CN109657842A - The prediction technique and device of air pollutant concentration, electronic equipment - Google Patents
The prediction technique and device of air pollutant concentration, electronic equipment Download PDFInfo
- Publication number
- CN109657842A CN109657842A CN201811428894.9A CN201811428894A CN109657842A CN 109657842 A CN109657842 A CN 109657842A CN 201811428894 A CN201811428894 A CN 201811428894A CN 109657842 A CN109657842 A CN 109657842A
- Authority
- CN
- China
- Prior art keywords
- pollutant concentration
- air
- air pollutant
- prediction
- website
- 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
Links
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
- 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
Abstract
This application involves the prediction techniques and device of environmental monitoring technology field more particularly to a kind of air pollutant concentration, electronic equipment.The prediction technique of air pollutant concentration, comprising: obtain the first location information of target prediction website and the predicted time section of air pollutant concentration；The second location information of several the air detection websites adjacent with the target prediction website, the acquisition time of history air pollutant concentration and the history air pollutant concentration are obtained according to the first location information；According to the second location information, history air pollutant concentration and acquisition time, the air pollutant concentration to the target prediction website in the predicted time section is predicted.Scheme provided by the present application is related to neural network algorithm and establishes prediction model, and the program is conducive to improve the accuracy of prediction data, reduces the error of prediction.
Description
Technical field
This application involves environmental monitoring technology fields, specifically, this application involves a kind of the pre- of air pollutant concentration
Survey method and device, electronic equipment.
Background technique
With the development of society, factory and motor vehicles continue to increase, many environmental problems generate therewith, and air pollution is asked
Topic is got worse, and people need to predict the accurate air pollutants situation in a certain region, so as to according to air pollutants situation into
The reasonable planning of row.
The prior art carries out air pollutants from the single dimension in time or space generally be directed to single detection website
Prediction, air quality monitoring stations point are influenced the detection of air pollutants by Multiple factors, such as: air pollutant concentration, day
Gas situation etc., therefore for a test point, the air quality situation of near zone is can exist to influence on testing result,
And the air pollutants distribution situation detection information for individually detecting website can not cover the air quality situation of near zone, lead
Cause prediction result there are large errors between actual conditions.
Summary of the invention
This application provides a kind of prediction technique of air pollutant concentration and devices, electronic equipment, to reduce prediction knot
The error of fruit improves the prediction precision of air pollutant concentration.Technical solution is as follows:
The embodiment of the present application provides firstly a kind of prediction technique of air pollutant concentration, comprising:
Obtain the first location information of target prediction website and the predicted time section of air pollutant concentration；
Several the air detection websites adjacent with the target prediction website are obtained according to the first location information
The acquisition time of second location information, history air pollutant concentration and the history air pollutant concentration；
According to the second location information, history air pollutant concentration and acquisition time, to the target prediction website
It is predicted in the air pollutant concentration of the predicted time section.
Preferably, pre- to the target according to the second location information, history air pollutant concentration and acquisition time
The step of air pollutant concentration in the predicted time section of survey station point is predicted include:
The second location information, history air pollutant concentration and acquisition time are integrated into three-dimensional sample data；
Using the sample data of the three-dimensional as training sample, the prediction model of air pollutant concentration is trained；
The predicted time section is inputted the prediction model to predict, obtains the air pollution of the predicted time section
Object concentration.
Preferably, described that the second location information, history air pollutant concentration and acquisition time are integrated into three-dimensional
Sample data the step of, comprising:
Air is carried out to the second location information, history air pollutant concentration and acquisition time of the air detection website
The integration of pollutant concentration information obtains the three-dimensional data of air pollutant concentration.
Preferably, the second location information, history air pollutant concentration and acquisition time are integrated into three-dimensional data
Before, further includes:
The second location information that each air detection website disperses is integrated into two-dimensional grid, the two-dimensional network includes
The relative position information of air detection website；
It is two-dimensional grid addition apart from channel, it is described to store several air detection websites to target apart from channel
Predict the range information of website.
Preferably, the second location information by the dispersion of each air detection website is integrated into the step in two-dimensional grid
Suddenly, comprising:
The relative position information that each air detection website is obtained according to the second location information, the relative position is believed
Breath is stored in two-dimensional grid.
Preferably, air pollutants there are it is a variety of when, using the sample data of the three-dimensional as training sample, train sky
The step of prediction model of gas pollutant concentration, comprising:
The history of every kind of air pollutants is obtained according to the attribute information of the history air pollutants of each air detection website
Air pollutant concentration；
According to the history air pollutant concentration of every kind of air pollutants and corresponding acquisition time and second location information
Establish the prediction model of every kind of air pollutant concentration.
