impact of accidents on ecosystems and society.

[0003] At present, existing methods often rely on limited models and experience, face challenges in real-time data processing and complex environmental factors, and data processing methods face problems of large data volume and slow processing speed, especially when dealing with large-scale pollution incidents. Summary of the invention

[0004] The purpose of the present invention is to provide a big data method for emergency response and disposal of water pollution accidents to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A big data method for emergency response and disposal of water pollution accidents includes the following steps:

[0007] Step S1, deploying various types of sensor networks in pollution-prone areas to collect environmental data in real time;

[0008] Step S2, transmitting the real-time data acquired by the sensor to the cloud storage system, and performing real-time data cleaning and quality control to ensure the accuracy and integrity of the data;

[0009] Step S3, using a real-time big data processing platform to process and analyze the cleaned data, using complex event processing technology to monitor real-time event patterns in environmental data, and generating a real-time environmental data model;

[0010] Step S4, using machine learning technology and geographic information system to analyze real-time environmental data to predict the diffusion path and impact range of pollutants and quickly locate the pollution source;

[0011] Step S5, based on the location of pollution sources and the results of environmental impact assessment, intelligent emergency response measures are implemented through the intelligent decision support system, including resource allocation, pollution source blocking, water ecological restoration and public safety notifications.

[0012] Furthermore, in step S1, the multiple types of sensor networks include water quality sensors, meteorological sensors and biosensors, and the sensor networks are distributed in different pollution-prone areas, and the layout and quantity of each sensor are adaptively adjusted based on regional characteristics and expected pollutant quality;

[0013] Water quality sensor layout model expression:

[0014] [X_{water}(i,j)=f_{water}(Loc_i,Feat_j,Q_i)]

[0015] Among them, (X_{water}(i,j)) represents the layout decision variable of the (j)th water quality sensor in the (i)th region, (Loc_i) represents the geographical location characteristics of the (i)th region, (Feat_j) represents the characteristics of sensor (j), and (Q_i) represents the expected pollutant quality in the (i)th region;

[0016] Meteorological sensor layout model expression:

[0017] [X_{weather}(i,j)=f_{weather}(Loc_i,Feat_j,Q_i)]

[0018] Among them, (X_{weather}(i,j)) represents the layout decision variable of the (j)th meteorological sensor in the (i)th region, (Loc_i) represents the geographical location characteristics of the (i)th region, (Feat_j) represents the characteristics of sensor (j), and (Q_i) represents the expected pollutant quality in the (i)th region;

[0019] Biosensor layout model expression:

[0020] [X_{biological}(i,j)=f_{biological}(Loc_i,Feat_j,Q_i)]

[0021] Among them, (X_{biological}(i,j)) represents the layout decision variable of the (j)th biosensor in the (i)th region, (Loc_i) represents the geographical location characteristics of the (i)th region, (Feat_j) represents the characteristics of sensor (j), and (Q_i) represents the expected pollutant quality in the (i)th region.

[0022] Furthermore, in step S2, the cloud storage system adopts a distributed database structure to support real-time data storage and large-scale data processing;

[0023] Data transfer function expression:

[0024] [T_{data}(t)=f_{transmit}(Data_{sensor}(t),Dest_{cloud})]

[0025] Among them, (T_{data}(t)) represents the amount of data transmitted at time (t), (Data_{sensor}(t)) represents the data obtained from the sensor at time (t), and (Dest_{cloud}) represents the destination of the cloud storage system;

[0026] Data cleaning function expression:

[0027] [C_{clean}(Data_{raw}(t))=f_{clean}(Data_{raw}(t))]

[0028] Among them, (C_{clean}(Data_{raw}(t))) represents the amount of data after cleaning the original data (Data_{raw}(t)), and (Data_{raw}(t)) represents the unprocessed raw data at time (t).

