CN114565170A - Pollutant tracing method and device, equipment, medium and product - Google Patents

Pollutant tracing method and device, equipment, medium and product Download PDF

Info

Publication number
CN114565170A
CN114565170A CN202210213989.9A CN202210213989A CN114565170A CN 114565170 A CN114565170 A CN 114565170A CN 202210213989 A CN202210213989 A CN 202210213989A CN 114565170 A CN114565170 A CN 114565170A
Authority
CN
China
Prior art keywords
pollutant
tracing
concentration
track
area
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.)
Pending
Application number
CN202210213989.9A
Other languages
Chinese (zh)
Inventor
丁建辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN202210213989.9A priority Critical patent/CN114565170A/en
Publication of CN114565170A publication Critical patent/CN114565170A/en
Pending legal-status Critical Current

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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G01N33/0004—Gaseous mixtures, e.g. polluted air
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • 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
    • 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
    • G06Q30/00—Commerce
    • G06Q30/018—Certifying business or products
    • 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Chemical & Material Sciences (AREA)
  • Development Economics (AREA)
  • Human Resources & Organizations (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Accounting & Taxation (AREA)
  • Combustion & Propulsion (AREA)
  • Educational Administration (AREA)
  • Primary Health Care (AREA)
  • Operations Research (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)

Abstract

The utility model provides a pollutant tracing method and device, equipment, medium and product, which relates to the technical field of artificial intelligence, in particular to the technical field of space-time big data, and the concrete implementation scheme comprises: determining a pollutant concentration distribution characteristic based on M regions, wherein M is an integer greater than 3; determining a first pollutant tracing track aiming at a preset monitoring area in the M areas based on a pollutant concentration gradient rule according to the pollutant concentration distribution characteristics; determining a second pollutant tracing track aiming at the monitoring area by utilizing a pollutant diffusion prediction model according to the pollutant concentration distribution characteristics; and determining a comprehensive tracing track of pollutants associated with the monitoring area according to the tracing track of the first pollutants and the tracing track of the second pollutants.

