CN113283630A - Air quality prediction method, device, equipment and computer readable storage medium - Google Patents
Air quality prediction method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN113283630A CN113283630A CN202110383262.0A CN202110383262A CN113283630A CN 113283630 A CN113283630 A CN 113283630A CN 202110383262 A CN202110383262 A CN 202110383262A CN 113283630 A CN113283630 A CN 113283630A
- Authority
- CN
- China
- Prior art keywords
- data
- air quality
- prediction
- emission source
- current
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 51
- 238000012549 training Methods 0.000 claims description 14
- 238000003062 neural network model Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 230000015654 memory Effects 0.000 claims description 4
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 2
- 230000006403 short-term memory Effects 0.000 claims description 2
- 239000003344 environmental pollutant Substances 0.000 abstract description 12
- 231100000719 pollutant Toxicity 0.000 abstract description 12
- 238000013508 migration Methods 0.000 abstract description 2
- 230000005012 migration Effects 0.000 abstract description 2
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 12
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 8
- 238000012937 correction Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000011109 contamination Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000013618 particulate matter Substances 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013526 transfer learning Methods 0.000 description 2
- 238000003915 air pollution Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
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
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Embodiments of the present disclosure provide an air quality prediction method, apparatus, device, and computer-readable storage medium. The method comprises the steps of predicting an emission source to obtain emission source prediction data; inputting the emission source prediction data, the current emission source data, the current air quality monitoring data, the current meteorological data and the meteorological forecast data into a pre-trained air quality prediction model to obtain air quality prediction data; and acquiring air quality monitoring data, and if the air quality monitoring data is higher than air quality prediction data at a corresponding moment and the difference value is greater than a preset value, sending an alarm instruction. In this way, the influence of local pollutant emission and other regional pollutant migration can be simultaneously considered, and the air quality forecast can be more accurately carried out.
Description
Technical Field
Embodiments of the present disclosure relate generally to the field of environmental monitoring and, more particularly, to air quality prediction methods, apparatus, devices, and computer-readable storage media.
Background
The air quality is more and more emphasized by the government and the public, and the research of the air pollution forecasting mode corresponding to the air quality is also greatly developed. The currently commonly used air quality prediction modes mainly include: numerical prediction and statistical prediction. The numerical prediction mainly utilizes an air quality mode to systematize complex atmospheric physical and chemical modes, establishes a model related to pollutant emission, weather and chemical reactions, and simulates the change of air quality. In fact, besides the meteorological data, the numerical prediction also requires more accurate pollutant emission data, detailed geographical environment data, boundary conditions, etc., and requires a lot of calculation. Meanwhile, because the pollutant emission dynamic change of the pollution source is large, accurate pollution source data is difficult to obtain, and therefore the current forecasting effect of numerical forecasting is often difficult to achieve an ideal effect.
Disclosure of Invention
According to an embodiment of the present disclosure, an air quality prediction scheme is provided.
In a first aspect of the disclosure, an air quality prediction method is provided. The method comprises the following steps: carrying out emission source prediction to obtain emission source prediction data; inputting the emission source prediction data, the current emission source data, the current air quality monitoring data, the current meteorological data and the meteorological forecast data into a pre-trained air quality prediction model to obtain air quality prediction data; and acquiring air quality monitoring data, and if the air quality monitoring data is higher than air quality prediction data at a corresponding moment and the difference value is greater than a preset value, sending an alarm instruction.
The above-described aspects and any possible implementation further provide an implementation, where performing emission source prediction, and obtaining emission source prediction data includes: according to a pre-trained emission source data prediction model, obtaining emission source prediction data of 1 st to n th first preset time intervals from a first moment, wherein n is a positive integer greater than or equal to 1.
The above-mentioned aspects and any possible implementation further provide an implementation, wherein inputting the emission source prediction data, the current emission source data, the current air quality monitoring data, the current weather data, and the weather forecast data into a pre-trained air quality prediction model, and obtaining the air quality prediction data includes: inputting emission source prediction data of 1 st to n th first preset time intervals, current emission source data, current air quality monitoring data, current meteorological data and meteorological forecast data of 1 st to m th second preset time intervals into a pre-trained air quality prediction model to obtain air quality prediction data of 1 st to L th third preset time intervals; wherein m and L are positive integers of more than or equal to 1.