[0029] Furthermore, in step S3, the real-time big data processing platform uses an open source complex event processing engine to perform real-time analysis and event detection on environmental data based on streaming data processing technology;

[0030] Complex event processing technology is used to monitor real-time event patterns in environmental data, expressed as:

[0031] [E_{complex}(t)=f_{CEP}(Data_{clean}(t))]

[0032] Among them, (E_{complex}(t)) represents the complex events detected at time (t), (Data_{clean}(t)) represents the environmental data after cleaning at time (t);

[0033] Use the results of complex event processing to generate a real-time environmental data model for further analysis and prediction. The expression is:

[0034] [M_{env}(t)=f_{model}(E_{complex}(t))]

[0035] Among them, (M_{env}(t)) represents the real-time environment data model at time (t).

[0036] Furthermore, in step S4, machine learning technology trains a pollution diffusion prediction model based on historical data and real-time sensor data to improve prediction accuracy and pollution source location accuracy;

[0037] Pollution diffusion prediction model, expression:

[0038] [P_{spread}(t)=f_{MLGIS}(Data_{clean}(t))]

[0039] Where (P_{spread}(t)) represents the pollutant spread prediction result at time (t),

[0040] (f_{MLGIS}) represents a model based on machine learning and geographic information system, using cleaned real-time environmental data (Data_{clean}(t)) for prediction;

[0041] Pollution source location model, expression:

[0042] [L_{source}(t)=f_{locate}(Data_{clean}(t))]

[0043] Among them, (L_{source}(t)) represents the pollution source positioning result at time (t), (f_{locate}) represents the positioning model based on machine learning and geographic information system, and the location of the pollution source is inferred using the cleaned real-time environmental data (Data_{clean}(t)).

[0044] Furthermore, in step S5, the intelligent decision support system displays the impact analysis and cost-benefit evaluation of different emergency response plans through a visual interface, supporting decision makers to quickly formulate and adjust emergency response strategies;

[0045] Emergency response decision model, expression:

[0046] [D_{decision}(t)=f_{decision}(L_{source}(t),M_{env}(t))]

[0047] Where (D_{decision}(t)) represents the emergency response decision result at time (t),

[0048] (f_{decision}) represents the decision support model based on pollution source location (L_{source}(t)) and real-time environmental data model (M_{env}(t)).

[0049] Resource allocation model, expression:

[0050] [R_{allocation}(t)=f_{allocate}(D_{decision}(t))]

[0051] Among them, (R_{allocation}(t)) represents the resource allocation decision result at time (t),

[0052] (f_{allocate}) represents the resource allocation model based on the emergency response decision (D_{decision}(t)), which is used to effectively implement emergency response measures.

[0053] Furthermore, in step S5, the emergency response measures include adjusting the operating parameters of the water quality treatment facilities in real time through an automated control system to quickly respond to changing conditions of the pollution incident.

[0054] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes any one of the big data methods for emergency response and disposal of water pollution accidents.

[0055] A computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to execute any one of the big data methods for emergency response and disposal of water pollution accidents.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] 1. The present invention uses real-time data stream processing technology and complex event processing, which can monitor environmental data in real time and respond quickly to emergencies. The real-time nature can greatly shorten the response time, so that pollution incidents can be discovered and handled earlier, thereby reducing environmental damage and the impact on the water purification system.

[0058] 2. The present invention uses a complex event processing engine and a geographic information system combined with machine learning technology to more accurately predict the diffusion path and impact range of pollutants, thereby enabling better response capabilities to the challenges of complex environmental factors and improving the accuracy and effectiveness of environmental monitoring and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 The present invention is a flowchart of a big data method for emergency response and disposal of water pollution accidents. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] See also Figure 1 , the present invention provides a technical solution:

[0062] A big data method for emergency response and disposal of water pollution accidents includes the following steps:

[0063] Step S1, deploying various types of sensor networks in pollution-prone areas to collect environmental data in real time;

[0064] Preferably, the multiple types of sensor networks include water quality sensors, meteorological sensors and biosensors, and the sensor networks are distributed in different pollution-prone areas, and the layout and quantity of each sensor are adaptively adjusted based on regional characteristics and expected pollutant quality;

[0065] Water quality sensor layout model expression:

[0066] [X_{water}(i,j)=f_{water}(Loc_i,Feat_j,Q_i)]

[0067] Among them, (X_{water}(i,j)) represents the layout decision variable of the (j)th water quality sensor in the (i)th region, (Loc_i) represents the geographical location characteristics of the (i)th region, (Feat_j) represents the characteristics of sensor (j), and (Q_i) represents the expected pollutant quality in the (i)th region;

[0068] Meteorological sensor layout model expression:

[0069] [X_{weather}(i,j)=f_{weather}(Loc_i,Feat_j,Q_i)]

[0070] Among them, (X_{weather}(i,j)) represents the layout decision variable of the (j)th meteorological sensor in the (i)th region, (Loc_i) represents the geographical location characteristics of the (i)th region, (Feat_j) represents the characteristics of sensor (j), and (Q_i) represents the expected pollutant quality in the (i)th region;

[0071] Biosensor layout model expression:

[0072] [X_{biological}(i,j)=f_{biological}(Loc_i,Feat_j,Q_i)]

[0073] Among them, (X_{biological}(i,j)) represents the layout decision variable of the (j)th biosensor in the (i)th region, (Loc_i) represents the geographical location characteristics of the (i)th region, (Feat_j) represents the characteristics of sensor (j), and (Q_i) represents the expected pollutant quality in the (i)th region;

[0074] In this step, a sensor network is deployed in designated sea areas to monitor water quality, meteorological and biological conditions in order to respond promptly to possible oil pollution incidents;

[0075] Assume that the sea area is divided into grids, each grid has different water characteristics, including flow rate and salinity. According to the expected possibility of oil pollution, the layout of water quality sensors in each grid is determined so that it can cover the key areas. The sensor layout model (X_{water}(i,j)) includes the solution of the optimization problem and takes into account the regional characteristics (Loc_i), sensor characteristics (Feat_j), and expected pollutant quality (Q_i);

[0076] Furthermore, based on the impact of meteorological conditions on pollution diffusion, including wind direction, wind speed, and humidity factors, the optimal layout of meteorological sensors is determined according to the prediction model in order to accurately predict the propagation path of pollutants. Biosensors are used to monitor aquatic biodiversity and its health. In areas that may be affected by pollution, biosensors are arranged according to the sensitivity of the ecosystem in order to detect ecosystem changes early.

[0077] Step S2, transmitting the real-time data acquired by the sensor to the cloud storage system, and performing real-time data cleaning and quality control to ensure the accuracy and integrity of the data;

[0078] Preferably, the cloud storage system adopts a distributed database structure to support real-time data storage and large-scale data processing;

[0079] Data transfer function expression:

[0080] [T_{data}(t)=f_{transmit}(Data_{sensor}(t),Dest_{cloud})]

[0081] Among them, (T_{data}(t)) represents the amount of data transmitted at time (t), (Data_{sensor}(t)) represents the data obtained from the sensor at time (t), and (Dest_{cloud}) represents the destination of the cloud storage system;

[0082] Data cleaning function expression:

[0083] [C_{clean}(Data_{raw}(t))=f_{clean}(Data_{raw}(t))]

[0084] Wherein, (C_{clean}(Data_{raw}(t))) represents the amount of data after cleaning the raw data (Data_{raw}(t)), and (Data_{raw}(t)) represents the unprocessed raw data at time (t);

[0085] In this step, the sensors begin to monitor the sea conditions in real time and transmit the data to the cloud system for further analysis and processing. Each sensor generates data periodically, and the data is transmitted to the cloud server in the form of data packets. The transmission function (T_{data}(t)) includes network protocol selection, data packet size and transmission rate factors. The data arriving at the cloud may be noisy, missing or outliers. The cleaning function (C_{clean}(Data_{raw}(t))) can process the data through filtering, interpolation or outlier detection to ensure the accuracy of subsequent analysis.

[0086] Step S3, using a real-time big data processing platform to process and analyze the cleaned data, using complex event processing technology to monitor real-time event patterns in environmental data, and generating a real-time environmental data model;

[0087] Preferably, the real-time big data processing platform is based on streaming data processing technology and uses an open source complex event processing engine to perform real-time analysis and event detection on environmental data;

[0088] Complex event processing technology is used to monitor real-time event patterns in environmental data, expressed as:

[0089] [E_{complex}(t)=f_{CEP}(Data_{clean}(t))]

[0090] Among them, (E_{complex}(t)) represents the complex events detected at time (t), (Data_{clean}(t)) represents the environmental data after cleaning at time (t);

[0091] Use the results of complex event processing to generate a real-time environmental data model for further analysis and prediction. The expression is:

[0092] [M_{env}(t)=f_{model}(E_{complex}(t))]

[0093] Where, (M_{env}(t)) represents the real-time environment data model at time (t);

[0094] In this step, the cloud system receives real-time data and uses complex event processing technology to monitor real-time event patterns in environmental data. Assume that after the data flows into the cloud, the complex event processing engine begins to monitor real-time event patterns, including abnormal water quality changes or abnormal meteorological conditions. The complex event processing model (E_{complex}(Data_{clean}(t))) uses rules or pattern recognition algorithms to detect and report potential pollution events. After complex event processing, an environmental data model is generated for further analysis and prediction. Among them, the model generation function (M_{env}(Data_{clean}(t))) includes statistical analysis, machine learning or geographic information system methods to establish a mathematical model of the real-time environmental status.

[0095] Step S4, using machine learning technology and geographic information system to analyze real-time environmental data to predict the diffusion path and impact range of pollutants and quickly locate the pollution source;

[0096] Preferably, machine learning technology trains a pollution diffusion prediction model based on historical data and real-time sensor data to improve prediction accuracy and pollution source location accuracy;

[0097] Pollution diffusion prediction model, expression:

[0098] [P_{spread}(t)=f_{MLGIS}(Data_{clean}(t))]

[0099] Where (P_{spread}(t)) represents the pollutant spread prediction result at time (t),

[0100] (f_{MLGIS}) represents a model based on machine learning and geographic information system, using cleaned real-time environmental data (Data_{clean}(t)) for prediction;

[0101] Pollution source location model, expression:

[0102] [L_{source}(t)=f_{locate}(Data_{clean}(t))]

[0103] Among them, (L_{source}(t)) represents the pollution source location result at time (t), (f_{locate}) represents the location model based on machine learning and geographic information system, and the location of the pollution source is inferred using the cleaned real-time environmental data (Data_{clean}(t));

[0104] In this step, it is confirmed that an oil pollution incident has occurred, and it is necessary to quickly predict the diffusion path of pollutants and accurately locate the pollution source. It is assumed that the machine learning model is trained using historical data and real-time sensor data to predict the diffusion path of oil pollution, where the model (P_{spread}(Data_{clean}(t))) includes a mathematical model, such as a diffusion equation or a machine learning algorithm, which is used to predict the spread range and speed of pollutants. According to the diffusion prediction results and real-time monitoring data, the location of the pollution source is located using a geographic information system and statistical analysis methods, and the positioning model (L_{source}(Data_{clean}(t))) is based on reverse reasoning or an optimization algorithm to accurately determine the geographic coordinates of the pollution source.

[0105] Step S5, based on the pollution source location and environmental impact assessment results, intelligent emergency response measures are implemented through the intelligent decision support system, including resource allocation, pollution source blocking, water ecological restoration and public safety notification;

[0106] Preferably, the intelligent decision support system displays the impact analysis and cost-benefit evaluation of different emergency response plans through a visual interface, supporting decision makers to quickly formulate and adjust emergency response strategies;

[0107] Emergency response decision model, expression:

[0108] [D_{decision}(t)=f_{decision}(L_{source}(t),M_{env}(t))]

[0109] Where (D_{decision}(t)) represents the emergency response decision result at time (t),

[0110] (f_{decision}) represents the decision support model based on pollution source location (L_{source}(t)) and real-time environmental data model (M_{env}(t)).