Description

Pollutant tracing method and device, equipment, medium and product
Technical Field
The utility model relates to an artificial intelligence technical field especially relates to space-time big data technical field, can be applied to scenes such as pollutant traceability.
Background
The tracing of pollutants has important significance for air pollution treatment and air quality improvement. However, in some scenes, the phenomena of high cost consumption, high professional requirements and poor tracing effect exist in the tracing of pollutants.
Disclosure of Invention
The present disclosure provides a method and apparatus, device, medium, and product for tracing a source of a contaminant.
According to an aspect of the present disclosure, there is provided a pollutant tracing method, including: determining a pollutant concentration distribution characteristic based on M regions, wherein M is an integer greater than 3; determining a first pollutant tracing track aiming at a preset monitoring area in the M areas based on a pollutant concentration gradient rule according to the pollutant concentration distribution characteristics; determining a second pollutant tracing track aiming at the monitoring area by utilizing a pollutant diffusion prediction model according to the pollutant concentration distribution characteristics; and determining a comprehensive pollutant tracing track associated with the monitoring area according to the first pollutant tracing track and the second pollutant tracing track.
According to another aspect of the present disclosure, there is provided a pollutant tracing apparatus, including: a first processing module for determining a pollutant concentration distribution characteristic based on M zones, M being an integer greater than 3; the second processing module is used for determining a first pollutant tracing track aiming at a preset monitoring area in the M areas based on a pollutant concentration gradient rule according to the pollutant concentration distribution characteristics; the third processing module is used for determining a second pollutant tracing track aiming at the monitoring area by utilizing a pollutant diffusion prediction model according to the pollutant concentration distribution characteristics; and the fourth processing module is used for determining a comprehensive pollutant tracing track associated with the monitoring area according to the first pollutant tracing track and the second pollutant tracing track.
According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor and a memory communicatively coupled to the at least one processor. Wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of tracing contaminants as described above.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the above-described contaminant traceability method.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of tracing contaminants as described above.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 schematically illustrates a system architecture of a contaminant tracing method and apparatus according to an embodiment of the present disclosure;
FIG. 2 schematically illustrates a flow diagram of a contaminant traceability method according to an embodiment of the present disclosure;
FIG. 3 schematically illustrates a flow diagram of a contaminant traceability method according to another embodiment of the present disclosure;
FIG. 4 schematically illustrates a process for determining a first contaminant traceability trajectory according to an embodiment of the present disclosure;
FIG. 5 schematically illustrates a block diagram of a contaminant tracing apparatus according to an embodiment of the present disclosure;
fig. 6 schematically illustrates a block diagram of an electronic device for performing a contaminant tracing method according to an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
The embodiment of the disclosure provides a pollutant tracing method. The pollutant tracing method comprises the following steps: determining pollutant concentration distribution characteristics based on M areas, wherein M is an integer larger than 3, determining a first pollutant tracing track aiming at a preset monitoring area in the M areas based on a pollutant concentration gradient rule according to the pollutant concentration distribution characteristics, determining a second pollutant tracing track aiming at the monitoring area by using a pollutant diffusion prediction model according to the pollutant concentration distribution characteristics, and determining a comprehensive pollutant tracing track associated with the monitoring area according to the first pollutant tracing track and the second pollutant tracing track.
Fig. 1 schematically illustrates a system architecture of a pollutant tracing method and apparatus according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.
The system architecture 100 according to this embodiment may include a data collection side 101, a network 102, and a server 103. Network 102 is the medium used to provide a communication link between data collection end 101 and server 103. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few. The server 103 may be an independent physical server, may be a server cluster or a distributed system formed by a plurality of physical servers, and may be a cloud server providing basic cloud computing services such as cloud services, cloud computing, network services, and middleware services.
The data acquisition terminal 101 interacts with the server 103 through the network 102 to receive or transmit data and the like. The data collection terminal 101 may be configured to collect characteristic parameters for predicting pollutant concentration, such as pollutant diffusion parameters, pollutant historical concentration parameters, and the like, and the pollutant diffusion parameters may include meteorological parameters, geographic characteristic parameters, pollutant types, and the like.
The server 103 may be a server providing various services, such as a background processing server (for example only) that performs pollutant tracing processing by using the characteristic parameters for predicting pollutant concentration provided by the data collection end 101.
For example, the server 103 determines, according to a characteristic parameter for predicting a pollutant concentration provided by the data acquisition end 101, pollutant concentration distribution characteristics based on M regions, where M is an integer greater than 3, determines, according to the pollutant concentration distribution characteristics, a first pollutant traceability trajectory for a preset monitoring region among the M regions based on a pollutant concentration gradient rule, determines, according to the pollutant concentration distribution characteristics, a second pollutant traceability trajectory for the monitoring region by using a pollutant diffusion prediction model, and determines, according to the first pollutant traceability trajectory and the second pollutant traceability trajectory, a pollutant comprehensive traceability trajectory associated with the monitoring region.
It should be noted that the method for tracing the source of the pollutant provided by the embodiment of the present disclosure may be executed by the server 103. Accordingly, the pollutant tracing apparatus provided by the embodiment of the present disclosure may be disposed in the server 103. The method for tracing the source of the pollutant provided by the embodiment of the present disclosure may also be performed by a server or a server cluster which is different from the server 103 and can communicate with the data collection terminal 101 and/or the server 103. Accordingly, the pollutant tracing apparatus provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the server 103 and capable of communicating with the data collection terminal 101 and/or the server 103.
It should be understood that the number of data collection terminals, networks, and servers in fig. 1 is merely illustrative. There may be any number of data collection terminals, networks, and servers, as desired for implementation.
The embodiment of the present disclosure provides a method for tracing a pollutant, and the method for tracing a pollutant according to an exemplary embodiment of the present disclosure is described below with reference to fig. 2 to 4 in conjunction with the system architecture of fig. 1. The method for tracing the source of the pollutant of the embodiment of the present disclosure can be performed by the server 103 shown in fig. 1, for example.
