CN116109462B - Pollution monitoring and early warning method and system for drinking water source area after natural disaster - Google Patents
Pollution monitoring and early warning method and system for drinking water source area after natural disaster Download PDFInfo
- Publication number
- CN116109462B CN116109462B CN202310378865.0A CN202310378865A CN116109462B CN 116109462 B CN116109462 B CN 116109462B CN 202310378865 A CN202310378865 A CN 202310378865A CN 116109462 B CN116109462 B CN 116109462B
- Authority
- CN
- China
- Prior art keywords
- pollution
- water source
- drinking water
- monitoring
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a method and a system for monitoring and early warning pollution of a drinking water source after natural disasters, comprising the following steps: obtaining the geographic position and the type of a target drinking water source area, extracting surrounding pollution characteristics and determining pollution factors and potential pollution factors; after the pollution monitoring indexes and the meteorological monitoring indexes are determined, sensor layout is carried out in a preset range of the target drinking water source area, after natural disaster early warning is carried out, pollution monitoring data of the target drinking water source area are obtained through the pollution monitoring indexes, a pollution prediction model is built based on deep learning, and pollution prediction information of the target drinking water source area is obtained; and carrying out pollution early warning on the target drinking water source area, and visually displaying pollution early warning information and pollution prediction information. According to the invention, effective early warning of water pollution events of a drinking water source in sudden water source places such as natural disasters is carried out through the monitoring of the Internet of things, the spatial characteristics and the dynamic characteristics of pollution information are obtained, and the pollution monitoring timeliness is ensured.
Description
Technical Field
The invention relates to the technical field of water source pollution monitoring, in particular to a method and a system for monitoring and early warning pollution of a drinking water source after natural disasters.
Background
Along with the shortage of water resources and the gradual frequent pollution phenomenon, the pollution problem of drinking water source is more and more emphasized, and the pollution control work of the water source is also a key environmental problem of current concern. The water source pollution causes a plurality of factors, natural disasters are one of the important reasons, most of water source areas are mountain areas, the mountain areas are changeable in climate and affected by heavy rainfall, mountain flood disasters are very easy to occur, sediment and stones are often carried in water flow which is exploded when mountain flood occurs, the destructive power is very strong, and large-area water source pollution is easy to cause. Because of uncertain factors of natural disasters, the difficulty of monitoring and early warning of water source pollution is increased.
The emergency monitoring of sudden pollution events in the water source can provide information such as pollutant types, concentration distribution, influence ranges, development situations and the like for accident handling decision departments, so that the monitoring of natural disasters and water bodies after the natural disasters is particularly important in order to protect the water source and effectively reduce the pollution degree of the natural disasters to the water source. The water pollution emergency treatment real-time monitoring method for the water source is difficult to adapt to the modern development requirements of emergency treatment, so that research and development of the water pollution emergency treatment real-time monitoring and early warning platform are very necessary, good help decision making of test data is guaranteed, and the problem that how to acquire priority monitoring data in real time based on a cloud frame and the Internet of things in the real-time monitoring and early warning platform, and ensuring accurate and effective monitoring and early warning information is an urgent need to be solved is solved.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method and a system for monitoring and early warning pollution of a drinking water source after natural disasters.
The first aspect of the invention provides a pollution monitoring and early warning method for a drinking water source area after natural disasters, which comprises the following steps:
obtaining the geographic position and the type of a target drinking water source place, extracting surrounding pollution characteristics according to the geographic position and the type of the source place, and determining pollution factors and potential pollution factors according to the pollution characteristics;
determining pollution monitoring indexes and weather monitoring indexes based on the pollution factors and potential pollution factors, arranging sensors within a preset range of a target drinking water source area according to the pollution monitoring indexes and the weather monitoring indexes, and monitoring the occurrence of natural disasters through weather monitoring data;
when the meteorological monitoring index exceeds a preset threshold range, natural disaster early warning is generated, pollution monitoring data of the target drinking water source area are obtained through the pollution monitoring index, a pollution prediction model is built based on deep learning, and pollution prediction information of the target drinking water source area is obtained;
and carrying out pollution early warning on the target drinking water source area according to the pollution prediction information, and visually displaying the pollution early warning information and the pollution prediction information.
In this scheme, according to geographic position and water source type draw peripheral pollution characteristic, confirm pollution factor and potential pollution factor through pollution characteristic, specifically do:
acquiring GIS geographic data within a preset range of a target drinking water source place by a GIS means, acquiring the topographic features of the water source place according to the GIS geographic data, identifying the type of the water source place, and setting a label of the target drinking water source place;
acquiring a pollution source in a preset range of a target drinking water source, acquiring a risk pollution source according to the position of the pollution source and the topographic features of the water source, and extracting the pollution source features of the risk pollution source according to pollutants related to the risk pollution source;
acquiring historical occurrence data of sudden water pollution by using a big data method, carrying out statistical analysis on the historical occurrence data of sudden water pollution by using the pollution source characteristics, acquiring the sudden times corresponding to the pollution source characteristics, screening the pollution sources, and independently marking the sudden water pollution caused by natural disasters;
summarizing the screened pollution source characteristics to obtain pollution characteristics of the periphery of the water source, determining pollution factors according to the pollution characteristics, wherein the pollution factors carry the position characteristics of pollution, determining potential pollution factors according to the pollution source characteristics corresponding to the burst water pollution marked independently, and setting double labels for repeated pollution factors.
In this scheme, according to pollution monitoring index and meteorological monitoring index are laid at target drinking water source place presets within range sensor, carry out natural disasters's emergence monitoring through meteorological monitoring data, specifically do:
obtaining pollution factors and potential pollution factors of a target drinking water source area, setting pollutant monitoring indexes according to the pollution factors and the potential pollution factors, and determining meteorological monitoring indexes according to historical natural disaster conditions of the area of the target drinking water source area;
determining corresponding sensor types through the pollutant monitoring index and the meteorological monitoring index, determining initial layout ranges of sensors of each type according to pollution factors and pollution position characteristics of potential pollution factors, and determining the number of the sensors according to the historical burst times of pollution sources in the initial layout ranges;
determining the comprehensive coverage rate of the sensors as an adaptability function according to the maximum coverage distance of the various sensors and the position of a pollution source to be monitored, and introducing adaptive variation and dynamic weight which change along with the iteration number to improve a particle swarm algorithm;
generating optimal layout positions of local sensors and optimal layout positions and layout quantity of global sensors in each initial layout range and a preset range of a target drinking water source area through an improved particle swarm algorithm;
And monitoring weather through sensors distributed in a preset range of a target drinking water source area to obtain weather monitoring data, generating natural disaster early warning when the weather monitoring data is larger than a preset threshold value, and waking up related sensors corresponding to potential pollution factors.