[0111] Resource allocation model, expression:

[0112] [R_{allocation}(t)=f_{allocate}(D_{decision}(t))]

[0113] Among them, (R_{allocation}(t)) represents the resource allocation decision result at time (t),

[0114] (f_{allocate}) represents the resource allocation model based on the emergency response decision (D_{decision}(t)), which is used to effectively implement emergency response measures;

[0115] In this step, after the pollution source is located, an intelligent decision support system is used to formulate an effective emergency response strategy. It is assumed that the decision support system provides evaluation and comparison of multiple emergency response plans based on the pollution source location and environmental impact assessment results. The decision model (D_{decision}(L_{source},M_{env}(t))) includes cost-benefit analysis, risk assessment and environmental impact simulation to support decision makers to make fast and accurate emergency response decisions. According to the selected emergency response plan, the decision support system allocates resources such as manpower, equipment and materials through optimization algorithms or simulation models. The resource allocation model (R_{allocation}(D_{decision}(t))) is based on optimization algorithms or greedy algorithms to maximize the efficiency and effectiveness of emergency response.

[0116] Furthermore, in step S5, the emergency response measures include adjusting the operating parameters of the water quality treatment facilities in real time through an automated control system to quickly respond to changing conditions of the pollution incident.

[0117] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes any one of the big data methods for emergency response and disposal of water pollution accidents.

[0118] A computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to execute any one of the big data methods for emergency response and disposal of water pollution accidents.

[0119] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0120] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A big data method for emergency response and disposal of water pollution accidents, characterized in that: The following steps are involved: Step S1, deploying various types of sensor networks in pollution-prone areas to collect environmental data in real time; Step S2, transmitting the real-time data acquired by the sensor to the cloud storage system, and performing real-time data cleaning and quality control to ensure the accuracy and integrity of the data; Step S3, using a real-time big data processing platform to process and analyze the cleaned data, using complex event processing technology to monitor real-time event patterns in environmental data, and generating a real-time environmental data model; Step S4, using machine learning technology and geographic information system to analyze real-time environmental data to predict the diffusion path and impact range of pollutants and quickly locate the pollution source; Step S5, based on the location of pollution sources and the results of environmental impact assessment, intelligent emergency response measures are implemented through the intelligent decision support system, including resource allocation, pollution source blocking, water ecological restoration and public safety notifications.

2. The big data method for emergency response and disposal of water pollution accidents according to claim 1 is characterized by: In step S1, the various types of sensor networks include water quality sensors, meteorological sensors and biosensors, and the sensor networks are distributed in different pollution-prone areas. The layout and quantity of each sensor are adaptively adjusted based on regional characteristics and expected pollutant quality; Water quality sensor layout model expression: [X_{water}(i,j)=f_{water}(Loc_i,Feat_j,Q_i)] Among them, (X_{water}(i,j)) represents the layout decision variable of the (j)th water quality sensor in the (i)th region, (Loc_i) represents the geographical location characteristics of the (i)th region, (Feat_j) represents the characteristics of sensor (j), and (Q_i) represents the expected pollutant quality in the (i)th region; Meteorological sensor layout model expression: [X_{weather}(i,j)=f_{weather}(Loc_i,Feat_j,Q_i)] Among them, (X_{weather}(i,j)) represents the layout decision variable of the (j)th meteorological sensor in the (i)th region, (Loc_i) represents the geographical location characteristics of the (i)th region, (Feat_j) represents the characteristics of sensor (j), and (Q_i) represents the expected pollutant quality in the (i)th region; Biosensor layout model expression: [X_{biological}(i,j)=f_{biological}(Loc_i,Feat_j,Q_i)] Among them, (X_{biological}(i,j)) represents the layout decision variable of the (j)th biosensor in the (i)th region, (Loc_i) represents the geographical location characteristics of the (i)th region, (Feat_j) represents the characteristics of sensor (j), and (Q_i) represents the expected pollutant quality in the (i)th region.