Fig. 2 schematically illustrates a flow chart of a contaminant tracing method according to an embodiment of the present disclosure.
As shown in fig. 2, the method 200 for tracing the source of the pollutant according to the embodiment of the present disclosure may include, for example, operations S210 to S240.
In operation S210, a contaminant concentration distribution characteristic based on M regions, M being an integer greater than 3, is determined.
In operation S220, a first pollutant tracing track for a preset monitoring area of the M areas is determined based on a pollutant concentration gradient rule according to the pollutant concentration distribution characteristics.
In operation S230, a second pollutant tracing track for the monitored area is determined according to the pollutant concentration distribution characteristics by using a pollutant diffusion prediction model.
In operation S240, a comprehensive tracing track of pollutants associated with the monitoring area is determined according to the first tracing track of pollutants and the second tracing track of pollutants.
An exemplary flow of each operation of the pollutant tracing method of the present embodiment is illustrated below.
Exemplarily, gridding a physical space to be subjected to pollutant tracing to obtain M regions, where M is an integer greater than 3. The determination is based on the pollutant concentration profile characteristics of the M zones, e.g., determining a predicted concentration of pollutant associated with each of the M zones, the predicted concentration of pollutant associated with each zone constituting the pollutant concentration profile characteristic.
According to the pollutant concentration distribution characteristics, a first pollutant tracing track aiming at a preset monitoring area in the M areas is determined based on a pollutant concentration gradient rule. For example, a first pollutant traceability trajectory associated with the monitored area is determined based on a pollutant concentration increment rule according to the pollutant predicted concentration associated with each area, taking the pollutant predicted concentration associated with the monitored area as a starting concentration.
And determining a second pollutant tracing track aiming at the monitoring area by utilizing a pollutant diffusion prediction model according to the pollutant concentration distribution characteristics. Illustratively, the predicted concentration of the pollutant associated with each zone is used as input data for a pollutant diffusion prediction model to obtain a second pollutant tracing track associated with the monitored zone.
The input data to the pollutant dispersion prediction model may include, in addition to the predicted concentration of pollutants associated with each zone, for example, historical pollutant concentration parameters, pollutant dispersion parameters, etc. associated with at least some of the zones, and the pollutant dispersion parameters may include, for example, meteorological parameters, geographic characteristic parameters, time parameters, pollutant type, etc.
The pollutant diffusion prediction model can be obtained based on the following operation training, and input data is constructed according to the data input requirements of the trained diffusion prediction reference model; carrying out pollutant diffusion track prediction based on input data by using a diffusion prediction reference model to obtain a diffusion track prediction result; and training the initial network model by using the input data and the diffusion track prediction result to obtain a pollutant diffusion prediction model. By transferring the pollutant diffusion prediction capability of the diffusion prediction reference model, the training difficulty and the training cost of the pollutant diffusion prediction model are favorably reduced, and the professional requirement height of pollutant tracing is favorably reduced.
The trained diffusion prediction reference model may be, for example, a balloon Trajectory computation model with good backward Trajectory prediction capability, such as a HYSPLIT (Hybrid Single-Particle Langrangian Integrated track model) model. Input data is constructed based on data input requirements of the diffusion prediction reference model, which may include, for example, pollutant concentration data, meteorological data, pollutant type data, geographic feature data, and the like. Meteorological data may include, for example, air temperature, air pressure, humidity, precipitation, wind speed, and the like. The geographic characteristic data may include, for example, latitude and longitude, altitude, terrain type, and the like.
And predicting the pollutant diffusion track by using a diffusion prediction reference model based on input data to obtain a diffusion track prediction result. Illustratively, backward trajectory prediction of the large air mass movement is carried out on the basis of input data by using a HYSPLIT model, and a diffusion trajectory prediction result is obtained. And inputting the constructed input data serving as feature data into the initial network model, and taking the diffusion track prediction result as a fitting target for training the initial network model. And iteratively training the initial network model based on a preset loss function threshold value to obtain a pollutant diffusion prediction model for predicting the tracing track of the second pollutant.
And determining a comprehensive tracing track of pollutants associated with the monitoring area according to the tracing track of the first pollutants and the tracing track of the second pollutants. Exemplarily, according to the weight coefficients respectively associated with the first pollutant tracing track and the second pollutant tracing track, vector superposition operation based on the first pollutant tracing track and the second pollutant tracing track is performed to obtain a pollutant comprehensive tracing track.
By adopting a multi-dimensional data fusion mode, the comprehensive tracing track of the pollutants associated with the monitoring area is determined, so that the tracing precision of the pollutants is improved, and the tracing effect of the pollutants is improved.
By the embodiment of the disclosure, pollutant concentration distribution characteristics based on M areas are determined, wherein M is an integer greater than 3; determining a first pollutant tracing track aiming at a preset monitoring area in the M areas based on a pollutant concentration gradient rule according to the pollutant concentration distribution characteristics; determining a second pollutant tracing track aiming at the monitoring area by utilizing a pollutant diffusion prediction model according to the pollutant concentration distribution characteristics; and determining a comprehensive tracing track of pollutants associated with the monitoring area according to the tracing track of the first pollutants and the tracing track of the second pollutants.
The pollutant concentration distribution characteristics based on the M areas are determined, the dependence degree of a pollutant tracing source on pollutant concentration data acquisition can be effectively reduced, the pollutant tracing cost is reduced, and the pollutant tracing efficiency is improved. Based on the pollutant concentration gradient rule, a first pollutant tracing track for the monitoring area is determined, the pollutant tracing mode is simple, and the tracing efficiency is high. And determining a second pollutant tracing track aiming at the monitored area by using a pollutant diffusion prediction model, and determining a comprehensive pollutant tracing track associated with the monitored area according to the first pollutant tracing track and the second pollutant tracing track, so that the pollutant tracing precision is improved, the pollutant tracing effect is improved, and data support with higher reference value is provided for atmospheric pollution control and air quality improvement.
Fig. 3 schematically illustrates a flow chart of a contaminant tracing method according to another embodiment of the present disclosure.
As shown in fig. 3, the method 300 for tracing the source of the pollutant according to the embodiment of the present disclosure may include, for example, operations S310 to S330, operation S230, and operation S240.
In operation S310, a predicted concentration of a contaminant associated with each of the M zones is determined, the predicted concentration of the contaminant associated with each zone constituting a contaminant concentration profile.