In the scheme, a pollution prediction model is built based on deep learning, and pollution prediction information of a target drinking water source area is obtained, specifically:
acquiring pollution monitoring data of a target drinking water source, respectively extracting time characteristics and space characteristics of the pollution monitoring data, and generating a space-time characteristic sequence of the pollution monitoring data;
constructing a pollution prediction model based on an RBF neural network, acquiring training data through historical sudden pollution monitoring data, and training the pollution prediction model by utilizing the training data;
and inputting the space-time characteristic sequence of the pollution monitoring data and the pollutant concentration data into a trained pollution prediction model, and acquiring pollution prediction information according to an output layer of the pollution prediction model.
In the scheme, the time feature and the space feature of the pollution monitoring data are extracted respectively to generate a space-time feature sequence of the pollution monitoring data, which is specifically as follows:
acquiring pollution monitoring data of a target drinking water source after natural disaster early warning, acquiring index standard data corresponding to normal monitoring according to pollution monitoring indexes, and determining interpretation data of all monitoring indexes according to the index standard data;
Performing data matching on the obtained interpretation data of each monitoring index and meteorological data to generate a monitoring data time sequence corresponding to each sensor, inputting the monitoring data time sequence into a time convolution neural network, and obtaining concentration change trend characteristics of pollutants according to the trained time convolution neural network;
representing the topological structure covered by the sensor connection of the target drinking water source area in a graph form, learning the graph representation of the topological structure through a graph attention network, and guiding the concentration change trend characteristics of each sensor node into the graph attention network;
and acquiring the attention weight of the adjacent sensor nodes to the target node through an attention mechanism, distributing the attention weight to each adjacent sensor node, generating an aggregate representation of the features by utilizing neighbor aggregation of the graph attention network, and generating a pollution monitoring data space-time feature sequence.
In this scheme, carry out the pollution early warning of target drinking water source area according to pollution forecast information to carry out visual demonstration with pollution early warning information and pollution forecast information, specifically:
obtaining pollution prediction information of a target drinking water source area, setting a pollution threshold according to the pollution time of the target drinking water source area, and obtaining pollution peak concentrations of different time stamps and distances from the peak concentrations to pollution sources according to the pollution prediction information;
Dividing the preset range of the target drinking water source area into a plurality of subareas according to GIS geographic data and sensor layout points, and acquiring the pollution peak concentration in the subareas according to the current time stamp;
judging whether the pollution peak value in the subarea is larger than a pollution threshold value corresponding to the current time stamp, if so, acquiring pollution concentration deviation, and acquiring a corresponding early warning grade according to the pollution concentration deviation to be matched with the subarea;
obtaining partition early warning within a preset range of a target drinking water source area, obtaining a three-dimensional visual model of the target drinking water source area according to the GIS geographic data, and guiding the partition early warning into the three-dimensional visual model;
and determining a pollutant range according to the partition early warning of the current timestamp, and acquiring the pollutant arrival time of the non-early-warning area based on the pollutant range, the pollutant peak concentration and the change characteristic of the distance from the peak concentration to the pollution source, thereby providing a basis for pollution emergency measures.
The second aspect of the invention also provides a pollution monitoring and early warning system for a drinking water source after natural disasters, which comprises: the device comprises a storage and a processor, wherein the storage comprises a pollution monitoring and early warning method program of a drinking water source area after natural disasters, and the pollution monitoring and early warning method program of the drinking water source area after natural disasters is implemented when executed by the processor as follows:
Obtaining the geographic position and the type of a target drinking water source place, extracting surrounding pollution characteristics according to the geographic position and the type of the source place, and determining pollution factors and potential pollution factors according to the pollution characteristics;
determining pollution monitoring indexes and weather monitoring indexes based on the pollution factors and potential pollution factors, arranging sensors within a preset range of a target drinking water source area according to the pollution monitoring indexes and the weather monitoring indexes, and monitoring the occurrence of natural disasters through weather monitoring data;
when the meteorological monitoring index exceeds a preset threshold range, natural disaster early warning is generated, pollution monitoring data of the target drinking water source area are obtained through the pollution monitoring index, a pollution prediction model is built based on deep learning, and pollution prediction information of the target drinking water source area is obtained;
and carrying out pollution early warning on the target drinking water source area according to the pollution prediction information, and visually displaying the pollution early warning information and the pollution prediction information.
The invention discloses a method and a system for monitoring and early warning pollution of a drinking water source after natural disasters, comprising the following steps: obtaining the geographic position and the type of a target drinking water source area, extracting surrounding pollution characteristics and determining pollution factors and potential pollution factors; after the pollution monitoring indexes and the meteorological monitoring indexes are determined, sensor layout is carried out in a preset range of the target drinking water source area, after natural disaster early warning is carried out, pollution monitoring data of the target drinking water source area are obtained through the pollution monitoring indexes, a pollution prediction model is built based on deep learning, and pollution prediction information of the target drinking water source area is obtained; and carrying out pollution early warning on the target drinking water source area, and visually displaying pollution early warning information and pollution prediction information. According to the invention, effective early warning of water pollution events of a drinking water source in sudden water source places such as natural disasters is carried out through the monitoring of the Internet of things, the spatial characteristics and the dynamic characteristics of pollution information are obtained, and the pollution monitoring timeliness is ensured.
Drawings
FIG. 1 shows a flow chart of a pollution monitoring and early warning method for a drinking water source after natural disasters;
FIG. 2 is a flow chart of a method of generating a sequence of spatiotemporal features of pollution monitoring data in accordance with the present invention;
FIG. 3 shows a flow chart of a method for performing pollution early warning on a target drinking water source according to pollution prediction information;
FIG. 4 shows a block diagram of a pollution monitoring and early warning system for a drinking water source after natural disasters.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
FIG. 1 shows a flow chart of a pollution monitoring and early warning method for a drinking water source after natural disasters.