Preferably, when air pollutants are there are when associated association air pollutants, according to every kind of air pollutants
History air pollutant concentration and corresponding acquisition time and second location information establish the pre- of every kind of air pollutant concentration
The step of surveying model, comprising:
Obtain the pollutant concentration of association air pollutants associated with the air pollutants；
In conjunction with the pollutant concentration and corresponding sample data conduct of the air pollutants and its association air pollutants
Training sample obtains the prediction model of this kind of air pollutant concentration.
Preferably, the sample data using the three-dimensional trains the pre- of air pollutant concentration as training sample
The step of surveying model, comprising:
Adjust the characteristic parameter of each dimension in the gain of parameter prediction model establishment process of convolutional neural networks；Its
In, the parameter of convolutional neural networks includes at least one of the size of three dimensional convolution kernel, step-length, the convolution number of plies；
Characteristic parameter is learnt as training sample using the sample data, according to the study of each characteristic parameter
As a result the prediction model of air pollutant concentration is obtained.
Further, present invention also provides a kind of prediction meanss of air pollutant concentration, comprising:
First obtains module, the prediction of first location information and air pollutant concentration for obtaining target prediction website
Period；
Second obtains module, adjacent with the target prediction website several for being obtained according to the first location information
When the acquisition of the second location information of a air detection website, Historical Pollution object concentration and the history air pollutant concentration
Between；
Prediction module is used for according to the second location information, history air pollutant concentration and acquisition time, to described
Target prediction website is predicted in the air pollutant concentration of the predicted time section.
Further, the embodiment of the present application also provides a kind of electronic equipment comprising:
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and quilt
It is configured to be executed by one or more of processors, one or more of application programs are configured to: execute any of the above-described
The step of prediction technique of air pollutant concentration described in item technical solution.
Further, the embodiment of the present application also provides a kind of computer readable storage mediums, described computer-readable
Storage medium when run on a computer, allows computer to execute any of the above-described skill for storing computer instruction
The step of prediction technique of air pollutant concentration described in art scheme.
Compared with prior art, scheme provided by the present application has the advantage that
The prediction technique of air pollutant concentration provided by the embodiments of the present application, by obtaining target prediction website adjacent vacant
Gas detects the data of the history air pollutant concentration of website, and the air for obtaining the target prediction website in predicted time section is dirty
Contaminate the prediction data of object concentration.Compared with carrying out air pollutant concentration prediction based on the historical data of target detection website, this
It is pre- that the Historical Pollution object concentration data that scheme combines the air detection website acquisition adjacent with target prediction website carries out target
The air pollutant concentration of survey station point is predicted, it is contemplated that influence of the adjacent air measuring station point to target detection website is conducive to
The accuracy for improving prediction data, reduces the error of prediction.
The prediction technique of air pollutant concentration provided by the embodiments of the present application, by the way that second location information, history is empty
Gas pollutant concentration and acquisition time are integrated into three-dimensional sample data, are carried out based on the three-dimensional data to air pollutant concentration
Prediction is conducive to improve the accuracy for obtaining prediction data.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The application can be limited.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, institute in being described below to the embodiment of the present application
Attached drawing to be used is needed to be briefly described.
Fig. 1 is the flow diagram of the prediction technique of air pollutant concentration provided by the embodiments of the present application；
Fig. 2 is provided by the embodiments of the present application according to the second location information, history air pollutant concentration and acquisition
Time, the process for the step of air pollutant concentration in the predicted time section of the target prediction website is predicted
Schematic diagram；
Fig. 3 be it is provided by the embodiments of the present application by the second location information, history air pollutant concentration and acquisition when
Between before the step of being integrated into three-dimensional data step flow diagram；
Fig. 4 be it is provided by the embodiments of the present application when air pollutants there are it is a variety of when, with the sample data of three-dimensional work
For training sample, the flow diagram for the step of training the prediction model of air pollutant concentration；
Fig. 5 is the block schematic illustration of the prediction meanss of air pollutant concentration provided by the embodiments of the present application；
Fig. 6 is the structural schematic diagram of a kind of electronic equipment provided by the embodiments of the present application.
Specific embodiment
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the application, and cannot be construed to the limitation to the application.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in the description of the present application
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or wirelessly coupling.It is used herein to arrange
Diction "and/or" includes one or more associated wholes for listing item or any cell and all combinations.
How the technical solution of the application and the technical solution of the application are solved with specifically embodiment below above-mentioned
Technical problem is described in detail.These specific embodiments can be combined with each other below, for the same or similar concept
Or process may repeat no more in certain embodiments.Below in conjunction with attached drawing, embodiments herein is described.
This application provides a kind of prediction technique of air pollutant concentration, flow diagram is as shown in Figure 1, include such as
Lower step:
S110 obtains the first location information of target prediction website and the predicted time section of air pollutant concentration；
S120 obtains several air detection stations adjacent with the target prediction website according to the first location information
The acquisition time of the second location information, history air pollutant concentration and the history air pollutant concentration put；
S130, according to the second location information, history air pollutant concentration and acquisition time, to the target prediction
Website is predicted in the air pollutant concentration of the predicted time section.