The above-described aspect and any possible implementation further provide an implementation, wherein the air quality model is trained by: generating a training set according to historical emission source data, historical meteorological data and historical air quality data; training a preset neural network model through the training sample; wherein, the neural network model is an RNN recurrent neural network model or an LSTM long-term and short-term memory model.
The above-mentioned aspect and any possible implementation manner further provide an implementation manner that a sum of the n first preset time intervals and a sum of the m second preset time intervals are respectively greater than a sum of the L third preset time intervals.
The above-mentioned aspect and any possible implementation manner further provide an implementation manner, where obtaining the air quality prediction data of 1 st to L th third preset time intervals includes: the air quality data of the 1 st and third preset time intervals from the first moment are predicted firstly, then the air quality data of the 2 nd and third preset time intervals from the first moment are predicted on the basis of the air quality data, and the like.
As for the above-mentioned aspects and any possible implementation manner, there is further provided an implementation manner, wherein if the air quality monitoring data is higher than the corresponding air quality prediction data, and the difference is greater than a preset value, the sending an alarm instruction includes: the preset value is a specific value, or a percentage of the value of the air quality prediction data.
In a second aspect of the present disclosure, an air quality prediction device is provided. The device includes: the emission source prediction module is used for predicting the emission source to obtain emission source prediction data; the air quality prediction module is used for inputting the emission source prediction data, the current emission source data, the current air quality monitoring data, the current meteorological data and the meteorological forecast data into a pre-trained air quality prediction model to obtain air quality prediction data; and the alarm module is used for acquiring air quality monitoring data, and if the air quality monitoring data is higher than the air quality prediction data at the corresponding moment and the difference value is greater than a preset value, sending an alarm instruction.
In a third aspect of the disclosure, an electronic device is provided. The electronic device includes: a memory having a computer program stored thereon and a processor implementing the method as described above when executing the program.
In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which program, when executed by a processor, implements a method as according to the first and/or second aspect of the present disclosure.
It should be understood that the statements herein reciting aspects are not intended to limit the critical or essential features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like or similar reference characters designate like or similar elements, and wherein:
FIG. 1 shows a flow diagram of an air quality prediction method according to an embodiment of the present disclosure;
FIG. 2 illustrates a block diagram of an air quality prediction device according to an embodiment of the present disclosure;
FIG. 3 illustrates a block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, but not all embodiments of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Fig. 1 shows a flow diagram of an air quality prediction method 100 according to an embodiment of the present disclosure.
At block 102, emissions source prediction is performed to obtain emissions source prediction data;
in some embodiments, the emission source prediction data for 1 st to nth first preset time intervals from the first time is obtained according to a pre-trained emission source data prediction model.
In some embodiments, emission parameter monitoring data is obtained from an emission source provided with monitoring equipment, a training sample is generated according to the emission parameter monitoring data and corresponding time (including information such as month, working day, time (different time in each day) and the like), a preset neural network model is trained, and an emission source data prediction model is established; the emission source data prediction model can reflect the rule that the emission parameters of the emission sources of the area to be subjected to air quality prediction change along with time.
In some embodiments, the emission source data and the current time at the current time or at a plurality of first preset time intervals before the current time are input into a pre-established emission source data prediction model, so as to obtain the emission source prediction data of the 1 st to nth first preset time intervals, where n is a positive integer greater than or equal to 1. By inputting the emission source data at the current time or at the current time and a plurality of first preset time intervals before the current time into the pre-established emission source data prediction model, the emission source prediction can be more accurately performed compared with the case that only the emission source data at the current time is input.
In some embodiments, the rules for the variation of the emission parameters with time include rules that vary according to time such as quarterly, month, week (working day), day (hour), and the like.