As shown in fig. 1, the first aspect of the present invention provides a method for monitoring and early warning pollution of a drinking water source after a natural disaster, comprising:
s102, acquiring the geographic position and the type of a target drinking water source, extracting surrounding pollution characteristics according to the geographic position and the type of the source, and determining pollution factors and potential pollution factors according to the pollution characteristics;
s104, determining pollution monitoring indexes and weather monitoring indexes based on the pollution factors and the potential pollution factors, arranging sensors within a preset range of a target drinking water source area according to the pollution monitoring indexes and the weather monitoring indexes, and monitoring the occurrence of natural disasters through weather monitoring data;
s106, when the weather monitoring index exceeds a preset threshold range, natural disaster early warning is generated, pollution monitoring data of the target drinking water source area are obtained through the pollution monitoring index, a pollution prediction model is built based on deep learning, and pollution prediction information of the target drinking water source area is obtained;
s108, carrying out pollution early warning on the target drinking water source area according to the pollution prediction information, and carrying out visual display on the pollution early warning information and the pollution prediction information.
The method comprises the steps of obtaining GIS geographic data within a preset range of a target drinking water source region through a GIS means, obtaining the topographic features of the water source region according to the GIS geographic data, identifying the type of the water source region, wherein the type of the water source region comprises a ground water source, an overground water source, a distributed water source, a centralized water source and the like, and setting a label of the target drinking water source region; the method comprises the steps of obtaining pollution sources in a preset range of a target drinking water source area, including urban domestic sewage discharge, industrial sewage discharge, agricultural sewage discharge, pollution discharge caused by traffic accidents and the like, and obtaining the terrain position which is easy to cause natural disasters, such as debris flow caused by climate mutation and the like, through terrain feature analysis of the water source area. Acquiring a risk pollution source according to the position of the pollution source and the topographic features of the water source, and extracting pollution source features of the risk pollution source according to pollutants related to the risk pollution source; acquiring historical occurrence data of sudden water pollution by using a big data method, carrying out statistical analysis on the historical occurrence data of sudden water pollution by using the pollution source characteristics, acquiring the sudden times corresponding to the pollution source characteristics, screening the pollution sources, retaining the pollution source characteristics with the sudden times larger than a preset threshold, and independently marking the sudden water pollution caused by natural disasters; summarizing the screened pollution source characteristics to obtain pollution characteristics around a water source area, determining pollution factors according to the pollution characteristics, wherein the pollution factors carry pollution position characteristics, analyzing the water pollution data caused by the historical natural disasters because the water pollution historical data caused by the natural disasters are relatively less, determining potential pollution factors according to the pollution source characteristics corresponding to the individually marked sudden water pollution, and setting double labels for the repeated pollution factors.
It is to be noted that, the pollution factor and the potential pollution factor of the target drinking water source are obtained, the pollutant monitoring index is set according to the pollution factor and the potential pollution factor, the weather monitoring index is determined according to the historical natural disaster condition of the area of the target drinking water source, the corresponding sensor category is determined according to the pollutant monitoring index and the weather monitoring index, preferably, the geographic deformation sensor is also arranged, the natural disasters such as earthquake, debris flow and the like are monitored, the initial layout range of the sensors of each category is determined according to the pollution position characteristics of the pollution factor and the potential pollution factor, and the number of the sensors is determined according to the historical burst times of the pollution source in the initial layout range; determining the comprehensive coverage rate of the sensors as a fitness function according to the maximum distance covered by the various sensors and the position of the pollution source to be monitored, wherein the comprehensive coverage rate is expressed as
Wherein->
For the comprehensive coverage of the sensor, +.>
For the maximum coverage of the sensor,
for the distance of the target pollution source a to the sensor b, +.>
The method comprises the steps that a preset range is adopted, when a sensor is arranged outside the maximum coverage range of the sensor, the probability of monitoring a target pollution source is 0, and when the sensor is arranged in the preset range, the probability of monitoring the target pollution source is 1; the comprehensive coverage rate of all the sensors is aggregated, and an fitness function is obtained;
Introducing adaptive variation and dynamic weight which change along with the iteration times to improve a particle swarm algorithm; the self-adaptive variation expands the search space to lead the particles to jump out of the currently searched optimal position, thereby searching in a larger space, being beneficial to better solution of the particle search, the dynamic weight reflects the proportion of the particles inheriting the previous speed, changes along with the iteration times of the particles, optimizes the particle search and has the dynamic weight
The calculation formula is as follows: />
，
For initial dynamic weights, ++>
For final dynamic weight, ++>
For the number of iterations->
The maximum iteration number; generating optimal layout positions of local sensors and optimal layout positions and layout quantity of global sensors in each initial layout range and a preset range of a target drinking water source area through an improved particle swarm algorithm; and monitoring weather through sensors distributed in a preset range of a target drinking water source area to obtain weather monitoring data, generating natural disaster early warning when the weather monitoring data is larger than a preset threshold value, and waking up related sensors corresponding to potential pollution factors, wherein the sensors corresponding to the pollution factors are in a state of being always on, so as to perform daily pollution monitoring.
FIG. 2 illustrates a flow chart of a method of generating a sequence of spatiotemporal features of pollution monitoring data in accordance with the present invention.
According to the embodiment of the invention, the time characteristics and the space characteristics of the pollution monitoring data are respectively extracted to generate a space-time characteristic sequence of the pollution monitoring data, which is specifically as follows:
s202, pollution monitoring data of a target drinking water source area are obtained after natural disaster early warning, index standard data corresponding to normal monitoring is obtained according to pollution monitoring indexes, and interpretation data of all monitoring indexes are determined according to the index standard data;
s204, performing data matching on the acquired interpretation data of each monitoring index and meteorological data to generate a monitoring data time sequence corresponding to each sensor, inputting the monitoring data time sequence into a time convolution neural network, and acquiring concentration change trend characteristics of pollutants according to the trained time convolution neural network;
s206, representing the topological structure according to the connection coverage of the sensor at the target drinking water source site in a graph form, learning the graph representation of the topological structure through a graph attention network, and guiding the concentration change trend characteristics of each sensor node into the graph attention network;
and S208, acquiring the attention weight of the adjacent sensor nodes to the target node through an attention mechanism, distributing the attention weight to each adjacent sensor node, generating an aggregate representation of the features by utilizing neighbor aggregation of the graph attention network, and generating a time-space feature sequence of the pollution monitoring data.