Multiple monitoring stations for being used to detect current air mass are distributed in the same area, for ease of description, the application is real
It applies in example, monitoring station to be predicted is known as target prediction website, the geographical location information of the target prediction website is first
Location information, the monitoring station adjacent with the target prediction website are known as air detection website, the air detection website
Geographical location information is second location information.Obtain target prediction website first location information and air detection website second
Location information transfers the air pollutants information of air detection website acquisition and the acquisition time of the air pollutants information, institute
Stating air pollutants information includes air pollutants type and air pollutant concentration.
The prediction scheme of air pollutant concentration provided by the embodiments of the present application, by obtaining target prediction website adjacent vacant
Gas detects the data of the history air pollutant concentration of website, and the air for obtaining the target prediction website in predicted time section is dirty
Contaminate the prediction data of object concentration.In scheme provided in this embodiment, second location information, history based on air detection website are empty
The acquisition time of gas pollutant concentration and Historical Pollution object concentration predicts the air pollutant concentration of predicted time section, obtains
The prediction data obtained is more accurate, reduces the error of prediction.
In a kind of embodiment, the process of the prediction technique of the air pollutant concentration is as follows:
S110 obtains the first location information of target prediction website and the predicted time section of air pollutant concentration.
The type of the air pollutants includes but is not limited to: PM2.5, PM10, O3、NO2、CO、SO2Deng the target is pre-
The air pollutants of survey station point are at least a kind of.
The first location information of target prediction website is obtained, the first location information is preferably the warp of target prediction website
Latitude information, the predicted time section of the air pollutant concentration of the target prediction website, preferably lower a period of time of current time
Between section if current time is 8:00 can obtain the history air pollutant concentration before current time, then the predicted time
Section is preferably the air pollutant concentration of 8:00 to 12:00 or same day 8:00 to next day 8:00.Due to air pollutant concentration
It is influenced by a variety of extraneous factors such as weather, generation changes greatly, and therefore, is obtained instantly according to history air pollutant concentration
The prediction data of the prediction data at moment, acquisition is more accurate compared with other predicted time sections.
S120 obtains several air detection stations adjacent with the target prediction website according to the first location information
The acquisition time of the second location information, history air pollutant concentration and the history air pollutant concentration put.
The air detection website is the adjacent sites of target prediction website, described adjacent including direct neighbor and indirect phase
Neighbour, for the quantity of the air detection website depending on actual conditions, the quantity of adjacent air measuring station point is more, and prediction target is pre-
The basic data of the air pollutant concentration of survey station point is more, help to obtain the prediction of more accurate air pollutant concentration
Value.
Several skies adjacent with the target prediction website are transferred from the storage device for be stored with air pollutant concentration
Gas detects the second location information of website, and the history air pollutant concentration and the history of each air detection website acquisition are empty
The acquisition time of gas pollutant concentration, so that the subsequent relationship based between the three carries out the air pollution of target prediction website
The prediction of object concentration.
S130, according to the second location information, history air pollutant concentration and acquisition time, to the target prediction
Website is predicted in the air pollutant concentration of the predicted time section.
It is dirty to the second location information of the air detection website of acquisition, history air pollutant concentration and the history air
The acquisition time for contaminating object concentration carries out the processing such as self study, carries out the target prediction website in prediction according to self study result
Between section air pollutant concentration prediction.
In a kind of embodiment, according to the second location information, history air pollutant concentration and acquisition time, to described
The step of air pollutant concentration in the predicted time section of target prediction website is predicted includes following sub-step,
Flow diagram is as shown in Figure 2:
The second location information, history air pollutant concentration and acquisition time are integrated into three-dimensional sample by S210
Data.
By the acquisition of the second location information of acquisition, history air pollutant concentration and the history air pollutant concentration
Time, each air detection website respectively detect air quality at multiple time points, obtain the multiple groups different acquisition time
Corresponding air pollutants are called in advance for the data packet of each air detection website storage, which includes that multiple groups are empty
Gas pollutant concentration, the corresponding acquisition time of every group of air pollutant concentration and second location information are transferred according to timestamp,
Obtain three-dimensional samples data.
In a kind of embodiment, the second location information, history air pollutant concentration and acquisition time are integrated into three
The step of sample data of dimension, comprising: to the second location information of the air detection website, history air pollutant concentration and
Acquisition time carries out the integration of air pollutant concentration information, obtains the three-dimensional data of air pollutant concentration.
Air pollutant concentration information is integrated, the corresponding pass of air pollutant concentration over time and space is obtained
System, predicts air pollutant concentration based on the three-dimensional data, help to obtain accurate prediction data.