In some embodiments, the emission source data may include one or more of a sulfur dioxide concentration, a nitrogen oxide concentration, an ozone concentration, or a total suspended particulate matter concentration, and may be weighted based on the sulfur dioxide concentration, the nitrogen oxide concentration, the ozone concentration, or the total suspended particulate matter concentration.
Through the step, the emission parameters of the emission sources of the area to be subjected to the air quality prediction can be predicted and used as local pollution source parameters to provide a basis for further air quality prediction.
Since the amount of data and the calculation power required for making the emission source prediction are relatively small, a short first preset time interval may be set. In some embodiments, the first predetermined time interval corresponds to a second predetermined time interval of the weather forecast data and a third predetermined time interval of the air quality prediction data, and takes the same value.
At block 104, inputting the emission source prediction data, current emission source data, current air quality monitoring data, current meteorological data, and meteorological forecast data into a pre-trained air quality prediction model to obtain air quality prediction data;
in some embodiments, the emission source prediction data of 1 to n first preset time intervals, the current emission source data, the current air quality monitoring data, the current meteorological data, and the meteorological forecast data of 1 to m second preset time intervals are input into a pre-trained air quality prediction model to obtain the air quality prediction data of 1 to L third preset time intervals; wherein m and L are positive integers of 1 or more, and n, m and L may be the same or different. In some embodiments, the sum of the n first preset time intervals and the sum of the m second preset time intervals are respectively greater than the sum of the L third preset time intervals, so as to ensure that the time range of the emission source prediction data and the weather forecast data is greater than the time range of the air quality prediction, and improve the accuracy of the air quality prediction. The first preset time interval from 1 st to n, the second preset time interval from 1 st to m and the third preset time interval from 1 st to L are all started from the current moment.
By comprehensively considering the local emission source data and the meteorological data, the influence of the local emission source and regional transmission on the air quality can be better reflected.
In some embodiments, the air quality prediction is performed separately for different regions where air quality prediction is to be performed.
In some embodiments, the air quality prediction model is trained by:
generating a training set according to historical emission source data, historical meteorological data and historical air quality data; the historical emission source data is emission parameter monitoring data obtained from an emission source provided with monitoring equipment; the historical meteorological data is meteorological monitoring data; the historical air quality data are air quality monitoring data, and after a sample training air quality prediction model is generated by adopting the historical data, the corresponding prediction data can be input into the trained air quality prediction model, so that the corresponding air quality prediction data can be obtained.
In some embodiments, the training set comprises samples and annotations, the samples comprising: first time discharge source data, first time meteorological data, first time air quality monitoring data, discharge source data for 1 st to n first predetermined time intervals from the first time, meteorological data for 1 st to m second predetermined time intervals from the first time, the labeling comprising: air quality data for 1 st to L third preset time intervals from the first time.
In some embodiments, the training samples comprise: emission source data of a plurality of first preset time intervals before a first moment and the first moment, meteorological data of a plurality of second preset time intervals before the first moment and the first moment, air quality data of a plurality of third preset time intervals before the first moment and the first moment, emission source data of 1 st to n th first preset time intervals from the first moment, meteorological data of 1 st to m second preset time intervals from the first moment, and the label comprises: air quality data for 1 st to L third preset time intervals from the first time. By adding the emission source data, the meteorological data and the air quality data of a plurality of first preset time intervals before the first moment to the training sample, the change rule of the air quality can be better embodied.
In some embodiments, the meteorological data includes dew point, temperature, wind direction, wind speed, cumulative hourly snow and cumulative hourly rain, among other data.
Training a preset neural network model through the training sample; wherein the neural network model may be an RNN recurrent neural network model or an LSTM long-short term memory model.
In some embodiments, the air quality data for the 1 st to L third preset time intervals from the first time instant may be directly predicted. Or the air quality data of the 1 st third preset time interval from the first time can be predicted firstly, then the air quality data of the 2 nd third preset time interval from the first time can be predicted on the basis, and the like, so as to further improve the prediction accuracy of the air quality. The air quality data predicted in the above manner and the air quality data directly predicted for the 1 st to L third preset time intervals from the first time may be subjected to weighted summation to obtain final prediction data.