The time convolution neural network is used for extracting the characteristics of the time sequence of the monitoring data corresponding to each sensor, mining the time characteristics of the time sequence of the monitoring data, and has stable gradient, so that the problems of gradient disappearance and gradient explosion are avoided, and the stability of characteristic extraction is ensured. Representing a topological structure covered by a sensor connection of a target drinking water source area in a graph form, taking the sensors as point structures of the graph form, generating edge structures in the graph form according to the connection among the sensors, learning and representing the graph form through a graph attention network, and learning attention values between a target sensor node i and an adjacent sensor node j in the graph form of the topological structure
The method comprises the following steps:
wherein, the liquid crystal display device comprises a liquid crystal display device,
representing an activation function->
Representing vector mapping parameters, ">
Representing feature vector concatenation->
Representing a characteristic transformation parameter matrix, < >>
A low-dimensional vector representation representing a target sensor node i and an adjacent sensor node j;
by means of the attention value between the target sensor node i and the adjacent sensor node j
Determining the attention weight by the ratio to the target sensor node i and the sum of the attention values of all neighboring sensor nodes >
After the attention weight is normalized, the characteristics of the target sensor node are updated and represented by utilizing a neighbor aggregation mechanism,
wherein->
Final updated representation representing target sensor node i,/->
Represents an activation function, j represents the number of neighboring node items, < ->
Representing a set of neighboring nodes of the target sensor node i.
Constructing a pollution prediction model based on deep learning, acquiring pollution prediction information of a target drinking water source region, acquiring pollution monitoring data of the target drinking water source region, extracting time features and space features of the pollution monitoring data respectively, and generating a pollution monitoring data space-time feature sequence; constructing a pollution prediction model based on an RBF neural network, wherein the RBF neural network comprises an input layer, a hidden layer and an output layer, acquiring training data through historical sudden pollution monitoring data, and training the pollution prediction model by utilizing the training data; the method comprises the steps of inputting a time-space characteristic sequence of pollution monitoring data and pollutant concentration data into a trained pollution prediction model, acquiring pollution prediction information according to an output layer of the pollution prediction model, and obtaining information such as peak concentrations at different times, distances between the peak concentrations and a pollution source, a transmission range of pollutants, affected time of a water source, and exceeding standard distances of water quality according to the pollution prediction information.
FIG. 3 shows a flow chart of a method for carrying out pollution early warning on a target drinking water source according to pollution prediction information.
According to the embodiment of the invention, the pollution early warning of the target drinking water source area is carried out according to the pollution prediction information, and the pollution early warning information and the pollution prediction information are visually displayed, specifically:
s302, pollution prediction information of a target drinking water source is obtained, a pollution threshold is set according to the pollution time of the target drinking water source, and pollution peak concentrations of different time stamps and distances from the peak concentrations to pollution sources are obtained through the pollution prediction information;
s304, dividing the preset range of the target drinking water source area into a plurality of subareas according to GIS geographic data and sensor layout points, and acquiring the pollution peak concentration in the subareas according to the current time stamp;
s306, judging whether a pollution peak value in the subarea is larger than a pollution threshold value corresponding to the current time stamp, if so, acquiring pollution concentration deviation, and acquiring a corresponding early warning level according to the pollution concentration deviation to be matched with the subarea;
s308, obtaining partition early warning in a preset range of a target drinking water source area, obtaining a three-dimensional visual model of the target drinking water source area according to the GIS geographic data, and guiding the partition early warning into the three-dimensional visual model;
S310, determining a pollutant range according to the partition early warning of the current timestamp, and simultaneously acquiring the pollutant arrival time of the non-early-warning area based on the pollutant range, the pollutant peak concentration and the change characteristic of the distance from the peak concentration to the pollutant source, so as to provide a basis for pollution emergency measures.
According to the embodiment of the invention, emergency measures of a target drinking water source area are generated based on pollution prediction information, and specifically: constructing a sudden water pollution database, matching the monitoring data of the historical sudden water pollution with corresponding emergency measures, and storing the monitoring data into the sudden water pollution database;
analyzing sensor data according to early warning information of a target drinking water source area, acquiring natural disaster type and natural disaster early warning degree, and predicting damage degree and implementation necessity of protective measures of the target drinking water source area through the natural disaster early warning degree;
when the natural disaster early warning degree is greater than or equal to a preset early warning degree threshold, the damage of the target drinking water source area is considered to be serious, the danger degree is high, and protection measures are not needed;
when the natural disaster early warning degree is smaller than a preset early warning degree threshold value, acquiring pollution change trend characteristics of a water source area, searching in the sudden water pollution database according to the pollution change characteristic trend, acquiring historical data with similarity meeting a preset standard in a data space, and extracting emergency measures in the historical data;
Screening the emergency measures according to the characteristics of the current geological disasters and the topographic characteristics of the target drinking water source, and carrying out continuous prediction on the geological disasters according to the characteristics of the current geological disasters to obtain the optimal implementation time of the screened emergency measures.
FIG. 4 shows a block diagram of a pollution monitoring and early warning system for a drinking water source after natural disasters.
The second aspect of the present invention also provides a pollution monitoring and early warning system 4 for a drinking water source after natural disasters, the system comprising: the storage 41 and the processor 42, wherein the storage comprises a pollution monitoring and early warning method program of a drinking water source after natural disasters, and the pollution monitoring and early warning method program of the drinking water source after natural disasters is implemented when executed by the processor as follows:
obtaining the geographic position and the type of a target drinking water source place, extracting surrounding pollution characteristics according to the geographic position and the type of the source place, and determining pollution factors and potential pollution factors according to the pollution characteristics;
determining pollution monitoring indexes and weather monitoring indexes based on the pollution factors and potential pollution factors, arranging sensors within a preset range of a target drinking water source area according to the pollution monitoring indexes and the weather monitoring indexes, and monitoring the occurrence of natural disasters through weather monitoring data;
When the meteorological monitoring index exceeds a preset threshold range, natural disaster early warning is generated, pollution monitoring data of the target drinking water source area are obtained through the pollution monitoring index, a pollution prediction model is built based on deep learning, and pollution prediction information of the target drinking water source area is obtained;
and carrying out pollution early warning on the target drinking water source area according to the pollution prediction information, and visually displaying the pollution early warning information and the pollution prediction information.