In a kind of embodiment, the second location information, history air pollutant concentration and acquisition time are integrated into three
Further include following sub-step before the step of dimension data, flow diagram is as shown in Figure 3:
The second location information that each air detection website disperses is integrated into two-dimensional grid, the two-dimensional mesh by S310
Network includes the relative position information of air detection website.
The location information of each air detection website is dispersion on geographical space, for the ease of to multiple second positions
Information carries out operation, and the second location information of dispersion is preferably integrated into two-dimensional grid by the present embodiment, in the two-dimensional grid
Relative position information comprising the air detection website, it is preferable that determine target prediction website in two-dimensional grid first
Position obtains each air detection website in two-dimensional grid according to the relationship between the second location information and first location information
In relative position information.Such as: the quantity of target prediction website and air detection website is total up to 9, can be by target prediction
The relative position information of website and air detection website is stored in nine grids, and target prediction website is at the center of nine grids, and one
The actual geographic of a air detection website is spatially the southeastern direction in target prediction website, and the air detection website is in two dimension
Position in grid is in the lower right position of target prediction website.
S320 is two-dimensional grid addition apart from channel, described to store several air detection websites apart from channel
To the range information of target prediction website.
Due to only saving the relative position information between target prediction website and air detection website in two-dimensional grid, it is
The accurate location of each website is saved in two-dimensional grid, then preferably the distance between two-dimensional grid addition grid channel, away from
From preferably storing range information of the air detection website to target prediction website in channel.
Such as: obtain the longitude and latitude of a certain regional 35 air detection websites, be arranged in the two-dimensional grid of 5*7) in space
Position is abstracted into after two-dimensional grid, and two-dimensional grid only remains each air detection website to the opposite position of target prediction website
It sets, and does not include the range information of each website temporarily.Further, in each feature of original 35 websites as two-dimensional mesh
It formats except each channel, is additionally superimposed one layer of two-dimensional grid apart from channel, is arrived for storing other each air detection websites
The distance feature of target prediction website.By this two-dimensional mesh format processing and add apart from channel, the relative bearing of website
And range information is fully retained, the air pollutant concentration information of original irregular dispersion is fitly arranged in two dimension
In grid, convolution study can be carried out by convolutional neural networks.
The second location information, history air pollutant concentration and acquisition time for obtaining air detection website carry out depth
Practise, extract second location information and history air pollutant concentration acquisition time and history air pollutant concentration acquisition when
Between in rudimentary specific features and high-level abstractions feature, with history air pollutant concentration and corresponding acquisition time, acquisition position
Confidence breath carries out the study and optimization of prediction model, obtains the pre- of the air pollutant concentration constructed by various features and its weight
Survey model.
S220 trains the prediction model of air pollutant concentration using the sample data of the three-dimensional as training sample.
Include in three-dimensional sample data air detection website second location information or second location information with first
The positional relationship of confidence breath, the acquisition time of history air pollutant concentration and history air pollutant concentration are based on the three-dimensional
Sample data establish the relationship between air pollutant concentration, acquisition time, if the acquisition time is following period,
The prediction model of the air pollutant concentration of target prediction website can then be established.The foundation of prediction model includes the following two kinds feelings
Shape: one is the history air pollutant concentration and acquisition time using whole websites, the history number based on air detection website
According to and target prediction website historical data obtain target prediction website the prediction model；Another kind is to utilize air detection
The history air pollutant concentration and acquisition time of website, the historical data based on air detection website obtain target prediction website
Level forecasts model, the level forecasts model is optimized further according to the historical data of target detection website, obtain it is excellent
Prediction model after change.
In a kind of embodiment, using the sample data of the three-dimensional as training sample, established using convolution log on pre-
During surveying model, the feature ginseng of each dimension in the gain of parameter prediction model establishment process of convolutional neural networks is adjusted
Number；Wherein, the parameter of convolutional neural networks includes at least one of size, step-length, the convolution number of plies of three dimensional convolution kernel；It utilizes
The sample data learns characteristic parameter as training sample, obtains air according to the learning outcome of each characteristic parameter
The prediction model of pollutant concentration.The characteristic parameter of each dimension is the characteristic parameter of different levels depth.Adjust convolution
The parameter extraction different depth of neural network and the characteristic parameter of range, and constantly model is instructed with three-dimensional characteristic
Practice and optimizes, the final prediction model for obtaining air pollutant concentration.
The present embodiment establishes prediction model by convolutional neural networks, the mould established by constantly adjusting characteristic parameter optimization
Type is conducive to the precision for improving prediction data.
In a kind of embodiment, when air pollutants there are it is a variety of when, using the sample data of the three-dimensional as training sample,
The step of training the prediction model of air pollutant concentration, including following sub-step, flow diagram are as shown in Figure 4:
S410 obtains every kind of air pollutants according to the attribute information of the history air pollutants of each air detection website
History air pollutant concentration.
All air pollutants in current detection air can be obtained various air pollutants when Detection of Air Quality
Characteristic, and by characteristic storage into database.When carrying out the prediction of air pollutant concentration, need to extract
The characteristic of every kind of air pollutants out, the characteristic based on this kind of air pollutants obtain this kind of air pollutant concentration
Prediction data need before this by the characteristic of this kind of air pollutants from saving there are many air pollutant concentration
Database in extract, the attribute information that the embodiment of the present application preferably passes through air pollutants transfers this kind of air pollutants
Characteristic.
The attribute information of the history air pollutants includes: the title, number, other description informations of air pollutants
Deng when storage obtains the characteristic information of air pollutants, by the title of air pollutants, No. CAS (chemical substance accession number) etc.
Attribute information is stored into database as the identification feature of air pollutants together, therefore, exists in air pollutants and is more than one
It, can be by attribute informations such as the title of air pollutants or characteristics, from the data of storage air pollutant concentration data when kind
The data of this kind of air pollutants are filtered out in library, i.e., the dirt are inquired from database by the title of certain air pollutants
Contaminate the characteristics such as object concentration.
The attribute informations such as the title by air pollutants filter the characteristic of this kind of air pollutants, and process is simple,
Reduce the resource consumption for obtaining this kind of air pollutants characteristic.
S420, according to the history air pollutant concentration of every kind of air pollutants and corresponding acquisition time and the second position
Information establishes the prediction model of every kind of air pollutant concentration.
Every kind of air dirt of air detection website and the acquisition of target detection website is obtained according to the scheme that step S410 is provided
The history air pollutant concentration for contaminating object, being established based on every kind of air pollutant concentration data, acquisition time and location information should
The prediction model of kind air pollutant concentration.
When air pollutants multiplicity, the prediction model of various air pollutant concentrations may be different, establish every kind of air dirt
The prediction model of object concentration is contaminated, so that the air pollutants model established is more accurate and fining, raising are based on the prediction mould
The accuracy for the air pollutant concentration that type obtains.
In a kind of embodiment, when air pollutants are there are when associated association air pollutants, according to every kind of air
It is dense that the history air pollutant concentration of pollutant and corresponding acquisition time and second location information establish every kind of air pollutants
The step of prediction model of degree, comprising:
Obtain the pollutant concentration of association air pollutants associated with the air pollutants；It is dirty in conjunction with the air
The pollutant concentration and corresponding sample data of dye object and its association air pollutants obtain this kind of air dirt as training sample
Contaminate the prediction model of object concentration.
In the prediction model for establishing air pollutant concentration, because certain air pollutant concentrations change related, such as O3With
NO2, establishing O3Prediction model when, by NO2Characteristic information as O3One of training data of prediction model.
The present embodiment combines the data of association air pollutant concentration to establish the prediction model of pollutant concentration, is conducive to mention
The accuracy of high prediction model.
The predicted time section is inputted the prediction model and predicted, obtains the sky of the predicted time section by S230
Gas pollutant concentration.
Preferably a certain future time section, the prediction model are that can be combining target pre- to the predicted time section recently
Survey station point, the historical data of air detection website and corresponding acquisition time, location information obtain, then will be defeated in prediction model
Enter the first location information and predicted time section of target prediction website, air pollution in the prediction model output predicted time section
The predicted value of object concentration.
The prediction scheme of air pollutant concentration provided by the embodiments of the present application, by the way that second location information, history is empty
Gas pollutant concentration and acquisition time are integrated into three-dimensional sample data, and based on the sample data of the three-dimensional, it is pre- to obtain target
Model is surveyed, the air pollutant concentration based on prediction model prediction is more accurate.
Further, the embodiment of the present application also provides a kind of prediction meanss of air pollutant concentration, comprising: first obtains
Modulus block 510, second obtains module 520, prediction module 530, and structural block diagram is as shown in Figure 5.
First obtains module 510, for obtaining the first location information and air pollutant concentration of target prediction website
Predicted time section；
Second obtains module 520, adjacent with the target prediction website for being obtained according to the first location information
The acquisition of the second location information, Historical Pollution object concentration and the history air pollutant concentration of several air detection websites
Time；
Prediction module 530 is used for according to the second location information, history air pollutant concentration and acquisition time, right
The target prediction website is predicted in the air pollutant concentration of the predicted time section.
About the prediction meanss of the air pollutant concentration in above-described embodiment, wherein modules, unit execute operation
Concrete mode be described in detail in the embodiment of the method, no detailed explanation will be given here.
Further, the embodiment of the present application provides a kind of electronic equipment, as shown in fig. 6, electronic equipment shown in fig. 6
600 include: processor 601 and memory 603.Wherein, processor 601 is connected with memory 603, is such as connected by bus 602.
Optionally, electronic equipment 600 can also include transceiver 604.It should be noted that transceiver 604 is not limited in practical application
One, the structure of the electronic equipment 600 does not constitute the restriction to the embodiment of the present application.
Processor 601 can be CPU, general processor, DSP, ASIC, FPGA or other programmable logic device, crystalline substance
Body pipe logical device, hardware component or any combination thereof.It, which may be implemented or executes, combines described by present disclosure
Various illustrative logic blocks, module and circuit.Processor 601 is also possible to realize the combination of computing function, such as wraps
It is combined containing one or more microprocessors, DSP and the combination of microprocessor etc..
Bus 602 may include an access, and information is transmitted between said modules.Bus 602 can be pci bus or EISA
Bus etc..Bus 602 can be divided into address bus, data/address bus, control bus etc..For convenient for indicating, in Fig. 6 only with one slightly
Line indicates, it is not intended that an only bus or a type of bus.
Memory 603 can be ROM or can store the other kinds of static storage device of static information and instruction, RAM
Or the other kinds of dynamic memory of information and instruction can be stored, it is also possible to EEPROM, CD-ROM or other CDs
Storage, optical disc storage (including compression optical disc, laser disc, optical disc, Digital Versatile Disc, Blu-ray Disc etc.), magnetic disk storage medium
Or other magnetic storage apparatus or can be used in carry or store have instruction or data structure form desired program generation
Code and can by any other medium of computer access, but not limited to this.
Optionally, memory 603 be used for store execution application scheme application code, and by processor 601
Control executes.Processor 601 is for executing the application code stored in memory 603, to realize that above-described embodiment provides
Air pollutant concentration prediction technique the step of.
Further, the embodiment of the present application also provides a kind of computer readable storage medium, the computer-readable storages
Computer program is stored on medium, which realizes air pollutant concentration shown in above-described embodiment when being executed by processor
Prediction technique the step of.
It should be understood that although each step in the flow chart of attached drawing is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, can execute in the other order.Moreover, at least one in the flow chart of attached drawing
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, execution sequence, which is also not necessarily, successively to be carried out, but can be with other
At least part of the sub-step or stage of step or other steps executes in turn or alternately.
The above is only some embodiments of the application, it is noted that for the ordinary skill people of the art
For member, under the premise of not departing from the application principle, several improvements and modifications can also be made, these improvements and modifications are also answered
It is considered as the protection scope of the application.
Claims (10)
1. a kind of prediction technique of air pollutant concentration characterized by comprising
Obtain the first location information of target prediction website and the predicted time section of air pollutant concentration；
The second of several the air detection websites adjacent with the target prediction website is obtained according to the first location information
The acquisition time of location information, history air pollutant concentration and the history air pollutant concentration；
According to the second location information, history air pollutant concentration and acquisition time, to the target prediction website in institute
The air pollutant concentration for stating predicted time section is predicted.
2. the prediction technique of air pollutant concentration according to claim 1, which is characterized in that according to the second position
Information, history air pollutant concentration and acquisition time, to the air in the predicted time section of the target prediction website
The step of pollutant concentration is predicted include:
The second location information, history air pollutant concentration and acquisition time are integrated into three-dimensional sample data；
Using the sample data of the three-dimensional as training sample, the prediction model of air pollutant concentration is trained；
The predicted time section is inputted into the prediction model and predicts that the air pollutants for obtaining the predicted time section are dense
Degree.
3. the prediction technique of air pollutant concentration according to claim 2, which is characterized in that described by the second
The step of confidence breath, history air pollutant concentration and acquisition time are integrated into three-dimensional sample data, comprising:
Air pollution is carried out to the second location information, history air pollutant concentration and acquisition time of the air detection website
The integration of object concentration information obtains the three-dimensional data of air pollutant concentration.
4. the prediction technique of air pollutant concentration according to claim 1, which is characterized in that by the second confidence
Breath, history air pollutant concentration and acquisition time are integrated into before three-dimensional data, further includes:
The second location information that each air detection website disperses is integrated into two-dimensional grid, the two-dimensional network includes air
Detect the relative position information of website；
It is two-dimensional grid addition apart from channel, it is described to store several air detection websites to target prediction apart from channel
The range information of website.
5. the prediction technique of air pollutant concentration according to claim 4, which is characterized in that described to examine each air
The second location information of survey station point dispersion is integrated into the step in two-dimensional grid, comprising:
The relative position information that each air detection website is obtained according to the second location information, the relative position information is deposited
It is stored in two-dimensional grid.
6. the prediction technique of air pollutant concentration according to claim 2, which is characterized in that air pollutants exist more
Kind when, using the sample data of three-dimensional as training sample, the step of training the prediction model of air pollutant concentration, is wrapped
It includes:
The history air of every kind of air pollutants is obtained according to the attribute information of the history air pollutants of each air detection website
Pollutant concentration；
It is established according to the history air pollutant concentration of every kind of air pollutants and corresponding acquisition time and second location information
The prediction model of every kind of air pollutant concentration.
7. the prediction technique of air pollutant concentration according to claim 6, which is characterized in that when air pollutants exist
When associated association air pollutants, according to the history air pollutant concentration and corresponding acquisition of every kind of air pollutants
Time and second location information establish the step of prediction model of every kind of air pollutant concentration, comprising:
Obtain the pollutant concentration of association air pollutants associated with the air pollutants；
Training is used as in conjunction with the pollutant concentration and corresponding sample data of the air pollutants and its association air pollutants
Sample obtains the prediction model of this kind of air pollutant concentration.
8. the prediction technique of air pollutant concentration according to claim 2, which is characterized in that described with described three-dimensional
Sample data is as training sample, the step of training the prediction model of air pollutant concentration, comprising:
Adjust the characteristic parameter of each dimension in the gain of parameter prediction model establishment process of convolutional neural networks；Wherein, it rolls up
The parameter of product neural network includes at least one of size, step-length, the convolution number of plies of three dimensional convolution kernel；
Characteristic parameter is learnt as training sample using the sample data, according to the learning outcome of each characteristic parameter
Obtain the prediction model of air pollutant concentration.
9. a kind of prediction meanss of air pollutant concentration characterized by comprising
First obtains module, for obtaining the first location information of target prediction website and the predicted time of air pollutant concentration
Section；
Second obtains module, for obtaining several skies adjacent with the target prediction website according to the first location information
Gas detects the acquisition time of the second location information of website, Historical Pollution object concentration and the history air pollutant concentration；
Prediction module is used for according to the second location information, history air pollutant concentration and acquisition time, to the target
Prediction website is predicted in the air pollutant concentration of the predicted time section.
10. a kind of electronic equipment, characterized in that it comprises:
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and are configured
To be executed by one or more of processors, one or more of application programs are configured to: being executed according to claim 1
To air pollutant concentration described in any one of 8 prediction technique the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811428894.9A CN109657842A (en) | 2018-11-27 | 2018-11-27 | The prediction technique and device of air pollutant concentration, electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811428894.9A CN109657842A (en) | 2018-11-27 | 2018-11-27 | The prediction technique and device of air pollutant concentration, electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109657842A true CN109657842A (en) | 2019-04-19 |
Family
ID=66111645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811428894.9A Pending CN109657842A (en) | 2018-11-27 | 2018-11-27 | The prediction technique and device of air pollutant concentration, electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109657842A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210681A (en) * | 2019-06-11 | 2019-09-06 | 西安电子科技大学 | A kind of prediction technique of the monitoring station PM2.5 value based on distance |
| CN112580898A (en) * | 2020-12-30 | 2021-03-30 | 成都佳华物链云科技有限公司 | Pollution prediction method and pollution prediction model training method |
| CN112801423A (en) * | 2021-03-29 | 2021-05-14 | 北京英视睿达科技有限公司 | Method and device for identifying abnormity of air quality monitoring data and storage medium |
| CN112986492A (en) * | 2019-12-17 | 2021-06-18 | 华为技术有限公司 | Method and device for establishing gas concentration prediction model |
| CN113191626A (en) * | 2021-04-28 | 2021-07-30 | 中国科学院地理科学与资源研究所 | Abnormal area identification method and device |
| CN114066059A (en) * | 2021-11-16 | 2022-02-18 | 中科三清科技有限公司 | Method and device for predicting environmental pollution |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104850913A (en) * | 2015-05-28 | 2015-08-19 | 深圳先进技术研究院 | Air quality PM2.5 predicating method and air quality PM2.5 predicating system |
| CN105488316A (en) * | 2014-09-17 | 2016-04-13 | 日本电气株式会社 | Air quality prediction system and method |
| US20160370339A1 (en) * | 2015-06-16 | 2016-12-22 | International Business Machines Corporation | Air-Pollution Anomaly Location Mechanism |
| CN106485353A (en) * | 2016-09-30 | 2017-03-08 | 中国科学院遥感与数字地球研究所 | Air pollutant concentration forecasting procedure and system |
| CN106814162A (en) * | 2016-12-15 | 2017-06-09 | 珠海华海科技有限公司 | A kind of Outdoor Air Quality solution and system |
| CN108351866A (en) * | 2015-11-12 | 2018-07-31 | 国际商业机器公司 | Air pollution forecasting when ultrashort |
| CN108701274A (en) * | 2017-05-24 | 2018-10-23 | 北京质享科技有限公司 | A kind of small scale air quality index prediction technique in city and system |
-
2018
- 2018-11-27 CN CN201811428894.9A patent/CN109657842A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488316A (en) * | 2014-09-17 | 2016-04-13 | 日本电气株式会社 | Air quality prediction system and method |
| CN104850913A (en) * | 2015-05-28 | 2015-08-19 | 深圳先进技术研究院 | Air quality PM2.5 predicating method and air quality PM2.5 predicating system |
| US20160370339A1 (en) * | 2015-06-16 | 2016-12-22 | International Business Machines Corporation | Air-Pollution Anomaly Location Mechanism |
| CN108351866A (en) * | 2015-11-12 | 2018-07-31 | 国际商业机器公司 | Air pollution forecasting when ultrashort |
| CN106485353A (en) * | 2016-09-30 | 2017-03-08 | 中国科学院遥感与数字地球研究所 | Air pollutant concentration forecasting procedure and system |
| CN106814162A (en) * | 2016-12-15 | 2017-06-09 | 珠海华海科技有限公司 | A kind of Outdoor Air Quality solution and system |
| CN108701274A (en) * | 2017-05-24 | 2018-10-23 | 北京质享科技有限公司 | A kind of small scale air quality index prediction technique in city and system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210681A (en) * | 2019-06-11 | 2019-09-06 | 西安电子科技大学 | A kind of prediction technique of the monitoring station PM2.5 value based on distance |
| CN112986492A (en) * | 2019-12-17 | 2021-06-18 | 华为技术有限公司 | Method and device for establishing gas concentration prediction model |
| CN112580898A (en) * | 2020-12-30 | 2021-03-30 | 成都佳华物链云科技有限公司 | Pollution prediction method and pollution prediction model training method |
| CN112580898B (en) * | 2020-12-30 | 2023-11-03 | 成都佳华物链云科技有限公司 | Pollution prediction method and pollution prediction model training method |
| CN112801423A (en) * | 2021-03-29 | 2021-05-14 | 北京英视睿达科技有限公司 | Method and device for identifying abnormity of air quality monitoring data and storage medium |
| CN112801423B (en) * | 2021-03-29 | 2021-07-20 | 北京英视睿达科技有限公司 | Method and device for identifying abnormity of air quality monitoring data and storage medium |
| CN113191626A (en) * | 2021-04-28 | 2021-07-30 | 中国科学院地理科学与资源研究所 | Abnormal area identification method and device |
| CN113191626B (en) * | 2021-04-28 | 2022-02-01 | 中国科学院地理科学与资源研究所 | Abnormal area identification method and device |
| CN114066059A (en) * | 2021-11-16 | 2022-02-18 | 中科三清科技有限公司 | Method and device for predicting environmental pollution |
| CN114066059B (en) * | 2021-11-16 | 2023-03-28 | 中科三清科技有限公司 | Method and device for predicting environmental pollution |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109657842A (en) | The prediction technique and device of air pollutant concentration, electronic equipment | |
| CN104596507B (en) | A kind of determination method of mobile terminal trip track | |
| CN105785411B (en) | A kind of abnormal track-detecting method based on region division | |
| CN105203718B (en) | Air quality monitoring method and system | |
| CN104567906B (en) | A kind of city road network vehicle path planning method and device based on the Big Dipper | |
| CN105206057B (en) | Detection method and system based on Floating Car resident trip hot spot region | |
| CN111612670B (en) | Method, device and computer equipment for constructing emission list of motor vehicle | |
| KR101900777B1 (en) | Server for city enviromental analysis, and control method thereof | |
| CN102147260A (en) | Electronic map matching method and device | |
| CN108446324A (en) | A kind of GPS data reconstructing method based on long memory network LSTM in short-term | |
| CN110222906A (en) | Electric vehicle energy consumption prediction technique, computer readable storage medium and electronic equipment | |
| CN110239577A (en) | A kind of in-vehicle exposure environment Train occupant's health protection system and method | |
| CN109934379A (en) | Prediction technique, device and the electronic equipment of air pollutant concentration | |
| CN111241214B (en) | Water quality remote online detection method and device for hydraulic engineering and electronic equipment | |
| CN103267716B (en) | System for rapid discovery of initiation point of large-area PM 2.5 pollution and operation method thereof | |
| CN110175507A (en) | Model evaluation method, apparatus, computer equipment and storage medium | |
| CN117109582A (en) | Atmospheric pollution source positioning system and method combining sensing network and machine learning | |
| Zhu et al. | Multi-sensing paradigm based urban air quality monitoring and hazardous gas source analyzing: a review | |
| CN116340768B (en) | Intelligent road dust accumulation load monitoring method and monitoring device | |
| CN108596381B (en) | Urban parking demand prediction method based on OD data | |
| Berjisian et al. | Evaluation of map‐matching algorithms for smartphone‐based active travel data | |
| Sik et al. | Toward cognitive data analysis with big data environment | |
| Aoya | Structural position of the Seba eclogite unit in the Sambagawa Belt: Supporting evidence for an eclogite nappe | |
| CN114396956A (en) | Navigation method and apparatus, computing device, storage medium, and computer program product | |
| Sun et al. | Cooperative calibration scheme for mobile wireless sensor network |
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 |