In operation S320, N tracing areas associated with a preset monitoring area of the M areas are determined according to the pollutant concentration distribution characteristics, where N is an integer greater than 2 and less than M-1.
In operation S330, a first pollutant tracing track for the monitoring area is determined according to the N tracing track areas.
In operation S230, a second pollutant tracing track for the monitored area is determined according to the pollutant concentration distribution characteristics by using a pollutant diffusion prediction model.
In operation S240, a comprehensive tracing track of the pollutants associated with the monitoring area is determined according to the tracing track of the first pollutants and the tracing track of the second pollutants.
An exemplary flow of each operation of the pollutant tracing method of the present embodiment is illustrated below.
Illustratively, the following operations are repeatedly performed until a predicted concentration of the contaminant associated with each of the M zones is obtained, the predicted concentration of the contaminant associated with each zone constituting a contaminant concentration profile: for any target zone of the M zones, a predicted concentration of a contaminant associated with the target zone is determined using a contaminant concentration prediction model for the target zone based on a contaminant diffusion effect parameter associated with the target zone, a contaminant diffusion effect parameter associated with a zone adjacent to the target zone, and a contaminant concentration parameter associated with the target zone based on at least one historical time period. The adjacent area and the target area meet the preset distance threshold condition.
A predicted concentration of the contaminant associated with each of the M zones is determined using a contaminant concentration prediction model. The method can effectively reduce the acquisition cost of the pollutant concentration data and reduce the acquisition difficulty of the pollutant concentration data. The dependence degree of a pollutant tracing source on pollutant concentration data acquisition can be effectively reduced, the pollutant tracing cost consumption is reduced, the pollutant tracing hardware facility requirement is reduced, and the method can be well applied to long-distance and cross-regional pollutant tracing scenes.
The pollutant spread parameters may include, for example, meteorological parameters, geographic characteristic parameters, pollutant types, time parameters, and the like. The meteorological parameters may include, for example, a prospect meteorological parameter and an earth meteorological parameter. The sounding meteorological parameters may be, for example, meteorological parameters ranging from ground to about 40 kilometers in height, and may include, for example, air temperature, air pressure, humidity, wind direction, and wind speed in the atmospheric boundary layer and free atmosphere. The surface weather parameters may include, for example, weather parameters provided by a weather data network or local weather monitoring station.
The pollutant concentration prediction model for the target area can be, for example, a deep space-time neural network model, which can include, for example, a temporal information inference module, a spatial information aggregation module, and a multidimensional information fusion module.
The time information reasoning module can model the historical pollutant concentration information based on the time dimension by using a sequence model to obtain the pollutant predicted concentration for the current time period. Sequence models may include, for example, LSTM (Long short-Term Memory) and GRU (Gated current Unit).
The spatial information aggregation module may associate the pollutant diffusion effect parameters of the target region and the neighboring region with a local convolution feature of a CNN (Convolutional Neural network), so as to obtain a pollutant predicted concentration for the current time period.
Illustratively, assume that the contaminant concentration parameter associated with the target region based on at least one historical time period comprises { res _ t1，res_t2，...，res_tn}，res_tnRepresenting the historical concentration of the contaminant associated with the target area on the past nth day. And modeling the historical pollutant concentration information based on the time dimension by using a sequence model to obtain the pollutant predicted concentration for the current time period. For example, the predicted concentration of the contaminant res _ t ═ LSTM ({ res _ t) for the current day is obtained1，res_t2，...，res_tn})。
Assuming that the neighbor1, neighbor2, etc., and neighbor m are m neighboring regions associated with the target region, the contaminant diffusion effect parameter, goal _ fea, associated with the target region, and the contaminant diffusion effect parameters, neighbor1_ fea, neighbor2_ fea, etc., associated with the m neighboring regions are used as input data of the convolutional neural network, so as to obtain the predicted contaminant concentration res _ s ═ CNN (good _ fea, neighbor1_ fea, neighbor2_ fea, etc., for the current day).
The multidimensional information fusion module is used for fusing res _ t and res _ s to obtain a pollutant predicted concentration res _ final ═ a × res _ t + (1-a) × res _ s associated with the target region, and the value range of a is [0, 1 ].
Illustratively, when performing pollutant concentration prediction for a target area, besides using pollutant diffusion effect parameters associated with the target area, pollutant diffusion effect parameters associated with a neighboring area of the target area, and pollutant concentration parameters associated with the target area based on at least one historical time period as input data of a pollutant concentration prediction model, pollutant concentration parameters associated with the neighboring area based on at least one historical time period may be used as input data of the pollutant concentration prediction model. The adjacent area and the target area meet the preset distance threshold condition.
The pollutant concentration prediction model for the target area is obtained by training according to training sample data associated with the target area. In the case that training sample data associated with the target area does not meet the preset data volume requirement, a pre-training model associated with the target area may be determined. And predicting the pollutant concentration based on the training sample data by using a pre-training model to obtain the pollutant prediction reference concentration associated with the target area. And adjusting model parameters of the pre-training model according to the pollutant prediction reference concentration and the pollutant concentration label associated with the target area to obtain an adjusted pre-training model which is used as a pollutant concentration prediction model for the target area.
And adjusting the model parameters of the pre-training model to obtain a pollutant concentration prediction model for the target area. The method is favorable for realizing the pollutant concentration prediction model training of a target area with too few air quality monitoring points and deficient diffusion effect data. Through sharing the pollutant concentration prediction knowledge of the pre-training model, the method is favorable for reducing the difficulty in acquiring pollutant concentration data, reducing the requirement on hardware facilities for acquiring the pollutant concentration data, and is favorable for realizing efficient and low-cost pollutant tracing.
The pre-training model is obtained by training based on sample data which meets a preset similarity threshold condition with training sample data and meets the requirement of the data volume, and the pre-training model can be a pollutant concentration prediction model for a reference area with rich sample data volume. The sample data associated with the reference region meets the requirement of a preset data volume, and the similarity of the sample data and the training sample data is higher than a preset threshold value. The similarity with the training sample data can be determined by parameters such as the distance between the reference region and the target region, the similarity of meteorological conditions, and the similarity of geographic features.