The method comprises the steps of obtaining GIS geographic data within a preset range of a target drinking water source region through a GIS means, obtaining the topographic features of the water source region according to the GIS geographic data, identifying the type of the water source region, wherein the type of the water source region comprises a ground water source, an overground water source, a distributed water source, a centralized water source and the like, and setting a label of the target drinking water source region; the method comprises the steps of obtaining pollution sources in a preset range of a target drinking water source area, including urban domestic sewage discharge, industrial sewage discharge, agricultural sewage discharge, pollution discharge caused by traffic accidents and the like, and obtaining the terrain position which is easy to cause natural disasters, such as debris flow caused by climate mutation and the like, through terrain feature analysis of the water source area. Acquiring a risk pollution source according to the position of the pollution source and the topographic features of the water source, and extracting pollution source features of the risk pollution source according to pollutants related to the risk pollution source; acquiring historical occurrence data of sudden water pollution by using a big data method, carrying out statistical analysis on the historical occurrence data of sudden water pollution by using the pollution source characteristics, acquiring the sudden times corresponding to the pollution source characteristics, screening the pollution sources, retaining the pollution source characteristics with the sudden times larger than a preset threshold, and independently marking the sudden water pollution caused by natural disasters; summarizing the screened pollution source characteristics to obtain pollution characteristics around a water source area, determining pollution factors according to the pollution characteristics, wherein the pollution factors carry pollution position characteristics, analyzing the water pollution data caused by the historical natural disasters because the water pollution historical data caused by the natural disasters are relatively less, determining potential pollution factors according to the pollution source characteristics corresponding to the individually marked sudden water pollution, and setting double labels for the repeated pollution factors.
The method is used for obtaining the target drinking waterThe method comprises the steps of setting pollutant monitoring indexes according to pollution factors and potential pollution factors of a source land, determining meteorological monitoring indexes according to historical natural disaster conditions of an area where a target drinking water source land is located, determining corresponding sensor types through the pollutant monitoring indexes and the meteorological monitoring indexes, determining initial layout ranges of sensors of the various types according to pollution position characteristics of the pollution factors and the potential pollution factors, and determining the number of the sensors according to historical burst times of the pollution sources in the initial layout ranges; determining the comprehensive coverage rate of the sensors as a fitness function according to the maximum distance covered by the various sensors and the position of the pollution source to be monitored, wherein the comprehensive coverage rate is expressed as
Wherein->
For the comprehensive coverage of the sensor, +.>
For maximum coverage of the sensor, +.>
For the distance of the target pollution source a to the sensor b, +.>
The method comprises the steps that a preset range is adopted, when a sensor is arranged outside the maximum coverage range of the sensor, the probability of monitoring a target pollution source is 0, and when the sensor is arranged in the preset range, the probability of monitoring the target pollution source is 1; the comprehensive coverage rate of all the sensors is aggregated, and an fitness function is obtained;
Introducing adaptive variation and dynamic weight which change along with the iteration times to improve a particle swarm algorithm; the self-adaptive variation expands the search space to lead the particles to jump out of the currently searched optimal position, thereby searching in a larger space, being beneficial to searching better solutions by the particles, the dynamic weight reflects the proportion of the particles to inherit the previous speed, and the dynamic weight changes along with the iteration times of the particles, thus the method is suitable for the search of the particlesParticle search optimization, dynamic weighting
The calculation formula is as follows: />
，
For initial dynamic weights, ++>
For final dynamic weight, ++>
For the number of iterations->
The maximum iteration number; generating optimal layout positions of local sensors and optimal layout positions and layout quantity of global sensors in each initial layout range and a preset range of a target drinking water source area through an improved particle swarm algorithm; and monitoring weather through sensors distributed in a preset range of a target drinking water source area to obtain weather monitoring data, generating natural disaster early warning when the weather monitoring data is larger than a preset threshold value, and waking up related sensors corresponding to potential pollution factors, wherein the sensors corresponding to the pollution factors are in a state of being always on, so as to perform daily pollution monitoring.
According to the embodiment of the invention, the time characteristics and the space characteristics of the pollution monitoring data are respectively extracted to generate a space-time characteristic sequence of the pollution monitoring data, which is specifically as follows:
acquiring pollution monitoring data of a target drinking water source after natural disaster early warning, acquiring index standard data corresponding to normal monitoring according to pollution monitoring indexes, and determining interpretation data of all monitoring indexes according to the index standard data;
performing data matching on the obtained interpretation data of each monitoring index and meteorological data to generate a monitoring data time sequence corresponding to each sensor, inputting the monitoring data time sequence into a time convolution neural network, and obtaining concentration change trend characteristics of pollutants according to the trained time convolution neural network;
representing the topological structure covered by the sensor connection of the target drinking water source area in a graph form, learning the graph representation of the topological structure through a graph attention network, and guiding the concentration change trend characteristics of each sensor node into the graph attention network;
and acquiring the attention weight of the adjacent sensor nodes to the target node through an attention mechanism, distributing the attention weight to each adjacent sensor node, generating an aggregate representation of the features by utilizing neighbor aggregation of the graph attention network, and generating a pollution monitoring data space-time feature sequence.
The time convolution neural network is used for extracting the characteristics of the time sequence of the monitoring data corresponding to each sensor, mining the time characteristics of the time sequence of the monitoring data, and has stable gradient, so that the problems of gradient disappearance and gradient explosion are avoided, and the stability of characteristic extraction is ensured. Representing a topological structure covered by a sensor connection of a target drinking water source area in a graph form, taking the sensors as point structures of the graph form, generating edge structures in the graph form according to the connection among the sensors, learning and representing the graph form through a graph attention network, and learning attention values between a target sensor node i and an adjacent sensor node j in the graph form of the topological structure
The method comprises the following steps:
wherein, the liquid crystal display device comprises a liquid crystal display device,
representing an activation function->
Representing vector mapping parameters, ">
Representing feature vector concatenation->
Representing a characteristic transformation parameter matrix, < >>
A low-dimensional vector representation representing a target sensor node i and an adjacent sensor node j;
by means of the attention value between the target sensor node i and the adjacent sensor node j
Determining the attention weight by the ratio to the target sensor node i and the sum of the attention values of all neighboring sensor nodes >
After the attention weight is normalized, the characteristics of the target sensor node are updated and represented by utilizing a neighbor aggregation mechanism,
wherein->
Final updated representation representing target sensor node i,/->
Represents an activation function, j represents the number of neighboring node items, < ->
Representing a set of neighboring nodes of the target sensor node i.
Constructing a pollution prediction model based on deep learning, acquiring pollution prediction information of a target drinking water source region, acquiring pollution monitoring data of the target drinking water source region, extracting time features and space features of the pollution monitoring data respectively, and generating a pollution monitoring data space-time feature sequence; constructing a pollution prediction model based on an RBF neural network, wherein the RBF neural network comprises an input layer, a hidden layer and an output layer, acquiring training data through historical sudden pollution monitoring data, and training the pollution prediction model by utilizing the training data; the method comprises the steps of inputting a time-space characteristic sequence of pollution monitoring data and pollutant concentration data into a trained pollution prediction model, acquiring pollution prediction information according to an output layer of the pollution prediction model, and obtaining information such as peak concentrations at different times, distances between the peak concentrations and pollution sources, affected time of a water source, exceeding standard distances of water quality and the like according to the pollution prediction information.