3. The big data method for emergency response and disposal of water pollution accidents according to claim 1 is characterized by: In step S2, the cloud storage system adopts a distributed database structure to support real-time data storage and large-scale data processing; Data transfer function expression: [T_{data}(t)=f_{transmit}(Data_{sensor}(t),Dest_{cloud})] Among them, (T_{data}(t)) represents the amount of data transmitted at time (t), (Data_{sensor}(t)) represents the data obtained from the sensor at time (t), and (Dest_{cloud}) represents the destination of the cloud storage system; Data cleaning function expression: [C_{clean}(Data_{raw}(t))=f_{clean}(Data_{raw}(t))] Among them, (C_{clean}(Data_{raw}(t))) represents the amount of data after cleaning the original data (Data_{raw}(t)), and (Data_{raw}(t)) represents the unprocessed raw data at time (t).

4. The big data method for emergency response and disposal of water pollution accidents according to claim 1 is characterized by: In step S3, the real-time big data processing platform uses an open source complex event processing engine based on streaming data processing technology to perform real-time analysis and event detection on environmental data; Complex event processing technology is used to monitor real-time event patterns in environmental data, expressed as: [E_{complex}(t)=f_{CEP}(Data_{clean}(t))] Among them, (E_{complex}(t)) represents the complex events detected at time (t), (Data_{clean}(t)) represents the environmental data after cleaning at time (t); Use the results of complex event processing to generate a real-time environmental data model for further analysis and prediction. The expression is: [M_{env}(t)=f_{model}(E_{complex}(t))] Among them, (M_{env}(t)) represents the real-time environment data model at time (t).

5. The big data method for emergency response and disposal of water pollution accidents according to claim 1 is characterized by: In step S4, machine learning technology trains the pollution diffusion prediction model based on historical data and real-time sensor data to improve the prediction accuracy and the accuracy of pollution source positioning; Pollution diffusion prediction model, expression: [P_{spread}(t)=f_{MLGIS}(Data_{clean}(t))] Where (P_{spread}(t)) represents the pollutant spread prediction result at time (t), (f_{MLGIS}) represents a model based on machine learning and geographic information system, using cleaned real-time environmental data (Data_{clean}(t)) for prediction; Pollution source location model, expression: [L_{source}(t)=f_{locate}(Data_{clean}(t))] Among them, (L_{source}(t)) represents the pollution source positioning result at time (t), (f_{locate}) represents the positioning model based on machine learning and geographic information system, and the location of the pollution source is inferred using the cleaned real-time environmental data (Data_{clean}(t)).

6. A big data method for emergency response and disposal of water pollution accidents according to claim 1, characterized in that: In step S5, the intelligent decision support system displays the impact analysis and cost-benefit evaluation of different emergency response plans through a visual interface, supporting decision makers to quickly formulate and adjust emergency response strategies; Emergency response decision model, expression: [D_{decision}(t)=f_{decision}(L_{source}(t),M_{env}(t))] Where (D_{decision}(t)) represents the emergency response decision result at time (t), (f_{decision}) represents the decision support model based on pollution source location (L_{source}(t)) and real-time environmental data model (M_{env}(t)); Resource allocation model, expression: [R_{allocation}(t)=f_{allocate}(D_{decision}(t))] Among them, (R_{allocation}(t)) represents the resource allocation decision result at time (t), (f_{allocate}) represents the resource allocation model based on the emergency response decision (D_{decision}(t)), which is used to effectively implement emergency response measures.

7. The big data method for emergency response and disposal of water pollution accidents according to claim 1 is characterized by: In step S5, the emergency response measures include adjusting the operating parameters of the water quality treatment facilities in real time through the automated control system to quickly respond to the changing conditions of the pollution incident.

8. A computer device, characterized in that: It includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the big data method for emergency response and disposal of water pollution accidents as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor executes the big data method for emergency response and disposal of water pollution accidents as described in any one of claims 1 to 7.

Images