And determining N tracing track areas associated with a preset monitoring area in the M areas according to the pollutant concentration distribution characteristics, wherein N is an integer which is more than 2 and less than M-1. The pollutant prediction concentration of each tracing track area in the N tracing track areas is larger than that of the monitoring area, and the pollutant prediction concentrations of the N tracing track areas are sequentially increased. And determining a first pollutant tracing track based on a pollutant prediction concentration increasing rule, wherein the pollutant tracing mode is simple and the tracing efficiency is high.
When determining the N tracing areas associated with the monitored area, a first candidate area with the largest predicted concentration of pollutants satisfying a preset distance threshold condition with respect to the monitored area may be determined. And in the case that the predicted pollutant concentration of the first candidate area is greater than that of the monitoring area, taking the first candidate area as a 1 st tracing area associated with the monitoring area. And determining a second candidate region with the largest pollutant prediction concentration meeting a distance threshold condition with the (N-1) th tracing track region, wherein N is 2. And in the case that the predicted concentration of the pollutant of the second candidate area is greater than the predicted concentration of the pollutant of the (n-1) th tracing area, taking the second candidate area as the nth tracing area associated with the monitoring area.
Illustratively, the area with the largest predicted concentration of the pollutants and the distance from the monitoring area to the monitoring area is smaller than a preset threshold value and is taken as a first candidate area. And in the case that the predicted pollutant concentration of the first candidate area is greater than that of the monitoring area, taking the first candidate area as a tracing track area associated with the monitoring area.
And taking the latest tracing track area as an initial area, and taking an area with the largest pollutant prediction concentration and the distance between the latest tracing track area and the initial area smaller than a preset threshold value as a second candidate area. And in the case that the predicted concentration of the pollutant in the second candidate area is greater than the predicted concentration of the pollutant in the initial area, taking the second candidate area as a next tracing area associated with the monitoring area.
N may be a predetermined definite value or an unknown value that varies depending on the actual situation. Illustratively, the predicted concentration of the pollutant in the nth tracing area may be greater than a preset threshold, and in the case that the predicted concentration of the pollutant is greater than the preset threshold, the nth tracing area may be used as the source area of the pollutant. In addition, the nth tracing area may also be an area whose distance from the known pollution source area is less than a preset threshold.
And determining a first pollutant tracing track aiming at the monitoring area according to the N tracing track areas. Illustratively, according to the central point of each tracing track area in the N tracing track areas, performing line connection and smoothing on the N central points to obtain a first pollutant tracing track.
And determining a second pollutant tracing track aiming at the monitoring area by utilizing a pollutant diffusion prediction model according to the pollutant concentration distribution characteristics. And taking the predicted pollutant concentration associated with each area as at least part of input data of a pollutant diffusion prediction model to obtain a second pollutant tracing track aiming at the monitored area. And determining a comprehensive tracing track of pollutants associated with the monitoring area according to the tracing track of the first pollutants and the tracing track of the second pollutants.
Through confirming with the pollutant concentration distribution characteristic of M regions, on the basis of pollutant concentration distribution characteristic, confirm the comprehensive trace of tracing to the source of the pollutant that is correlated with the monitoring area, be favorable to reducing the degree of dependence of pollutant tracing to professional hardware equipment, can effectively reduce the cost consumption that the pollutant traced to the source, effectively reduce the professional requirement height that the pollutant traced to the source. And the pollutant source tracing is carried out based on the pollutant concentration gradient rule and the pollutant diffusion prediction model, so that the pollutant source tracing efficiency is improved, and the pollutant source tracing precision is improved.
Fig. 4 is a schematic diagram illustrating a process of determining a first pollutant tracing track according to an embodiment of the disclosure.
As shown in fig. 4, in the process of determining the first pollutant tracing track associated with the monitoring region 4A, a region set (as shown in fig. 4A, the region set includes 2 × 2 regions within the bold line frame) with the largest pollutant predicted concentration mean value satisfying the preset distance threshold condition with respect to the monitoring region 4A is determined. And taking the area 4b with the maximum predicted pollutant concentration in the area set as a first candidate area, and taking the first candidate area 4b as a source tracing area associated with the monitoring area 4a under the condition that the predicted pollutant concentration of the first candidate area 4b is greater than that of the monitoring area 4 a.
And determining a region set with the maximum average value of the predicted concentration of the pollutants meeting the preset distance threshold condition with the tracing track region 4B (as shown in fig. 4B, the region set comprises 2 x 2 regions in a bold line frame). And taking the area 4c with the maximum pollutant predicted concentration in the area set as a second candidate area, and taking the second candidate area 4c as the tracing track area associated with the monitoring area 4a under the condition that the pollutant predicted concentration of the second candidate area 4c is greater than that of the tracing track area 4 b.
The foregoing operations are repeatedly performed until N tracing areas associated with the monitoring area 4a are obtained: and determining a region set with the largest pollutant prediction concentration mean value meeting the preset distance threshold condition with the initial region by taking the latest tracing track region as the initial region. And taking the area with the maximum predicted pollutant concentration in the area set as a second candidate area, and taking the second candidate area as a tracing area associated with the monitoring area 4a under the condition that the predicted pollutant concentration of the second candidate area is greater than that of the starting area.
According to the N tracing track areas associated with the monitoring area 4a, the central points of the N tracing track areas are connected and smoothed to obtain a first pollutant tracing track. And determining a first pollutant tracing track based on a pollutant prediction concentration increasing rule, wherein the pollutant tracing mode is simple and the tracing efficiency is high.
Fig. 5 schematically illustrates a block diagram of a contaminant tracing apparatus according to an embodiment of the present disclosure.
As shown in fig. 5, the pollutant tracing apparatus 500 of the embodiment of the present disclosure includes, for example, a first processing module 510, a second processing module 520, a third processing module 530 and a fourth processing module 540.
A first processing module 510 for determining a pollutant concentration profile based on M zones, M being an integer greater than 3; the second processing module 520 is configured to determine, according to the pollutant concentration distribution characteristics, a first pollutant tracing track for a preset monitoring area of the M areas based on a pollutant concentration gradient rule; a third processing module 530, configured to determine, according to the pollutant concentration distribution characteristic, a second pollutant tracing track for the monitored area by using a pollutant diffusion prediction model; and a fourth processing module 540, configured to determine a comprehensive tracing track of pollutants associated with the monitoring area according to the tracing track of the first pollutants and the tracing track of the second pollutants.