According to the embodiment of the invention, the pollution early warning of the target drinking water source area is carried out according to the pollution prediction information, and the pollution early warning information and the pollution prediction information are visually displayed, specifically:
obtaining pollution prediction information of a target drinking water source area, setting a pollution threshold according to the pollution time of the target drinking water source area, and obtaining pollution peak concentrations of different time stamps and distances from the peak concentrations to pollution sources according to the pollution prediction information;
dividing the preset range of the target drinking water source area into a plurality of subareas according to GIS geographic data and sensor layout points, and acquiring the pollution peak concentration in the subareas according to the current time stamp;
judging whether the pollution peak value in the subarea is larger than a pollution threshold value corresponding to the current time stamp, if so, acquiring pollution concentration deviation, and acquiring a corresponding early warning grade according to the pollution concentration deviation to be matched with the subarea;
obtaining partition early warning within a preset range of a target drinking water source area, obtaining a three-dimensional visual model of the target drinking water source area according to the GIS geographic data, and guiding the partition early warning into the three-dimensional visual model;
and determining a pollutant range according to the partition early warning of the current timestamp, and acquiring the pollutant arrival time of the non-early-warning area based on the pollutant range, the pollutant peak concentration and the change characteristic of the distance from the peak concentration to the pollution source, thereby providing a basis for pollution emergency measures.
The third aspect of the present invention also provides a computer readable storage medium, where the computer readable storage medium includes a method program for monitoring and early warning pollution of a drinking water source after a natural disaster, and when the method program is executed by a processor, the method for monitoring and early warning pollution of a drinking water source after a natural disaster is implemented.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. The method for monitoring and early warning pollution of the drinking water source after natural disasters is characterized by comprising the following steps of:
obtaining the geographic position and the type of a target drinking water source place, extracting surrounding pollution characteristics according to the geographic position and the type of the source place, and determining pollution factors and potential pollution factors according to the pollution characteristics;
determining pollution monitoring indexes based on the pollution factors and the potential pollution factors, determining weather monitoring indexes according to the historical natural disaster conditions of the area where the target drinking water source is located, arranging sensors within a preset range of the target drinking water source according to the pollution monitoring indexes and the weather monitoring indexes, and monitoring the occurrence of natural disasters according to weather monitoring data;
when the meteorological monitoring index exceeds a preset threshold range, natural disaster early warning is generated, pollution monitoring data of the target drinking water source area are obtained through the pollution monitoring index, a pollution prediction model is built based on deep learning, and pollution prediction information of the target drinking water source area is obtained;
performing pollution early warning on the target drinking water source area according to the pollution prediction information, and visually displaying the pollution early warning information and the pollution prediction information;
The pollution prediction model is constructed based on deep learning, and pollution prediction information of a target drinking water source area is obtained, specifically:
acquiring pollution monitoring data of a target drinking water source, respectively extracting time characteristics and space characteristics of the pollution monitoring data, and generating a space-time characteristic sequence of the pollution monitoring data;
constructing a pollution prediction model based on an RBF neural network, acquiring training data through historical sudden pollution monitoring data, and training the pollution prediction model by utilizing the training data;
inputting the space-time characteristic sequence of the pollution monitoring data and the pollutant concentration data into a trained pollution prediction model, and acquiring pollution prediction information according to an output layer of the pollution prediction model;
extracting time features and space features of pollution monitoring data respectively to generate a space-time feature sequence of the pollution monitoring data, wherein the space-time feature sequence specifically comprises the following steps:
acquiring pollution monitoring data of a target drinking water source after natural disaster early warning, acquiring index standard data corresponding to normal monitoring according to pollution monitoring indexes, and determining interpretation data of all monitoring indexes according to the index standard data;
performing data matching on the obtained interpretation data of each monitoring index and meteorological data to generate a monitoring data time sequence corresponding to each sensor, inputting the monitoring data time sequence into a time convolution neural network, and obtaining concentration change trend characteristics of pollutants according to the trained time convolution neural network;
Representing the topological structure covered by the sensor connection of the target drinking water source area in a graph form, learning the graph representation of the topological structure through a graph attention network, and guiding the concentration change trend characteristics of each sensor node into the graph attention network;
and acquiring the attention weight of the adjacent sensor nodes to the target node through an attention mechanism, distributing the attention weight to each adjacent sensor node, generating an aggregate representation of the features by utilizing neighbor aggregation of the graph attention network, and generating a pollution monitoring data space-time feature sequence.
2. The method for monitoring and early warning pollution of a drinking water source after natural disasters according to claim 1, wherein peripheral pollution characteristics are extracted according to the geographic position and the type of the water source, and pollution factors and potential pollution factors are determined according to the pollution characteristics, specifically:
acquiring GIS geographic data within a preset range of a target drinking water source place by a GIS means, acquiring the topographic features of the water source place according to the GIS geographic data, identifying the type of the water source place, and setting a label of the target drinking water source place;
acquiring a pollution source in a preset range of a target drinking water source, acquiring a risk pollution source according to the position of the pollution source and the topographic features of the water source, and extracting the pollution source features of the risk pollution source according to pollutants related to the risk pollution source;
Acquiring historical occurrence data of sudden water pollution by using a big data method, carrying out statistical analysis on the historical occurrence data of sudden water pollution by using the pollution source characteristics, acquiring the sudden times corresponding to the pollution source characteristics, screening the pollution sources, and independently marking the sudden water pollution caused by natural disasters;
summarizing the screened pollution source characteristics to obtain pollution characteristics of the periphery of the water source, determining pollution factors according to the pollution characteristics, wherein the pollution factors carry the position characteristics of pollution, determining potential pollution factors according to the pollution source characteristics corresponding to the burst water pollution marked independently, and setting double labels for repeated pollution factors.