The existing air quality prediction method is influenced by the prediction result at the previous moment, so that the prediction is easy to have hysteresis, and the accuracy of air quality prediction is reduced. The concrete expression is as follows: (1) hysteresis at the onset of heavy fouling: for example, when a heavy contamination process is started, the forecast may not capture the contamination because the observed value of the day before the heavy contamination is started is low, and the predicted value of the day may still be low. (2) Hysteresis at the end of heavy fouling: when the heavy contamination process is over, the predicted value for the day may indicate that contamination is still occurring for that day due to the effect of the high concentration observations on the day before the end of heavy contamination. Therefore, it is necessary to combine the current air quality monitoring data and the current meteorological data to avoid the occurrence of hysteresis in prediction.
In some embodiments, since the air quality prediction with a large data volume needs to consume a large amount of computing resources and computing time, the air quality prediction may be performed at a third larger preset time interval, and the prediction result may be determined, and if the change rate of the air quality exceeds the threshold value within a certain time range, the air quality prediction may be performed again at a third smaller preset time interval, so as to improve the prediction accuracy. The air quality prediction model adaptive to different third preset time intervals can be obtained in a transfer learning mode, and the air quality prediction model adaptive to the updated third preset time intervals can be obtained by performing transfer learning on the trained air quality prediction model by using a small number of updated samples of the third preset time intervals.
In some embodiments, the air quality prediction is periodically re-performed, updating the air quality prediction data. Specifically, a period for periodically re-performing air quality prediction may be set according to a demand for prediction accuracy, for example, if higher accuracy is required, data may be updated every third preset time interval; if less precision is required, the data may be updated again after every third predetermined time interval, e.g., L.
With this step, the previous air quality prediction can be periodically updated to provide more accurate air quality prediction data.
In some embodiments, based on the air quality monitoring data of the 1 st third preset time interval from the first time, calculating a correction coefficient with the air quality data prediction data of the 1 st third preset time interval from the first time; and correcting the air quality data prediction data of the 2 nd or more third preset time intervals from the first moment according to the correction coefficient. The correction coefficient is the air quality monitoring data of the 1 st third preset time interval starting from the first moment/the air quality data prediction data of the 1 st third preset time interval starting from the first moment. The correction coefficient may also be a partial regression coefficient obtained by performing linear regression on a plurality of sets of air quality monitoring data of the 1 st third preset time interval from the first time and the air quality data prediction data of the corresponding time in the past air quality prediction processes.
In some embodiments, a second correction factor is calculated according to the air quality monitoring data of the 2 nd third preset time interval starting from the first time and the air quality data prediction data of the 2 nd third preset time interval starting from the first time; and correcting the air quality data prediction data of 3 rd or more third preset time intervals from the first moment according to the second correction coefficient. The calculation method of the second correction coefficient is similar to that of the above embodiment, and is not described herein again.
In some embodiments, the air quality data prediction data for a third predetermined time interval may be modified by analogy.
Through the correction, the prediction precision is improved to a certain extent, and the frequency of periodically and repeatedly predicting the air quality can be reduced.
The operation of repeatedly performing air quality prediction at every third preset time interval is avoided, and the times of performing air quality prediction can be reduced.
In some embodiments, the method further comprises:
at block 106, air quality monitoring data is obtained, and if the air quality monitoring data is higher than the air quality prediction data at the corresponding moment and the difference value is greater than a preset value, an alarm instruction is issued.
In some embodiments, the air quality monitoring data for the 1 st to L third preset time intervals from the first time instant is obtained and compared with the air quality prediction data for the corresponding 1 st to L third preset time intervals.
In some embodiments, the air quality monitoring data for the 1 st third preset time interval from the first time instant is obtained and compared with the air quality prediction data for the corresponding 1 st third preset time interval.
In some embodiments, the preset value may be a specific value or a percentage of the value of the air quality prediction data, such as setting the preset value to 20% of the value of the air quality prediction data.
In some embodiments, if the air quality monitoring data of a third preset time interval of a preset number of consecutive times is higher than the air quality prediction data, and the difference is greater than the preset value, an alarm command is issued. If part of the air quality monitoring data of the third preset time interval is higher than the air quality prediction data, and the difference value is less than or equal to the preset value; or the air quality monitoring data is less than or equal to the air quality prediction data, ending the judgment process, and entering the judgment process of the air quality monitoring data and the air quality prediction data of the next continuous preset plurality of third preset time intervals.
In some embodiments, the air quality prediction data may include one or more of a sulfur dioxide concentration, a nitrogen oxide concentration, an ozone concentration, or a total suspended particulate matter concentration, and may be obtained by weighting the sulfur dioxide concentration, the nitrogen oxide concentration, the ozone concentration, or the total suspended particulate matter concentration.
In some embodiments, the cause of the abnormality of the air quality monitoring data may also be determined by the air quality prediction data, for example, the pollutant causing the abnormality of the air quality monitoring data may be determined according to the difference between the concentration of various pollutants in the air quality prediction data and the concentration of various pollutants in the air quality monitoring data, and the source of the pollutant may be further analyzed and determined, so as to avoid the false report of the local emission source data caused by the meteorological factors conveying the pollutants conveyed from other areas to the prediction area.
According to the embodiment of the disclosure, the following technical effects are achieved:
based on the emission source prediction data and the meteorological forecast data, the influence of local pollutant emission and other regional pollutant migration is considered, and air quality forecast can be accurately carried out;
the air quality forecast is carried out in stages, and the time precision of the air quality forecast can be flexibly adjusted.
It is noted that while for simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present disclosure is not limited by the order of acts, as some steps may, in accordance with the present disclosure, occur in other orders and concurrently. Further, those skilled in the art should also appreciate that the embodiments described in the specification are exemplary embodiments and that acts and modules referred to are not necessarily required by the disclosure.
The above is a description of embodiments of the method, and the embodiments of the apparatus are further described below.
Fig. 2 illustrates a block diagram of an air quality prediction apparatus 200 according to an embodiment of the present disclosure.
As shown in fig. 2, the apparatus 200 includes:
an emission source prediction module 202, configured to perform emission source prediction to obtain emission source prediction data;
the air quality prediction module 204 is used for inputting the emission source prediction data, the current emission source data, the current air quality monitoring data, the current meteorological data and the meteorological forecast data into a pre-trained air quality prediction model to obtain air quality prediction data;
and the alarm module 206 is configured to obtain the air quality monitoring data, and send an alarm instruction if the air quality monitoring data is higher than the air quality prediction data at the corresponding time and the difference is greater than a preset value.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the described module may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
FIG. 3 shows a schematic block diagram of an electronic device 300 that may be used to implement embodiments of the present disclosure. As shown, the device 300 includes a CPU301 that can perform various appropriate actions and processes according to computer program instructions stored in a ROM302 or loaded from a storage unit 308 into a RAM 303. In the RAM303, various programs and data necessary for the operation of the device 300 can also be stored. The CPU301, ROM302, and RAM303 are connected to each other via a bus 304. An I/O interface 305 is also connected to bus 304.
Various components in device 300 are connected to I/O interface 305, including: an input unit 306 such as a keyboard, a mouse, or the like; an output unit 307 such as various types of displays, speakers, and the like; a storage unit 308 such as a magnetic disk, optical disk, or the like; and a communication unit 309 such as a network card, modem, wireless communication transceiver, etc. The communication unit 309 allows the device 300 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The CPU301 executes the various methods and processes described above, such as the method 100. For example, in some embodiments, the method 100 may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 308. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 300 via ROM302 and/or communication unit 309. When the computer program is loaded into RAM303 and executed by CPU301, one or more steps of method 100 described above may be performed. Alternatively, in other embodiments, the CPU301 may be configured to perform the method 100 by any other suitable means (e.g., by way of firmware).
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
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 data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations 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 RAM, a ROM, an EPROM, an optical fiber, a CD-ROM, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims (10)
1. An air quality prediction method, comprising:
carrying out emission source prediction to obtain emission source prediction data;
inputting the emission source prediction data, the current emission source data, the current air quality monitoring data, the current meteorological data and the meteorological forecast data into a pre-trained air quality prediction model to obtain air quality prediction data;
and acquiring air quality monitoring data, and if the air quality monitoring data is higher than air quality prediction data at a corresponding moment and the difference value is greater than a preset value, sending an alarm instruction.
2. The method of claim 1, wherein performing emission source predictions and obtaining emission source prediction data comprises:
according to a pre-trained emission source data prediction model, obtaining emission source prediction data of 1 st to n th first preset time intervals from a first moment, wherein n is a positive integer greater than or equal to 1.
3. The method of claim 2, wherein inputting the emissions source prediction data, current emissions source data, current air quality monitoring data, current weather data, weather forecast data into a pre-trained air quality prediction model, resulting in air quality prediction data comprises:
inputting emission source prediction data of 1 st to n th first preset time intervals, current emission source data, current air quality monitoring data, current meteorological data and meteorological forecast data of 1 st to m th second preset time intervals into a pre-trained air quality prediction model to obtain air quality prediction data of 1 st to L th third preset time intervals; wherein m and L are positive integers of more than or equal to 1.
4. The method of claim 3, wherein the air quality prediction model is trained by:
generating a training set according to historical emission source data, historical meteorological data and historical air quality data;
training a preset neural network model through the training sample; wherein, the neural network model is an RNN recurrent neural network model or an LSTM long-term and short-term memory model.
5. The method of claim 3,
the sum of the n first preset time intervals and the sum of the m second preset time intervals are respectively greater than the sum of the L third preset time intervals.
6. The method of claim 3, wherein obtaining air quality prediction data for 1 st to L third predetermined time intervals comprises:
the air quality data of the 1 st third preset time interval from the first moment is predicted firstly, and then the air quality data of the 2 nd third preset time interval from the first moment is predicted on the basis of the air quality data, and so on.
7. The method of claim 3, wherein if the air quality monitoring data is higher than the corresponding air quality prediction data and the difference value is greater than a preset value, issuing an alarm command comprises:
the preset value is a specific value, or a percentage of the value of the air quality prediction data.
8. An air quality prediction apparatus, comprising:
the emission source prediction module is used for predicting the emission source to obtain emission source prediction data;
the air quality prediction module is used for inputting the emission source prediction data, the current emission source data, the current air quality monitoring data, the current meteorological data and the meteorological forecast data into a pre-trained air quality prediction model to obtain air quality prediction data;
and the alarm module is used for acquiring air quality monitoring data, and if the air quality monitoring data is higher than the air quality prediction data at the corresponding moment and the difference value is greater than a preset value, sending an alarm instruction.
9. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program, wherein the processor, when executing the program, implements the method of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110383262.0A CN113283630A (en) | 2021-04-09 | 2021-04-09 | Air quality prediction method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110383262.0A CN113283630A (en) | 2021-04-09 | 2021-04-09 | Air quality prediction method, device, equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113283630A true CN113283630A (en) | 2021-08-20 |
Family
ID=77276491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110383262.0A Pending CN113283630A (en) | 2021-04-09 | 2021-04-09 | Air quality prediction method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113283630A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113777236A (en) * | 2021-09-08 | 2021-12-10 | 中科三清科技有限公司 | Air quality monitoring method and device based on emission source |
| CN114241157A (en) * | 2021-12-16 | 2022-03-25 | 中科三清科技有限公司 | Air quality visual display method, device and equipment |
| CN115619008A (en) * | 2022-09-23 | 2023-01-17 | 中科三清科技有限公司 | Air quality prediction method, device, equipment and computer readable storage medium |
| US11774426B1 (en) * | 2022-03-25 | 2023-10-03 | Project Canary, Pbc | Emissions detection system and methods |
| US11781979B1 (en) | 2020-09-10 | 2023-10-10 | Project Canary, Pbc | Air quality monitoring system and method |
| US11788889B1 (en) | 2018-11-13 | 2023-10-17 | Project Canary, Pbc | Air quality monitoring system and method |
| US11810216B1 (en) | 2023-02-01 | 2023-11-07 | Project Canary, Pbc | Air quality monitors minimization system and methods |
| US11861753B1 (en) | 2023-02-01 | 2024-01-02 | Project Canary, Pbc | Air quality monitors minimization system and methods |
| US11887203B1 (en) | 2023-02-01 | 2024-01-30 | Project Canary, Pbc | Air quality monitors minimization system and methods |
| US11892437B2 (en) | 2019-01-23 | 2024-02-06 | Project Canary, Pbc | Apparatus and methods for reducing fugitive gas emissions at oil facilities |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108053071A (en) * | 2017-12-21 | 2018-05-18 | 宇星科技发展(深圳)有限公司 | Regional air pollutant concentration Forecasting Methodology, terminal and readable storage medium storing program for executing |
| CN109946209A (en) * | 2019-03-13 | 2019-06-28 | 北京英视睿达科技有限公司 | A kind of method and device of atmosphere pollution alarm |
| CN110531029A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of device based on environmentally friendly Internet of Things big data prediction air quality trend |
| CN110836952A (en) * | 2019-09-29 | 2020-02-25 | 北京众蓝科技有限公司 | Air quality forecasting method and device for adjusting emission source list by using emission source monitoring data |
| CN111103405A (en) * | 2019-12-24 | 2020-05-05 | 象辑知源（武汉）科技有限公司 | Air quality forecast early warning system |
| CN111814964A (en) * | 2020-07-20 | 2020-10-23 | 江西省环境监测中心站 | Air pollution treatment method based on air quality condition prediction and storage medium |
| CN112288192A (en) * | 2020-11-23 | 2021-01-29 | 深圳市维度数据科技股份有限公司 | Environment-friendly monitoring and early warning method and system |
| CN112363251A (en) * | 2020-10-26 | 2021-02-12 | 上海眼控科技股份有限公司 | Weather prediction model generation method, weather prediction method and device |
-
2021
- 2021-04-09 CN CN202110383262.0A patent/CN113283630A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108053071A (en) * | 2017-12-21 | 2018-05-18 | 宇星科技发展(深圳)有限公司 | Regional air pollutant concentration Forecasting Methodology, terminal and readable storage medium storing program for executing |
| CN109946209A (en) * | 2019-03-13 | 2019-06-28 | 北京英视睿达科技有限公司 | A kind of method and device of atmosphere pollution alarm |
| CN110531029A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of device based on environmentally friendly Internet of Things big data prediction air quality trend |
| CN110836952A (en) * | 2019-09-29 | 2020-02-25 | 北京众蓝科技有限公司 | Air quality forecasting method and device for adjusting emission source list by using emission source monitoring data |
| CN111103405A (en) * | 2019-12-24 | 2020-05-05 | 象辑知源（武汉）科技有限公司 | Air quality forecast early warning system |
| CN111814964A (en) * | 2020-07-20 | 2020-10-23 | 江西省环境监测中心站 | Air pollution treatment method based on air quality condition prediction and storage medium |
| CN112363251A (en) * | 2020-10-26 | 2021-02-12 | 上海眼控科技股份有限公司 | Weather prediction model generation method, weather prediction method and device |
| CN112288192A (en) * | 2020-11-23 | 2021-01-29 | 深圳市维度数据科技股份有限公司 | Environment-friendly monitoring and early warning method and system |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11788889B1 (en) | 2018-11-13 | 2023-10-17 | Project Canary, Pbc | Air quality monitoring system and method |
| US11892437B2 (en) | 2019-01-23 | 2024-02-06 | Project Canary, Pbc | Apparatus and methods for reducing fugitive gas emissions at oil facilities |
| US11867619B1 (en) | 2020-09-10 | 2024-01-09 | Project Canary, Pbc | Air quality monitoring system and method |
| US11781979B1 (en) | 2020-09-10 | 2023-10-10 | Project Canary, Pbc | Air quality monitoring system and method |
| US12031905B2 (en) | 2020-09-10 | 2024-07-09 | Project Canary, Pbc | Air quality monitoring system and method |
| CN113777236B (en) * | 2021-09-08 | 2022-04-26 | 中科三清科技有限公司 | Air quality monitoring method and device based on emission source |
| CN113777236A (en) * | 2021-09-08 | 2021-12-10 | 中科三清科技有限公司 | Air quality monitoring method and device based on emission source |
| CN114241157A (en) * | 2021-12-16 | 2022-03-25 | 中科三清科技有限公司 | Air quality visual display method, device and equipment |
| US11774426B1 (en) * | 2022-03-25 | 2023-10-03 | Project Canary, Pbc | Emissions detection system and methods |
| US12031967B2 (en) | 2022-03-25 | 2024-07-09 | Project Canary, Pbc | Emissions detection system and methods |
| CN115619008A (en) * | 2022-09-23 | 2023-01-17 | 中科三清科技有限公司 | Air quality prediction method, device, equipment and computer readable storage medium |
| US11810216B1 (en) | 2023-02-01 | 2023-11-07 | Project Canary, Pbc | Air quality monitors minimization system and methods |
| US11861753B1 (en) | 2023-02-01 | 2024-01-02 | Project Canary, Pbc | Air quality monitors minimization system and methods |
| US11887203B1 (en) | 2023-02-01 | 2024-01-30 | Project Canary, Pbc | Air quality monitors minimization system and methods |
| US12112392B2 (en) | 2023-02-01 | 2024-10-08 | Project Canary, Pbc | Air quality monitors minimization system and methods |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113283630A (en) | Air quality prediction method, device, equipment and computer readable storage medium | |
| Nguyen et al. | A new method for forecasting energy output of a large-scale solar power plant based on long short-term memory networks a case study in Vietnam | |
| CN113537563B (en) | Pollution emergency management and control effect evaluation method and device | |
| CN110232483B (en) | Deep learning load prediction method and device and terminal equipment | |
| CN112285807B (en) | Meteorological information prediction method and device | |
| US20150317589A1 (en) | Forecasting system using machine learning and ensemble methods | |
| CN109471783B (en) | Method and device for predicting task operation parameters | |
| US20180239057A1 (en) | Forecasting air quality | |
| CN113777236B (en) | Air quality monitoring method and device based on emission source | |
| KR20200052806A (en) | Operating method of deep learning based climate change prediction system | |
| WO2024046137A1 (en) | Power prediction model construction method for multi-energy combined power generation system and power prediction method for multi-energy combined power generation system | |
| CN113642263B (en) | Air quality early warning method and device based on Beidou grid | |
| Qu et al. | A parameter and resolution adaptive algorithm for rapid detection of ramp events in different timescale databases of the power system | |
| CN114254840A (en) | Data processing method, electronic equipment and storage medium | |
| US11645540B2 (en) | Deep graph de-noise by differentiable ranking | |
| CN113689125A (en) | Information pushing method and device | |
| CN106909983A (en) | Based on many meteorological sources ultra-short term wind speed forecasting methods of Kalman filter and device | |
| CN112819260B (en) | Data processing system for predicting flight delay state | |
| CN113011664A (en) | Logistics timeliness monitoring method and device, electronic equipment and storage medium | |
| CN115456168B (en) | Training method of reinforcement learning model, energy consumption determining method and device | |
| CN117391257A (en) | Road congestion condition prediction method and device | |
| CN115619008A (en) | Air quality prediction method, device, equipment and computer readable storage medium | |
| KR20190129675A (en) | System and Method for Energy Forecasting using Directional Cost Function | |
| CN115453053A (en) | Pollution analysis method, device, equipment and storage medium | |
| CN114565170A (en) | Pollutant tracing method and device, equipment, medium and product |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210820 |
|
| RJ01 | Rejection of invention patent application after publication |