By the embodiment of the disclosure, pollutant concentration distribution characteristics based on M areas are determined, wherein M is an integer greater than 3; determining a first pollutant tracing track aiming at a preset monitoring area in the M areas based on a pollutant concentration gradient rule according to the pollutant concentration distribution characteristics; determining a second pollutant tracing track aiming at the monitoring area by utilizing a pollutant diffusion prediction model according to the pollutant concentration distribution characteristics; and determining a comprehensive tracing track of pollutants associated with the monitoring area according to the tracing track of the first pollutants and the tracing track of the second pollutants.
The pollutant concentration distribution characteristics based on the M areas are determined, the dependence degree of a pollutant tracing source on pollutant concentration data acquisition can be effectively reduced, the pollutant tracing cost is reduced, and the pollutant tracing efficiency is improved. Based on the pollutant concentration gradient rule, a first pollutant tracing track for the monitoring area is determined, the pollutant tracing mode is simple, and the tracing efficiency is high. And determining a second pollutant tracing track aiming at the monitored area by using a pollutant diffusion prediction model, and determining a comprehensive pollutant tracing track associated with the monitored area according to the first pollutant tracing track and the second pollutant tracing track, so that the pollutant tracing precision is improved, the pollutant tracing effect is improved, and data support with higher reference value is provided for atmospheric pollution control and air quality improvement.
According to an embodiment of the present disclosure, a first processing module includes: a first processing sub-module for repeatedly performing the following operations until a predicted concentration of contaminants associated with each of the M zones is obtained, the predicted concentration of contaminants associated with each zone constituting a contaminant concentration profile: and aiming at any target area in the M areas, determining the pollutant predicted concentration associated with the target area by using a pollutant concentration prediction model aiming at the target area according to the pollutant diffusion action parameter associated with the target area, the pollutant diffusion action parameter associated with the adjacent area of the target area and the pollutant concentration parameter associated with the target area and based on at least one historical time period, wherein the adjacent area and the target area meet the preset distance threshold condition.
According to the embodiment of the disclosure, the pollutant concentration prediction model for the target area is trained based on the following operations: determining a pre-training model associated with the target area under the condition that training sample data associated with the target area does not meet the requirement of a preset data volume; carrying out pollutant concentration prediction based on training sample data by using a pre-training model to obtain pollutant prediction reference concentration associated with a target area; and adjusting model parameters of the pre-training model according to the pollutant prediction reference concentration and the pollutant concentration label associated with the target area to obtain an adjusted pre-training model which is used as a pollutant concentration prediction model for the target area. The pre-training model is obtained by training based on sample data which meets a preset similarity threshold condition with training sample data and meets the requirement of the data volume.
According to an embodiment of the present disclosure, the second processing module includes: the second processing submodule is used for determining N tracing track areas associated with the monitoring area in the M areas, wherein N is an integer which is larger than 2 and smaller than M-1; and the third processing submodule is used for determining the tracing track of the first pollutant according to the N tracing track areas. The pollutant prediction concentration of each tracing track area in the N tracing track areas is larger than that of the monitoring area, and the pollutant prediction concentrations of the N tracing track areas are sequentially increased.
According to an embodiment of the present disclosure, the second processing submodule includes: the first processing unit is used for determining a first candidate region with the maximum pollutant prediction concentration meeting a preset distance threshold condition with the monitored region; the second processing unit is used for taking the first candidate area as a 1 st tracing area associated with the monitoring area under the condition that the pollutant predicted concentration of the first candidate area is greater than that of the monitoring area; a third processing unit, configured to determine a second candidate region with a largest predicted concentration of pollutants, where the second candidate region meets a distance threshold condition with an (N-1) th tracing track region, where N is 2. And a fourth processing unit, configured to, in a case that the predicted concentration of the pollutant in the second candidate region is greater than the predicted concentration of the pollutant in the (n-1) th tracing area, take the second candidate region as the nth tracing area associated with the monitoring area.
According to the embodiment of the disclosure, the pollutant diffusion prediction model is trained based on the following operations: constructing input data according to the data input requirements of the trained diffusion prediction reference model; carrying out pollutant diffusion track prediction based on input data by using a diffusion prediction reference model to obtain a diffusion track prediction result; and training the initial network model by using the input data and the diffusion track prediction result to obtain a pollutant diffusion prediction model.
According to an embodiment of the present disclosure, the fourth processing module includes: and the fourth processing submodule is used for performing vector superposition operation based on the first pollutant tracing track and the second pollutant tracing track according to the weight coefficients respectively associated with the first pollutant tracing track and the second pollutant tracing track to obtain the comprehensive pollutant tracing track.
It should be noted that in the technical solutions of the present disclosure, the processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the related information are all in accordance with the regulations of the related laws and regulations, and do not violate the customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
Fig. 6 schematically illustrates a block diagram of an electronic device for performing a contaminant tracing method according to an embodiment of the disclosure.
FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. The electronic device 600 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the apparatus 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 601 performs the various methods and processes described above, such as the contaminant tracing method. For example, in some embodiments, the contaminant traceability method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When loaded into RAM 603 and executed by the computing unit 601, a computer program may perform one or more steps of the contamination tracing method described above. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the contaminant provenance method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable contaminant provenance device such that the program codes, when executed by the processor or controller, cause the functions/acts specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with an object, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to an object; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which objects can provide input to the computer. Other kinds of devices may also be used to provide for interaction with an object; for example, feedback provided to the subject can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the object may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., an object computer having a graphical object interface or a web browser through which objects can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims (17)

1. A method of contaminant tracing, comprising:
determining a pollutant concentration distribution characteristic based on M regions, wherein M is an integer greater than 3;
determining a first pollutant tracing track aiming at a preset monitoring area in the M areas based on a pollutant concentration gradient rule according to the pollutant concentration distribution characteristics;
determining a second pollutant tracing track aiming at the monitoring area by utilizing a pollutant diffusion prediction model according to the pollutant concentration distribution characteristics; and
and determining a comprehensive tracing track of pollutants associated with the monitoring area according to the tracing track of the first pollutants and the tracing track of the second pollutants.
2. The method of claim 1, wherein the determining is based on contaminant concentration profile characteristics for the M zones, comprising:
repeatedly performing the following operations until a predicted concentration of contaminants associated with each of the M zones is obtained, the predicted concentration of contaminants associated with each zone constituting the contaminant concentration profile:
for any target zone of the M zones, determining a predicted concentration of a contaminant associated with the target zone using a contaminant concentration prediction model for the target zone as a function of a contaminant diffusion parameter associated with the target zone, a contaminant diffusion parameter associated with a zone adjacent to the target zone, and a contaminant concentration parameter associated with the target zone based on at least one historical time period,
wherein the adjacent area and the target area meet a preset distance threshold condition.
3. The method of claim 2, wherein the prediction model of contaminant concentration for the target region is trained based on:
determining a pre-training model associated with the target area under the condition that training sample data associated with the target area does not meet the requirement of a preset data volume;
carrying out pollutant concentration prediction based on the training sample data by using the pre-training model to obtain pollutant prediction reference concentration associated with the target area;
adjusting model parameters of the pre-training model according to the pollutant prediction reference concentration and the pollutant concentration label associated with the target area to obtain an adjusted pre-training model as a pollutant concentration prediction model for the target area,
the pre-training model is obtained by training based on sample data which meets a preset similarity threshold condition with the training sample data and meets the requirement of the data volume.
4. The method of claim 2, wherein the determining a first pollutant tracing track for a preset monitoring area of the M areas based on a pollutant concentration gradient rule according to the pollutant concentration distribution characteristic comprises:
determining N tracing track areas associated with the monitoring area in the M areas, wherein N is an integer greater than 2 and less than M-1; and
determining the tracing track of the first pollutant according to the N tracing track areas,
and the pollutant prediction concentration of each tracing track area in the N tracing track areas is greater than that of the monitoring area, and the pollutant prediction concentrations of the N tracing track areas are sequentially increased.
5. The method of claim 4, wherein said determining N traceback regions associated with the monitoring region among the M regions comprises:
determining a first candidate region with the maximum pollutant predicted concentration meeting a preset distance threshold condition with the monitoring region;
in the case that the predicted concentration of the pollutant of the first candidate region is greater than the predicted concentration of the pollutant of the monitored region, taking the first candidate region as a 1 st tracing area associated with the monitored region;
determining a second candidate region with the largest pollutant prediction concentration meeting a distance threshold condition with the (N-1) th tracing track region, wherein N is 2, … … N; and
and in the case that the predicted concentration of the pollutant of the second candidate region is greater than the predicted concentration of the pollutant of the (n-1) th tracing area, taking the second candidate region as the nth tracing area associated with the monitoring area.
6. The method of claim 1, wherein the pollutant diffusion prediction model is trained based on:
constructing input data according to the data input requirements of the trained diffusion prediction reference model;
utilizing the diffusion prediction reference model to carry out pollutant diffusion track prediction based on the input data to obtain a diffusion track prediction result; and
and training an initial network model by using the input data and the diffusion track prediction result to obtain the pollutant diffusion prediction model.
7. The method of any one of claims 1 to 6, wherein the determining a composite trace of origin of contaminants associated with the monitored area from the first trace of origin of contaminants and the second trace of origin of contaminants comprises:
and performing vector superposition operation based on the first pollutant tracing track and the second pollutant tracing track according to weight coefficients respectively associated with the first pollutant tracing track and the second pollutant tracing track to obtain the comprehensive pollutant tracing track.
8. A contaminant tracing apparatus comprising:
a first processing module for determining a pollutant concentration distribution characteristic based on M zones, wherein M is an integer greater than 3;
the second processing module is used for determining a first pollutant tracing track aiming at a preset monitoring area in the M areas based on a pollutant concentration gradient rule according to the pollutant concentration distribution characteristics;
the third processing module is used for determining a second pollutant tracing track aiming at the monitoring area by utilizing a pollutant diffusion prediction model according to the pollutant concentration distribution characteristics; and
and the fourth processing module is used for determining a comprehensive tracing track of pollutants associated with the monitoring area according to the tracing track of the first pollutants and the tracing track of the second pollutants.
9. The apparatus of claim 8, wherein the first processing module comprises:
a first processing sub-module for repeatedly performing the following operations until a predicted concentration of contaminants associated with each of the M zones is obtained, the predicted concentration of contaminants associated with each zone constituting the contaminant concentration profile:
for any target zone of the M zones, determining a predicted concentration of a contaminant associated with the target zone using a contaminant concentration prediction model for the target zone as a function of a contaminant diffusion parameter associated with the target zone, a contaminant diffusion parameter associated with a zone adjacent to the target zone, and a contaminant concentration parameter associated with the target zone based on at least one historical time period,
wherein the adjacent area and the target area meet a preset distance threshold condition.
10. The apparatus of claim 9, wherein the prediction model of contaminant concentration for the target region is trained based on:
determining a pre-training model associated with the target area under the condition that training sample data associated with the target area does not meet the requirement of a preset data volume;
carrying out pollutant concentration prediction based on the training sample data by using the pre-training model to obtain pollutant prediction reference concentration associated with the target area;
adjusting model parameters of the pre-training model according to the pollutant prediction reference concentration and the pollutant concentration label associated with the target area to obtain an adjusted pre-training model as a pollutant concentration prediction model for the target area,
the pre-training model is obtained by training based on sample data which meets a preset similarity threshold condition with the training sample data and meets the requirement of the data volume.
11. The apparatus of claim 9, wherein the second processing module comprises:
the second processing submodule is used for determining N tracing track areas associated with the monitoring area in the M areas, wherein N is an integer which is larger than 2 and smaller than M-1; and
a third processing submodule, configured to determine the first pollutant tracing track according to the N tracing track areas,
and the pollutant prediction concentration of each tracing track area in the N tracing track areas is greater than that of the monitoring area, and the pollutant prediction concentrations of the N tracing track areas are sequentially increased.
12. The apparatus of claim 11, wherein the second processing submodule comprises:
the first processing unit is used for determining a first candidate region with the maximum pollutant prediction concentration meeting a preset distance threshold condition with the monitored region;
a second processing unit, configured to, in a case that the predicted concentration of the pollutant of the first candidate region is greater than the predicted concentration of the pollutant of the monitored region, take the first candidate region as a 1 st tracing area associated with the monitored region;
a third processing unit, configured to determine a second candidate region with a largest predicted concentration of pollutants, where the second candidate region meets a distance threshold condition with an (N-1) th tracing track region, where N is 2. And
and the fourth processing unit is used for taking the second candidate area as the nth tracing area associated with the monitoring area under the condition that the pollutant predicted concentration of the second candidate area is greater than that of the (n-1) th tracing area.
13. The apparatus of claim 8, wherein the pollutant dispersion prediction model is trained based on:
constructing input data according to the data input requirements of the trained diffusion prediction reference model;
utilizing the diffusion prediction reference model to carry out pollutant diffusion track prediction based on the input data to obtain a diffusion track prediction result; and
and training an initial network model by using the input data and the diffusion track prediction result to obtain the pollutant diffusion prediction model.
14. The apparatus of any of claims 8 to 13, wherein the fourth processing module comprises:
and the fourth processing submodule is used for performing vector superposition operation based on the first pollutant tracing track and the second pollutant tracing track according to the weight coefficients respectively associated with the first pollutant tracing track and the second pollutant tracing track to obtain the comprehensive pollutant tracing track.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any of claims 1-7.
17. A computer program product comprising a computer program which, when executed by a processor, implements a method according to any one of claims 1 to 7.
CN202210213989.9A 2022-03-04 2022-03-04 Pollutant tracing method and device, equipment, medium and product Pending CN114565170A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210213989.9A CN114565170A (en) 2022-03-04 2022-03-04 Pollutant tracing method and device, equipment, medium and product

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210213989.9A CN114565170A (en) 2022-03-04 2022-03-04 Pollutant tracing method and device, equipment, medium and product

Publications (1)

Publication Number Publication Date
CN114565170A true CN114565170A (en) 2022-05-31

Family

ID=81717683

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210213989.9A Pending CN114565170A (en) 2022-03-04 2022-03-04 Pollutant tracing method and device, equipment, medium and product

Country Status (1)

Country Link
CN (1) CN114565170A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117524354A (en) * 2024-01-05 2024-02-06 北京佳华智联科技有限公司 Air pollution tracing method and device for chemical region

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117524354A (en) * 2024-01-05 2024-02-06 北京佳华智联科技有限公司 Air pollution tracing method and device for chemical region
CN117524354B (en) * 2024-01-05 2024-03-29 北京佳华智联科技有限公司 Air pollution tracing method and device for chemical region

Similar Documents

Publication Publication Date Title
US20220092418A1 (en) Training method for air quality prediction model, prediction method and apparatus, device, program, and medium
CN114596553B (en) Model training method, trajectory prediction method and device and automatic driving vehicle
US20210341646A1 (en) Weather parameter prediction model training method, weather parameter prediction method, electronic device and storage medium
CN113870334B (en) Depth detection method, device, equipment and storage medium
CN113361578A (en) Training method and device of image processing model, electronic equipment and storage medium
CN113895460B (en) Pedestrian trajectory prediction method, device and storage medium
CN114187459A (en) Training method and device of target detection model, electronic equipment and storage medium
CN112884837A (en) Road positioning method, device, equipment and storage medium
CN116545495A (en) Topology prediction model training method and prediction method applied to satellite network
CN114715145B (en) Trajectory prediction method, device and equipment and automatic driving vehicle
CN113739811A (en) Method and device for training key point detection model and generating high-precision map lane line
CN114742280B (en) Road condition prediction method and corresponding model training method, device, equipment and medium
CN113836661B (en) Time prediction method, model training method, related device and electronic equipment
CN115471805A (en) Point cloud processing and deep learning model training method and device and automatic driving vehicle
CN114972877A (en) Image classification model training method and device and electronic equipment
CN114565170A (en) Pollutant tracing method and device, equipment, medium and product
CN116739189A (en) Transmission tracing method and device, storage medium and electronic equipment
CN113688920A (en) Model training and target detection method and device, electronic equipment and road side equipment
CN112862183A (en) Prediction method of charging difficulty, training method of model, training device of model and equipment
CN115456168B (en) Training method of reinforcement learning model, energy consumption determining method and device
CN113850297B (en) Road data monitoring method and device, electronic equipment and storage medium
CN113761086B (en) Automatic guiding transport vehicle track display method and device
CN114925076A (en) Map data updating method and device, electronic equipment and storage medium
CN114140553A (en) Intersection guide line generation method and system based on condition variation self-encoder
CN114218504A (en) Blocked road segment identification method and device, electronic equipment and storage medium

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