3. The method for monitoring and early warning pollution of a drinking water source after natural disasters according to claim 1, wherein sensors are arranged within a preset range of a target drinking water source according to the pollution monitoring index and the weather monitoring index, and the occurrence of the natural disasters is monitored by weather monitoring data, specifically comprising the following steps:
obtaining pollution factors and potential pollution factors of a target drinking water source area, setting pollutant monitoring indexes according to the pollution factors and the potential pollution factors, and determining meteorological monitoring indexes according to historical natural disaster conditions of the area of the target drinking water source area;
Determining corresponding sensor types through the pollutant monitoring index and the meteorological monitoring index, determining initial layout ranges of sensors of each type according to pollution factors and pollution position characteristics of potential pollution factors, and determining the number of the sensors according to the historical burst times of pollution sources in the initial layout ranges;
determining the comprehensive coverage rate of the sensors as an adaptability function according to the maximum coverage distance of the various sensors and the position of a pollution source to be monitored, and introducing adaptive variation and dynamic weight which change along with the iteration number to improve a particle swarm algorithm;
generating optimal layout positions of local sensors and optimal layout positions and layout quantity of global sensors in each initial layout range and a preset range of a target drinking water source area through an improved particle swarm algorithm;
and monitoring weather through sensors distributed in a preset range of a target drinking water source area to obtain weather monitoring data, generating natural disaster early warning when the weather monitoring data is larger than a preset threshold value, and waking up related sensors corresponding to potential pollution factors.
4. The method for monitoring and early warning pollution of a drinking water source after natural disasters according to claim 1, wherein the pollution early warning of a target drinking water source is performed according to the pollution prediction information, and the pollution early warning information and the pollution prediction information are visually displayed, specifically:
Obtaining pollution prediction information of a target drinking water source area, setting a pollution threshold according to the pollution time of the target drinking water source area, and obtaining pollution peak concentrations of different time stamps and distances from the peak concentrations to pollution sources according to the pollution prediction information;
dividing the preset range of the target drinking water source area into a plurality of subareas according to GIS geographic data and sensor layout points, and acquiring the pollution peak concentration in the subareas according to the current time stamp;
judging whether the pollution peak value in the subarea is larger than a pollution threshold value corresponding to the current time stamp, if so, acquiring pollution concentration deviation, and acquiring a corresponding early warning grade according to the pollution concentration deviation to be matched with the subarea;
obtaining partition early warning within a preset range of a target drinking water source area, obtaining a three-dimensional visual model of the target drinking water source area according to the GIS geographic data, and guiding the partition early warning into the three-dimensional visual model;
and determining a pollutant range according to the partition early warning of the current timestamp, and acquiring the pollutant arrival time of the non-early-warning area based on the pollutant range, the pollutant peak concentration and the change characteristic of the distance from the peak concentration to the pollution source, thereby providing a basis for pollution emergency measures.
5. The utility model provides a drinking water source area pollution monitoring early warning system after natural disasters which characterized in that, this system includes: the device comprises a storage and a processor, wherein the storage comprises a pollution monitoring and early warning method program of a drinking water source area after natural disasters, and the pollution monitoring and early warning method program of the drinking water source area after natural disasters is implemented when executed by the processor as follows:
obtaining the geographic position and the type of a target drinking water source place, extracting surrounding pollution characteristics according to the geographic position and the type of the source place, and determining pollution factors and potential pollution factors according to the pollution characteristics;
determining pollution monitoring indexes based on the pollution factors and the potential pollution factors, determining weather monitoring indexes according to the historical natural disaster conditions of the area where the target drinking water source is located, arranging sensors within a preset range of the target drinking water source according to the pollution monitoring indexes and the weather monitoring indexes, and monitoring the occurrence of natural disasters according to weather monitoring data;
when the meteorological monitoring index exceeds a preset threshold range, natural disaster early warning is generated, pollution monitoring data of the target drinking water source area are obtained through the pollution monitoring index, a pollution prediction model is built based on deep learning, and pollution prediction information of the target drinking water source area is obtained;
Performing pollution early warning on the target drinking water source area according to the pollution prediction information, and visually displaying the pollution early warning information and the pollution prediction information;
the pollution prediction model is constructed based on deep learning, and pollution prediction information of a target drinking water source area is obtained, specifically:
acquiring pollution monitoring data of a target drinking water source, respectively extracting time characteristics and space characteristics of the pollution monitoring data, and generating a space-time characteristic sequence of the pollution monitoring data;
constructing a pollution prediction model based on an RBF neural network, acquiring training data through historical sudden pollution monitoring data, and training the pollution prediction model by utilizing the training data;
inputting the space-time characteristic sequence of the pollution monitoring data and the pollutant concentration data into a trained pollution prediction model, and acquiring pollution prediction information according to an output layer of the pollution prediction model;
extracting time features and space features of pollution monitoring data respectively to generate a space-time feature sequence of the pollution monitoring data, wherein the space-time feature sequence specifically comprises the following steps:
acquiring pollution monitoring data of a target drinking water source after natural disaster early warning, acquiring index standard data corresponding to normal monitoring according to pollution monitoring indexes, and determining interpretation data of all monitoring indexes according to the index standard data;
Performing data matching on the obtained interpretation data of each monitoring index and meteorological data to generate a monitoring data time sequence corresponding to each sensor, inputting the monitoring data time sequence into a time convolution neural network, and obtaining concentration change trend characteristics of pollutants according to the trained time convolution neural network;
representing the topological structure covered by the sensor connection of the target drinking water source area in a graph form, learning the graph representation of the topological structure through a graph attention network, and guiding the concentration change trend characteristics of each sensor node into the graph attention network;
and acquiring the attention weight of the adjacent sensor nodes to the target node through an attention mechanism, distributing the attention weight to each adjacent sensor node, generating an aggregate representation of the features by utilizing neighbor aggregation of the graph attention network, and generating a pollution monitoring data space-time feature sequence.
6. The system for monitoring and early warning pollution of a drinking water source after natural disasters according to claim 5, wherein the pollution early warning of the target drinking water source is performed according to the pollution prediction information, and the pollution early warning information and the pollution prediction information are visually displayed, specifically:
Obtaining pollution prediction information of a target drinking water source area, setting a pollution threshold according to the pollution time of the target drinking water source area, and obtaining pollution peak concentrations of different time stamps and distances from the peak concentrations to pollution sources according to the pollution prediction information;
dividing the preset range of the target drinking water source area into a plurality of subareas according to GIS geographic data and sensor layout points, and acquiring the pollution peak concentration in the subareas according to the current time stamp;
judging whether the pollution peak value in the subarea is larger than a pollution threshold value corresponding to the current time stamp, if so, acquiring pollution concentration deviation, and acquiring a corresponding early warning grade according to the pollution concentration deviation to be matched with the subarea;
obtaining partition early warning within a preset range of a target drinking water source area, obtaining a three-dimensional visual model of the target drinking water source area according to the GIS geographic data, and guiding the partition early warning into the three-dimensional visual model;
and determining a pollutant range according to the partition early warning of the current timestamp, and acquiring the pollutant arrival time of the non-early-warning area based on the pollutant range, the pollutant peak concentration and the change characteristic of the distance from the peak concentration to the pollution source, thereby providing a basis for pollution emergency measures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310378865.0A CN116109462B (en) | 2023-04-11 | 2023-04-11 | Pollution monitoring and early warning method and system for drinking water source area after natural disaster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310378865.0A CN116109462B (en) | 2023-04-11 | 2023-04-11 | Pollution monitoring and early warning method and system for drinking water source area after natural disaster |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116109462A CN116109462A (en) | 2023-05-12 |
| CN116109462B true CN116109462B (en) | 2023-07-07 |
Family
ID=86258261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310378865.0A Active CN116109462B (en) | 2023-04-11 | 2023-04-11 | Pollution monitoring and early warning method and system for drinking water source area after natural disaster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116109462B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116403092B (en) * | 2023-06-02 | 2023-08-18 | 北京建工环境修复股份有限公司 | Underground water NAPL pollution degree judging method and system based on image learning |
| CN116385689B (en) * | 2023-06-02 | 2023-08-04 | 北京建工环境修复股份有限公司 | Visual information management method, system and medium for site pollution data |
| CN116609500B (en) * | 2023-06-02 | 2023-12-22 | 无锡点创科技有限公司 | Water quality data monitoring method based on Internet of things |
| CN116384754B (en) * | 2023-06-02 | 2023-08-04 | 北京建工环境修复股份有限公司 | Deep learning-based environmental pollution risk assessment method in chemical industry park |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109142233A (en) * | 2018-08-08 | 2019-01-04 | 安徽汇泽通环境技术有限公司 | A kind of mutation early warning of Drinking Water Source Quality and monitoring system and method |
| CN112949167A (en) * | 2021-02-03 | 2021-06-11 | 南京信息工程大学 | Dynamic monitoring and early warning system and method for drinking water source |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7866204B2 (en) * | 2007-01-31 | 2011-01-11 | The United States Of America As Represented By The Administrator Of The United States Environmental Protection Agency | Adaptive real-time contaminant detection and early warning for drinking water distribution systems |
| CN103282769B (en) * | 2010-10-18 | 2015-09-30 | Mikasa商事株式会社 | Water quality monitoring device |
| SE537489C2 (en) * | 2014-02-03 | 2015-05-19 | Method and device for online water quality monitoring | |
| CN112966409A (en) * | 2021-02-03 | 2021-06-15 | 南京信息工程大学 | Water supply pipe network pollutant dynamic monitoring system and monitoring and early warning method thereof |
| CN113156075B (en) * | 2021-03-25 | 2022-04-08 | 北京市环境保护科学研究院 | Drinking water source information management system |
| CN115270632A (en) * | 2022-08-02 | 2022-11-01 | 天津天滨瑞成环境技术工程有限公司 | System and method for predicting water bloom risk of drinking water source |
-
2023
- 2023-04-11 CN CN202310378865.0A patent/CN116109462B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109142233A (en) * | 2018-08-08 | 2019-01-04 | 安徽汇泽通环境技术有限公司 | A kind of mutation early warning of Drinking Water Source Quality and monitoring system and method |
| CN112949167A (en) * | 2021-02-03 | 2021-06-11 | 南京信息工程大学 | Dynamic monitoring and early warning system and method for drinking water source |
Non-Patent Citations (2)
| Title |
|---|
| 中国环境风险预警现状及发展趋势;毕军;曲常胜;黄蕾;;环境监控与预警(01);全文 * |
| 张家港市饮用水源地水质立体化监测系统研究;卫臻;周密;朱元龙;张磊;陈颖俊;;水资源保护(04);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116109462A (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116109462B (en) | Pollution monitoring and early warning method and system for drinking water source area after natural disaster | |
| Huang et al. | Predicting monthly high-resolution PM2. 5 concentrations with random forest model in the North China Plain | |
| Shahabi et al. | Evaluating Boolean, AHP and WLC methods for the selection of waste landfill sites using GIS and satellite images | |
| Myronidis et al. | Landslide susceptibility mapping based on landslide history and analytic hierarchy process (AHP) | |
| Nourqolipour et al. | A GIS-based model to analyze the spatial and temporal development of oil palm land use in Kuala Langat district, Malaysia | |
| CN116385689B (en) | Visual information management method, system and medium for site pollution data | |
| Sun et al. | A review of risk analysis methods for natural disasters | |
| CN113222283A (en) | Mountain torrent forecasting and early warning method and system based on digital twin | |
| Guo et al. | Monitoring and simulation of dynamic spatiotemporal land use/cover changes | |
| Hu | Rainstorm flash flood risk assessment using genetic programming: a case study of risk zoning in Beijing | |
| Liang et al. | Modeling urban growth in the middle basin of the Heihe River, northwest China | |
| Qiu et al. | Disaggregating population data for assessing progress of SDGs: methods and applications | |
| CN114067535B (en) | Geological disaster early warning method and device based on artificial intelligence and storage medium | |
| Moayedi et al. | Spatial assessment of landslide risk using two novel integrations of neuro-fuzzy system and metaheuristic approaches; Ardabil Province, Iran | |
| Lecacheux et al. | Toward the probabilistic forecasting of cyclone-induced marine flooding by overtopping at Reunion Island aided by a time-varying random-forest classification approach | |
| Zhang et al. | Quantitative risk assessment of typhoon storm surge for multi-risk sources | |
| CN112233381B (en) | Debris flow early warning method and system based on mechanism and machine learning coupling | |
| Sun et al. | Urban flooding risk assessment based on FAHP–EWM combination weighting: a case study of Beijing | |
| Cuellar et al. | Assessing the accuracy of sensitivity analysis: an application for a cellular automata model of Bogota’s urban wetland changes | |
| Wang et al. | Evaluating future habitat quality responding to land use change under different city compaction scenarios in Southern China | |
| Zheng et al. | Disaster loss calculation method of urban flood bimodal data fusion based on remote sensing and text | |
| Wang et al. | The architecture and application of an automatic operational model system for basin scale water environment management and design making supporting | |
| Ibrahim et al. | Landslide’s analysis and Hazard mapping based on ANALYTIC HIERARCHY PROCESS (AHP) using GIS, in Lawas, Sabah-Sarawak | |
| CN115035256B (en) | Mine waste reservoir accident potential and risk evolution method and system | |
| CN117151499A (en) | Monitoring and evaluating method and system for homeland space planning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |