CN117612645B - Pollution weather condition prediction method and device, storage medium and electronic equipment - Google Patents
Pollution weather condition prediction method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN117612645B CN117612645B CN202410094388.XA CN202410094388A CN117612645B CN 117612645 B CN117612645 B CN 117612645B CN 202410094388 A CN202410094388 A CN 202410094388A CN 117612645 B CN117612645 B CN 117612645B
- Authority
- CN
- China
- Prior art keywords
- historical
- future
- pollutant
- concentration
- different
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 216
- 231100000719 pollutant Toxicity 0.000 claims abstract description 216
- 230000008859 change Effects 0.000 claims abstract description 53
- 239000000356 contaminant Substances 0.000 claims description 126
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004088 simulation Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 12
- 238000009825 accumulation Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 230000002349 favourable effect Effects 0.000 description 7
- 230000010354 integration Effects 0.000 description 4
- 238000001556 precipitation Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 235000000100 Hibiscus rosa sinensis Nutrition 0.000 description 1
- 101100518501 Mus musculus Spp1 gene Proteins 0.000 description 1
- 240000008254 Rosa chinensis Species 0.000 description 1
- 235000000664 Rosa chinensis Nutrition 0.000 description 1
- 235000016785 Rosa della China Nutrition 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- 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—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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Crystallography & Structural Chemistry (AREA)
- Computing Systems (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure relates to a pollution weather condition prediction method, a pollution weather condition prediction device, a storage medium and electronic equipment, and relates to the technical field of pollution prediction. Comprising the following steps: taking the historical meteorological data and a fixed pollution source emission list of a plurality of different first time periods as input parameters of an air quality model to obtain first historical pollutant concentrations of different first time periods; taking the first historical pollutant concentrations in different first time periods as input parameters of a statistical prediction model to obtain future pollutant concentrations; the statistical prediction model is used for predicting and obtaining the future pollutant concentration according to the historical pollutant concentration; and obtaining the same ratio change rate according to the first historical pollutant concentration and the future pollutant concentration. By using the pollution meteorological condition prediction method provided by the disclosure, the influence of meteorological data on the concentration of pollutants can be accurately obtained.
Description
Technical Field
The disclosure relates to the technical field of pollution prediction, in particular to a pollution weather condition prediction method, a pollution weather condition prediction device, a storage medium and electronic equipment.
Background
In the related technology, the pollutant concentration is influenced by meteorological data and pollutant emission, a statistical prediction model can be established according to the meteorological data and the pollutant emission, future pollutant concentration is predicted through the statistical prediction model, and the same-ratio change rate of the polluted meteorological conditions is obtained according to the predicted pollutant concentration and the historical pollutant concentration.
However, the influence of the meteorological data and the pollutant emission on the pollutant concentration cannot be separated, so that the statistical prediction model obtains the pollutant concentration under the common influence of the meteorological data and the pollutant emission, and cannot obtain the pollutant concentration under the influence of the meteorological data alone.
Disclosure of Invention
The disclosure aims to provide a pollution weather condition prediction method, a pollution weather condition prediction device, a storage medium and electronic equipment, so as to solve the technical problems.
According to a first aspect of embodiments of the present disclosure, there is provided a pollution weather condition prediction method, including:
taking historical meteorological data of a plurality of different first time periods and a fixed pollution source emission list as input parameters of an air quality model to obtain first historical pollutant concentrations of different first time periods;
Taking the first historical pollutant concentrations in different first time periods as input parameters of a statistical prediction model to obtain future pollutant concentrations; the statistical prediction model is used for predicting and obtaining the future pollutant concentration according to the historical pollutant concentration;
and obtaining a same-ratio change rate according to the first historical pollutant concentration and the future pollutant concentration, wherein the same-ratio change rate is used for representing future meteorological data influencing the future pollutant concentration and is used for comparing specific values of historical meteorological data preference or deviation influencing the first historical pollutant concentration.
Optionally, the obtaining future pollutant concentrations by using the first historical pollutant concentrations in different first time periods as input parameters of a statistical prediction model includes:
and taking the second historical pollutant concentrations belonging to the same second time period in the first historical pollutant concentrations of different first time periods as input parameters of a statistical prediction model corresponding to the second time period to obtain future pollutant concentrations corresponding to different second time periods, wherein the time range of the second time period is smaller than that of the first time period.
Optionally, the method further comprises:
And fitting according to the second historical pollutant concentrations in different second time periods to obtain statistical prediction models corresponding to the different second time periods.
Optionally, the fitting to obtain the statistical prediction model corresponding to the second time period according to the second historical pollutant concentration of the second time period includes:
fitting to obtain an autoregressive order, a differential order and a moving average order according to the second historical pollutant concentrations in the same second time period in different first time periods;
and obtaining a statistical prediction model corresponding to the second time period according to the autoregressive order, the differential order and the moving average order.
Optionally, the obtaining the same ratio change rate according to the first historical pollutant concentration and the future pollutant concentration includes:
and obtaining the same-ratio change rate according to the second historical pollutant concentration belonging to the same second time period in the first historical pollutant concentrations of different first time periods and the future pollutant concentration of the second time period, wherein the same-ratio change rate is used for representing a specific value of preference or deviation of future meteorological data affecting the future pollutant concentration compared with the historical meteorological data affecting the second historical pollutant concentration.
Optionally, the method further comprises:
and taking the topographic data and the initial meteorological data in different first time periods as input parameters of a mesoscale model to obtain the historical meteorological data in different first time periods.
Optionally, the method further comprises:
changing an initial field of the air quality model at intervals of a preset time period; the preset duration is less than the duration of the second time period.
According to a second aspect of embodiments of the present disclosure, there is provided a pollution weather condition prediction apparatus, comprising:
the first prediction module is configured to take historical meteorological data of a plurality of different first time periods and a fixed pollution source emission list as input parameters of an air quality model to obtain first historical pollutant concentrations of the different first time periods;
the second prediction module is configured to take the first historical pollutant concentrations in different first time periods as input parameters of a statistical prediction model to obtain future pollutant concentrations in different first time periods; the statistical prediction model is used for predicting and obtaining the future pollutant concentration according to the historical pollutant concentration;
a rate of change of identity determination module configured to derive a rate of change of identity from the first historical contaminant concentration and the future contaminant concentration, the rate of change of identity being indicative of future meteorological data affecting the future contaminant concentration, the identity affecting a specific value of historical meteorological data preference or deviation of the first historical contaminant concentration.
According to a third aspect of embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method for predicting a contaminated weather condition provided by the first aspect of embodiments of the present disclosure.
According to a fourth aspect of embodiments of the present disclosure, there is provided an electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method for predicting pollution weather conditions provided in the first aspect of the embodiment of the disclosure.
According to the technical scheme, the first historical pollutant concentrations in different first time periods are obtained by inputting the historical meteorological data in different first time periods and the fixed pollutant source emission list into the air quality model, and the influence of the pollutant source emission list on the first historical pollutant concentrations is eliminated because the historical meteorological data input into the air quality model is changed and the pollutant source emission list is unchanged, so that the influence of the change of the historical meteorological data on the first historical pollutant concentrations is obtained, and the problem that the influence of the historical meteorological data on the first historical pollutant concentrations cannot be separated by the statistical forecasting model is solved.
The first historical pollutant concentration output by the air quality model is input into the statistical prediction model to predict the future pollutant concentration, the statistical prediction model predicts the future pollutant concentration according to the first historical pollutant concentration of the time sequence instead of predicting the future pollutant concentration according to the pollutant concentration of the last time period based on the characteristics of the statistical prediction model, the accuracy of predicting the future pollutant concentration is higher, and the problem of error accumulation caused by predicting the future pollutant concentration by adopting the pollutant concentration of the last time period does not exist.
Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification, illustrate the disclosure and together with the description serve to explain, but do not limit the disclosure. In the drawings:
FIG. 1 is a flowchart illustrating steps of a method for predicting pollution weather conditions, according to an exemplary embodiment.
Fig. 2 is a schematic diagram of error accumulation over time, according to an example embodiment.
FIG. 3 is a block diagram of a pollution weather condition prediction device, according to an example embodiment.
Fig. 4 is a block diagram of an electronic device according to an exemplary embodiment.
Fig. 5 is a block diagram of an electronic device according to an exemplary embodiment.
Detailed Description
Specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the disclosure, are not intended to limit the disclosure.
It should be noted that, all actions for acquiring signals, information or data in the present disclosure are performed under the condition of conforming to the corresponding data protection rule policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.
In order to obtain future contaminant concentrations, the applicant has considered several schemes below, but all of which suffer from certain drawbacks.
For example, for scheme 1, a statistical prediction model is established according to the weather data and the pollutant emission amount, and then the pollutant concentration is predicted by the statistical prediction model, however, the statistical prediction model established by the weather data and the pollutant emission amount reflects the future pollutant concentration obtained by the combined action of the weather data and the pollutant emission amount, i.e. the statistical prediction model can only reflect the influence of the combined change of the weather data and the pollutant emission amount on the future pollutant concentration, and the statistical prediction model cannot solely reflect the influence of the weather data on the future pollutant concentration.
For example, for scheme 2, the regional climate mode can be used to simulate historical meteorological data, and key historical meteorological data affecting the concentration of pollutants in the historical meteorological data can be extracted; predicting future meteorological data by using a meteorological model, and extracting key future meteorological data affecting the concentration of pollutants in the future meteorological data; finally, the future meteorological data and the historical meteorological data are compared, and the future meteorological data is judged to be more favorable, even or unfavorable compared with the historical meteorological data.
The meteorological data include temperature, air pressure, relative humidity, wind speed, precipitation, boundary layer height, illumination intensity, and the like. In general, for particulate matters, the future air temperature is higher than the historical air temperature, the future wind speed is smaller than the historical wind speed, and the future air pressure is lower than the historical air pressure, so that the potential force of cold air is weaker, the atmospheric level diffusion condition is poor, and the future meteorological data is more unfavorable than the historical meteorological data; the future humidity is higher than the historical humidity, which indicates that the moisture absorption and growth of the particulate matters are facilitated, the generation of pollutants is facilitated, and the future meteorological data is more unfavorable than the historical meteorological data; the future precipitation amount is less than the historical precipitation amount, so that pollutant settlement is not facilitated, and the future meteorological data is more unfavorable than the historical meteorological data; the future boundary layer height is lower than the historical boundary layer height, so that the range in which the particulate matters can diffuse is smaller, the concentration of the particulate matters is higher, and the future meteorological data is more unfavorable than the historical meteorological data.
However, in this scheme 2, only future weather data can be analyzed more favorably than historical weather data, either on average or more unfavorably, which cannot quantitatively analyze specific values of future weather data versus historical weather data preferences or deviations.
In order to quantitatively analyze the values of preference or deviation of future meteorological data and historical meteorological data, scheme 3 can be considered, and the historical meteorological data and a pollution source emission list can be input into an air quality model to obtain historical pollutant concentration; inputting future meteorological data and a pollution source emission list into an air quality model to obtain the concentration of the future pollutants; and finally, obtaining specific values of preference or deviation of future meteorological data and historical meteorological data according to the rising rate or the falling rate of the future pollutant concentration and the historical pollutant concentration. If the future contaminant concentration is less than the historical contaminant concentration, the future weather data is more favorable than the historical weather data; if the future contaminant concentration is greater than the historical contaminant concentration, the future weather data is less favorable than the historical weather data.
However, the atmosphere is a nonlinear power system which is very sensitive to the initial value of the pollutant concentration, the air quality model predicts the pollutant concentration in the next time period according to the pollutant concentration in the previous time period and the meteorological data in the next time period, so that a small error between the initial value of the predicted pollutant concentration and the initial value of the real pollutant concentration is increased continuously along with the lengthening of the integration time, and finally, a large deviation exists between the predicted pollutant concentration and the real pollutant concentration of the air quality model. For example, referring to fig. 2, the error between the predicted pollutant concentration and the actual pollutant concentration of the air quality model at the reporting time t0 is smaller, and as the integration time of the air quality model is longer, the error is continuously amplified until the time t0+n is reached, the difference between the predicted pollutant concentration and the actual pollutant concentration is very large, and if the pollutant concentration with the larger error is used to obtain the value of preference or deviation of future weather data compared with the historical weather data, the error of the value is also larger.
Based on this, the present disclosure proposes a pollution weather condition prediction method comprising the steps of:
in step S11, a plurality of historical meteorological data and a fixed pollutant source emission list of different first time periods are used as input parameters of an air quality model, so as to obtain first historical pollutant concentrations of different first time periods.
The first time period may be year, quarter, month, etc.
The historical meteorological data includes: historical temperature, historical barometric pressure, historical relative humidity, historical wind speed, historical precipitation, historical boundary layer height, historical illumination intensity, and the like.
The pollutant source emission list refers to pollutant emission amounts of all pollutant sources in a target area, and the pollutant source emission list is obtained by performing gridding treatment and then inputting the pollutant source emission list into an air quality model for simulation.
And generating a grid emission list according to the multi-scale emission list in the first time period, and obtaining a pollution source emission list in the first time period. The multi-scale emissions list is an emissions list of each region in a different first time period nationwide, taking 2022 as an example, and the region is provincial, and the multi-scale emissions list may be an emissions list of each region in 2022 nationwide; the grid emission list is a multi-scale emission list that is grid-formed, each simulation grid being used to indicate the pollutant emissions from one pollutant source.
Generating a grid emission list according to the multi-scale emission list in the first time period, and obtaining a pollution source emission list in the first time period, wherein the grid emission list comprises the following steps: gridding the multi-scale emission list in the first time period to obtain a gridded emission list; and screening a pollution source emission list of the target area from the multi-scale emission list of the first time period. For example, taking the example that the first time period is 2022 and the area is province, the multi-scale emission list may be an emission list of 2022 in each province nationwide, and the province a may be selected from the multi-scale emission list, so as to obtain a pollution source emission list of 2022 in province a.
The air quality model may be a three-generation air quality model, and for a first historical pollutant concentration in a first time period, the air quality model may simulate to obtain the historical pollutant concentration in a next time period according to the historical pollutant concentration in the previous time period and the historical meteorological data in the next time period.
When the first time period is years, the fixed pollution source emission list refers to the pollution source emission list used in different years, which is the same emission list and does not change with the change of the years.
For example, historical meteorological data and fixed pollutant source emissions listings for different years from 1963 to 2022 may be respectively input into the air quality model, resulting in first historical pollutant concentrations from 1963 to 2022, respectively.
In step S12, the first historical contaminant concentrations in different first time periods are used as input parameters of a statistical prediction model, so as to obtain future contaminant concentrations.
The statistical prediction model is used for predicting future pollutant concentration according to the change trend of the historical pollutant concentration along with the time sequence, but does not predict the future pollutant concentration of the next time period according to the historical pollutant concentration of the previous time period, and is a differential autoregressive moving average model (ARIMA).
For example, the statistical prediction model may predict the future contaminant concentration of 2023 based on the first historical contaminant concentrations of 1963 through 2022; likewise, the statistical prediction model may also predict the future contaminant concentration in 2024 based on the first historical contaminant concentrations in 1963 through 2022, which does not predict the contaminant concentration in 2024 based on the contaminant concentration in 2023; likewise, the statistical prediction model may also predict the future contaminant concentration in 2025 based on the first historical contaminant concentrations in 1963 through 2022, which does not predict the contaminant concentration in 2025 based on the contaminant concentration in 2024.
It can be seen that the statistical prediction model predicts the future contaminant concentration according to the first historical contaminant concentration that varies with time sequence over a period of time, rather than predicting the future contaminant concentration in the next period according to the historical contaminant concentration in the previous period, so that the problem of error accumulation caused by using the historical contaminant concentration in the previous period to predict the future contaminant concentration in the next period in the above scheme 3 can be avoided.
In step S13, a ratio of change rates representing future meteorological data affecting the future contaminant concentration to specific values of historical meteorological data preference or deviation affecting the first historical contaminant concentration is obtained according to the first historical contaminant concentration and the future contaminant concentration.
The prediction of the pollution weather condition may be regarded as a quantitative prediction of the preference or deviation of the future weather data to the historical weather data, i.e. the rate of change of the future weather data to the historical weather data to the same ratio. For example, future meteorological data affecting future contaminant concentrations in the future 2024, and historical meteorological data comparing first historical contaminant concentrations in the year 2020 to historical specific values of preference or deviation.
The first historical contaminant concentration may be subtracted from the future contaminant concentration to obtain a contaminant concentration difference, and the contaminant concentration difference divided by the first historical contaminant concentration to obtain a rate of change of the pollution weather conditions.
For example, the equation for the rate of change of the year 2024 from the year 1963 is as follows:
η 1 =(T 2024 -M 1963 )/M 1963
wherein η1 is the rate of change of the same ratio of the future pollutant concentration due to the future meteorological data change of 2024 to the first historical pollutant concentration of 1963, T 2024 The future pollutant concentration of 2024 output for the statistical forecasting model; m is M 1963 Representing the air quality model output 1963 of a first historical contaminant concentration. A positive value of η1 indicates that future weather data is comparably worse than historical weather data and a negative value indicates that future weather data is comparably better than historical weather data.
As another example, 2023 is calculated as follows with respect to the three year homonymous change of the history of 2020-2022:
wherein M is 2020 、M 2021 、M 2022 First historical pollutant concentrations, T, of 2020 to 2022 respectively output for air quality models 2023 The statistical prediction model outputs 2023 future contaminant concentrations. η1 is positive, which means that future meteorological data of 2023 is unfavorable compared with historical meteorological data of three years, namely pollution meteorological conditions are worse; η1 is negative, meaning that future weather data of 2023 is advantageous over historical weather data of three years in history, i.e. pollution weather conditions are better.
Through the technical scheme, the historical meteorological data of different first time periods and the fixed pollution source emission list are input into the air quality model to obtain the first historical pollutant concentrations of the different first time periods, so that the historical meteorological data input into the air quality model are changed, the pollution source emission list is unchanged, the influence of the pollution source emission list on the first historical pollutant concentrations is eliminated, the influence of the change of the historical meteorological data on the first historical pollutant concentrations is obtained, and the problem that the influence of the historical meteorological data on the first historical pollutant concentrations cannot be separated by the statistical forecasting model is solved.
The first historical pollutant concentration output by the air quality model is input into the statistical prediction model to predict the future pollutant concentration, the statistical prediction model predicts the future pollutant concentration according to the first historical pollutant concentration of the time sequence instead of predicting the future pollutant concentration according to the pollutant concentration of the last time period based on the characteristics of the statistical prediction model, the accuracy of predicting the future pollutant concentration is higher, and the problem of error accumulation caused by predicting the future pollutant concentration by adopting the pollutant concentration of the last time period does not exist. Naturally, on the basis of the accuracy of the obtained future pollutant concentration, the same-ratio change rate obtained based on the accurate future pollutant concentration can also be more accurate, and the same-ratio change rate can accurately and quantitatively represent the degree of preference or deviation of the pollution meteorological conditions.
A specific embodiment of the step S12 is described below, and this embodiment is used to explain that the statistical prediction model may obtain a more refined future pollutant concentration according to the first historical pollutant concentration in the same second time period in different first time periods.
When the statistical prediction model is built, because the weather data of different second time periods in the same first time period have larger differences, if the future pollutant concentration is predicted only according to the first historical pollutant concentrations of different first time periods, the obtained future pollutant concentration cannot reflect the differences generated by the weather data of different second time periods. For example, if the first time period is year and the second time period is month, if the future pollutant concentration of 2023 is predicted only according to the first historical pollutant concentration of 1963 to 2022, the predicted pollutant concentration of 2023 cannot represent the pollutant concentration difference caused by the 1 month to 12 China rose type change of 2023, and only represents the future pollutant concentration of 2023 as a whole.
Based on this, the disclosure may further use, as an input parameter of a statistical prediction model corresponding to the second time period, a second historical contaminant concentration belonging to the same second time period in the first historical contaminant concentrations of different first time periods, to obtain future contaminant concentrations corresponding to different second time periods.
The time range of the second time period is smaller than the time range of the first time period. For example, if the first time period is year, the corresponding second time period is month; if the first time period is a quarter, the corresponding second time period is a month.
For example, taking the first time period as year and the second time period as month as an example, 1 month of all years from 1963 to 2022 may be arranged in chronological order, for example, in chronological order of 1 month of 1963, 1 month of 1964, and 1 month of 1965, …, 2022, to obtain the second historical contaminant concentration of the time series, and 2 months of all years from 1963 to 2022 may be arranged in chronological order, for example, in chronological order of 2 months of 1963, 2 months of 1964, and …, 2022, to obtain the second historical contaminant concentration of the time series, and the subsequent 3 months to 12 months may be equally divided.
Taking 1 month from 1963 to 2022 as an example of the time-series second historical contaminant concentration, the future contaminant concentration of 1 month from 2023 can be obtained by taking the second historical contaminant concentration of 1 month from 1963 to 2022 as an input parameter of a statistical prediction model; taking 2 months from 1963 to 2022 as an example of the time-series second historical contaminant concentration, the future contaminant concentration of 2 months from 2023 may be obtained using the second historical contaminant concentration of 2 months from 1963 to 2022 as an input parameter to the statistical prediction model.
All subsequent months are similarly predicted, ultimately resulting in future contaminant concentrations of 2023 for 1 to 12 months each.
Of course, when the statistical prediction model is established, the statistical prediction model corresponding to the second time period can be established by using the second historical pollutant concentrations of the same second time period in different first time periods, so that different statistical prediction models corresponding to different second time periods can be obtained, and then future pollutant concentrations of different second time periods can be predicted by using the statistical prediction models corresponding to different time periods according to the second historical pollutant concentrations of the different second time periods.
For example, a statistical prediction model of 1 month may be established with the second historical contaminant concentration of the 1 month time series of 1963 to 2022, and the future contaminant concentration of 2023, 1 month, may be predicted using the statistical prediction model of 1 month; a statistical prediction model of 2 months may also be built from the second historical contaminant concentration of the 2 month time series from 1963 to 2022, and the future contaminant concentration of 2 months in 2023 may be predicted using the statistical prediction model of 2 months, and each subsequent month may be similar, so that 12 months respectively correspond to the respective statistical prediction model.
By adopting the technical scheme, the first time period is year, the second time period is month, and compared with the case that only the integral future pollutant concentration of 2023 can be obtained, the future pollutant concentration of each month of 2023 from 1 month to 12 months can be further obtained, and the future predicted concentration of 2023 is statistically predicted in months, so that the future pollutant concentration is predicted more finely; and the difference of future pollutant concentrations caused by meteorological data difference of different months is also considered, and the statistical prediction model corresponding to different months is established through the second historical pollutant concentration of the same month in different years, so that the future pollutant concentration of each month is predicted through the statistical prediction model corresponding to each month to be more accurate.
A specific embodiment related to the above step S11 is described below for explaining how to reduce the accumulated error of the air quality model so that the air quality model can output a more accurate second historical contaminant concentration.
In the process that the air quality model obtains the historical pollutant concentration at the next moment through the historical pollutant concentration at the last moment and the historical meteorological data at the next moment, the error between the predicted historical pollutant concentration and the actual historical pollutant concentration can be increased along with the lengthening of the simulation time.
For example, the air quality model predicts that the error between the historical contaminant concentration of 1 month 1 of 1963 and the actual historical contaminant concentration is small, whereas the historical contaminant concentration of 31 month 1 of 1963 predicted by the air quality model accumulates the error of the whole month 1 of 1963 as the simulation time is prolonged, so that the accuracy of the obtained historical contaminant concentration of 31 month 1 of 1963 is poor.
In order to reduce the error between the predicted historical pollutant concentration and the actual historical pollutant concentration, the application can also replace the initial field of the air quality model at intervals of preset time length; the preset duration is less than the duration of the second time period.
The initial field is an initial value of one round of prediction by the air quality model, and each preset duration corresponds to a round of prediction process.
For example, taking a preset duration of three days as an example, if a historical contaminant concentration of 1 month of 2022 is to be obtained, a simulation can be performed by WRF mode using FNL (final analysis data) global re-analysis data, the simulation start time is set to be 2021 at 12 months and 31 days and 18 days, and since the FNL data has four time periods of 0, 6, 12 and 18 days each day, the simulation is started from 18 days to give an adaptive time to the air quality model; the initial field is replaced every three days, the first simulation time is the historical pollutant concentration from 2021, 12 months, 31 days, 18 days to 2022, 1 months, 2 days, 18 days, the second simulation time is the historical pollutant concentration from 2022, 1 months, 2 days, 18 days to 2022, 1 months, 5 days, 18 days, and the cycle is performed, so that the second historical pollutant concentration of 2022, 1 months is obtained. In this example, the initial field is cyclically replaced every three days, and the integrated error accumulated in the initial field is significantly smaller every three days compared to the initial field cyclically replaced every one month, thus resulting in a higher accuracy of the resulting second, different, historical contaminant concentration. That is, each time the initial field is replaced, the previous integration error accumulation is cleared, so that the integration error accumulation is within three days.
After the daily historical pollutant concentration is obtained, the daily historical pollutant concentration in the same month can be added to obtain a second historical pollutant concentration corresponding to the month; after the second historical pollutant concentration of each month is obtained, the second historical pollutant concentrations of different months in the same year can be added to obtain the first historical pollutant concentration corresponding to the year.
It will be appreciated that the reason why a cyclic replacement initiation field may be employed for the prediction of historical contaminant concentrations is: the historical meteorological data represents the actual atmospheric state, and the historical pollutants corresponding to the historical meteorological data at any moment can be used as an initial field, so that the initial field can be circularly replaced to obtain the concentration of the historical pollutants; the future pollutant concentration is reported from the nearest moment, only one moment exists, and a plurality of moments do not exist, so that the initial field cannot be cyclically replaced to obtain the future pollutant concentration.
Through the technical scheme, the simulation time length of each round of air quality model prediction can be reduced, so that the problem of large error accumulation caused by the increase of the simulation time length is solved, and the accuracy of the obtained second historical pollutant concentration can be higher.
A specific embodiment related to the above step S12 is described below, and this embodiment is used to explain how to build a statistical prediction model for a second, different period of time.
And fitting to obtain a statistical prediction model corresponding to the second time period according to the second historical pollutant concentrations of the second time period.
When the statistical prediction model is established, the statistical prediction model can be established by the following steps:
step 1: determining whether the second historical contaminant concentration of the time series would be a stationary sequence, if the second historical contaminant concentration of the time series is a non-stationary sequence, using a differential method to check for outliers in the second historical contaminant concentration of the time series, and after processing the outliers, converting the non-stationary sequence to a stationary sequence.
Wherein if the mean, variance, and covariance of the second historical contaminant concentration of the time series are time-independent constants, i.e., the three are fixed values that do not change over time, then it may be determined that the second historical contaminant concentration of the time series is a stationary series; if any of the above is not satisfied, a second historical contaminant concentration of the time series is determined to be a non-stationary series.
Step 2: fitting to obtain an autoregressive order, a differential order and a moving average order according to the second historical pollutant concentrations in the same second time period in different first time periods; and obtaining a statistical prediction model corresponding to the second time period according to the autoregressive order, the differential order and the moving average order.
The statistical prediction model is an ARIMA model, which includes three parts, namely an autoregressive model (AR), a differential model (I) and a moving average Model (MA).
For the autoregressive model, the autoregressive model is used to predict the second historical contaminant concentration of the second time period immediately preceding the second historical contaminant concentration of the next second time period, for example, the second historical contaminant concentration of 1963 month 1 of the second time period immediately preceding the second historical contaminant concentration of 1 month 1964. The autoregressive model is defined by autoregressive order P values.
The P value represents a dependency relationship between the second historical contaminant concentration of the current second time period and the second historical contaminant concentration of a certain second time period in the past, for example, a dependency relationship between the second historical contaminant concentration of 1 month in 1964 and the second historical contaminant concentration of 1 month in 1963, if the P value is equal to 2; the P value is determined by the ACF map, and the number of truncations in the ACF map can be taken as the P value.
ACF is an autocorrelation coefficient that represents the degree of correlation of the same event between different periods, and can also be understood as measuring the effect of the second historical contaminant concentration of a last second period on the second historical contaminant concentration of a next second period, for example, the effect of the second historical contaminant concentration of 1 month in 1963 on the second historical contaminant concentration of 1 month in 1964.
For the differential model, the differential model is defined by a differential order d value, where d is used to represent the number of differences performed in the differential method that converts the non-stationary sequence to a stationary sequence, and if d is equal to 1, representing a first order difference that may be performed on the second historical contaminant concentration of the time sequence, the non-stationary sequence may be converted to a stationary sequence.
For the moving average model, the moving average model defines an error accumulation of the second historical contaminant concentration for all previous second time periods when the second historical contaminant concentration for the next second time period is predicted, for example, the moving average model defines an effect of error accumulation of the second historical contaminant concentration for 1 month of previous 1963 to 2021 when the second historical contaminant concentration for 1 month of 2022 is predicted, for example, the second historical contaminant concentration for 1 month of 2022 is influenced. The moving average model is defined by a moving average order q value.
The q value represents the dependency between the second historical contaminant concentration for the current second time period and the error for some second time period in the past, e.g., the q value represents the dependency between the second historical contaminant concentration for 1 month 2022 and the error accumulated in 1 month 2000 in the past. The q value is determined by the PACF map, and the number of truncations in the PACF map is taken as the q value.
The PACF is an autocorrelation coefficient for calculating the degree of influence of one element on another element, and is a constant for other elements, irrespective of the influence of other elements on another element.
After the autoregressive order P, the differential order d and the moving average order q are obtained, three models, namely an autoregressive model (AR), a differential model (I) and a moving average Model (MA), are respectively obtained, and form a statistical prediction model.
(3) Checking the statistical prediction model, wherein the success of the checking comprises the following conditions:
condition a: the residual sequence of the statistical prediction model is close to 0, i.e. the difference sequence between the second historical pollutant concentration predicted by the statistical prediction model and the actual second historical pollutant concentration is close to 0.
Condition B: the variance of the residual sequence of the statistical prediction model remains constant.
Condition C: the residual sequence of the statistical prediction model is a white noise sequence, i.e. the residual sequence has no autocorrelation.
After the statistical prediction model is established, the statistical prediction model may predict the future contaminant concentration of month 1 of 2023 based on the second historical contaminant concentration of month 1 of 1963 to 2022.
An alternative embodiment of the present disclosure is described below to explain how future weather data for future contaminant concentrations may be derived from the future contaminant concentrations and contemporaneous second historical contaminant concentrations, as compared to specific values of historical weather data preferences or deviations affecting the second historical contaminant concentrations, after the future contaminant concentrations are derived.
The rate of change of the same ratio may be derived from the future concentration of the contaminant and the second historical concentration of the contaminant for a second period of time, including: determining a difference between the future contaminant concentration and the second historical contaminant concentration for a second period of time; the ratio between the difference and the future contaminant concentration is taken as the rate of change of the same ratio.
The rate of change of the same ratio is used to quantify a specific value of the preference or deviation of future meteorological data affecting the future concentration of the contaminant as compared to historical meteorological data affecting the second historical concentration of the contaminant. The meaning of the homonymy is a comparison between the same second time periods in different first time periods, such as 1 month in 1963 and 1 month in 2022.
For example, the equation for the rate of change of year 1 of 2023 versus month 1 of 2022 is as follows:
η 1 =(T 2023 -M 2022 )/M 2022
wherein eta 1 is the same ratio of the change rate of the pollutant concentration caused by the change of meteorological data of 1 month 2023 to the pollutant concentration of 2022, T 2023 The concentration of the pollutant of 2023 month 1 output for the statistical forecasting model; m is M 2022 The concentration of contaminants at month 2022, which represents the output of the air quality model. Positive value of η1 represents futureA negative value indicates that future weather data is better compared to historical weather data.
As another example, the formula for year 1 of 2023 versus year 2020-2022 for three year homonymous changes is as follows:
wherein M is 2020 、M 2021 、M 2022 Pollutant concentrations, T, of 2020 to 2022 month 1 respectively output by the air quality model 2023 The statistical prediction model outputs the concentration of the pollutant of 2023 month 1. η1 is positive, which means that future weather data of 1 month of 2023 is unfavorable compared with historical weather data of three years of history, namely weather conditions are poor; η1 is negative, meaning that future weather data for month 1 of 2023 is advantageous over historical weather data for month 1 of three years of history, i.e. weather conditions are better.
According to the technical scheme, the same-ratio change rate can be obtained according to the future pollution concentration and the second historical pollutant concentration in the second time period, and then whether the future meteorological conditions are favorable compared with the historical meteorological conditions or not and the favorable or unfavorable degree can be quantitatively analyzed according to the same-ratio change rate, for example, when the same-ratio change rate is negative and the negative value is larger, the future meteorological conditions are favorable compared with the historical meteorological conditions, and the favorable degree is larger.
An alternative embodiment of the present disclosure is described below for explaining the process of obtaining historical meteorological data for a first period of time.
Obtaining historical meteorological data for a first time includes: and taking the topographic data and the initial meteorological data in a plurality of different first time periods as input parameters of a mesoscale model to obtain the historical meteorological data in different first time periods.
The mesoscale model may be a WRF (Weather Research and Forecasting Model, weather research and forecast model) model that predicts historical meteorological data for a wider area than a smaller scale model.
The initial weather data may be monitored historical weather data, the initial weather data including: meteorological parameters of wind speed and direction, temperature, humidity, air pressure and the like; the historical meteorological data obtained based on the initial meteorological data is a meteorological background field, the historical meteorological data such as rainfall and transport capacity can be obtained through simulation of the initial meteorological data, and the format of the initial meteorological data is not supported by the air quality model, so that the air quality model cannot identify the initial meteorological data, and the initial meteorological data (FNL) can be identified by the air quality model after being simulated through WRF.
Terrain data refers to the geographic location of different areas.
After the historical meteorological data are obtained, the actual monitoring data such as ground monitoring data, sounding data, cloud image data and the like can be utilized to assimilate the historical meteorological data, and the assimilated historical meteorological data can reflect the actual state of the atmosphere in the historical year, so that the more actual historical meteorological data are used for predicting and obtaining the more actual first historical pollutant concentration.
By the technical scheme, the terrain data and the initial meteorological data in a plurality of different first time periods can be used as input parameters of the mesoscale model, and the historical meteorological data in the different first time periods can be obtained. Because the historical meteorological data is obtained through the mesoscale model simulation, compared with the actual monitored historical meteorological data, the quantity of the simulated historical meteorological data is more, the air quality model can simulate the historical pollutant concentration with more quantity according to the historical meteorological data with more quantity, and therefore the model can learn the change trend of the historical pollutant concentration of the time sequence better when the statistical forecasting model is built, and the accurate future pollutant concentration is forecasted.
FIG. 3 is a block diagram of a contaminated weather condition prediction apparatus 300 according to an embodiment, the apparatus 300 comprising: the first prediction module 320, the second prediction module 330, and the rate of change of the same ratio determination module 340.
A first prediction module 320 configured to obtain a first historical contaminant concentration for a plurality of different first time periods using the historical meteorological data for the first time periods and the fixed pollutant source emissions inventory as input parameters for the air quality model;
a second prediction module 330 configured to obtain future contaminant concentrations of different first time periods using the first historical contaminant concentrations of different first time periods as input parameters of a statistical prediction model; the statistical prediction model is used for predicting and obtaining the future pollutant concentration according to the historical pollutant concentration;
a rate of change of identity determination module 340 configured to derive a rate of change of identity from the first historical contaminant concentration and the future contaminant concentration, the rate of change of identity being indicative of future meteorological data affecting the future contaminant concentration, the identity affecting a specific value of historical meteorological data preference or deviation of the first historical contaminant concentration.
Optionally, the second prediction module 330 includes:
the first prediction submodule is configured to obtain future pollutant concentrations corresponding to different second time periods by using second historical pollutant concentrations belonging to the same second time period in the first historical pollutant concentrations of the different first time periods as input parameters of a statistical prediction model corresponding to the second time periods, and the time range of the second time periods is smaller than that of the first time period.
Optionally, the pollution weather condition prediction apparatus 300 includes:
and the fitting module is configured to fit and obtain a statistical prediction model corresponding to the second time period according to the second historical pollutant concentration of the second time period.
Optionally, the fitting module includes:
the order determining submodule is configured to obtain an autoregressive order, a differential order and a moving average order in a fitting mode according to second historical pollutant concentrations in the same second time period in different first time periods;
and the fitting sub-module is configured to obtain a statistical prediction model corresponding to the second time period according to the autoregressive order, the differential order and the moving average order.
Optionally, the rate of change of identity determination module 340:
a homonymous change rate determination sub-module configured to derive the homonymous change rate from a second historical concentration of contaminants belonging to the same second time period in a first historical concentration of contaminants of different ones of the first time periods and a future concentration of contaminants of the second time period, the homonymous change rate being used to represent a specific value of a preference or deviation of future meteorological data affecting the future concentration of contaminants compared to historical meteorological data affecting the second historical concentration of contaminants.
Optionally, the pollution weather condition prediction apparatus 300 includes:
and the third prediction module is configured to take the terrain data and the initial meteorological data of a plurality of different first time periods as input parameters of a mesoscale model to obtain the historical meteorological data of different first time periods.
Optionally, the pollution weather condition prediction apparatus 300 includes:
a replacement module configured to replace an initial field of the air quality model at intervals of a preset duration; the preset duration is less than the duration of the second time period.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
Fig. 4 is a block diagram of an electronic device 400, shown in accordance with an exemplary embodiment. As shown in fig. 4, the electronic device 400 may include: a first processor 401, a first memory 402. The electronic device 400 may also include one or more of a multimedia component 403, a first input/output (I/O) interface 404, and a first communication component 405.
Wherein the first processor 401 is configured to control the overall operation of the electronic device 400 to perform all or part of the steps of the pollution weather condition prediction method described above. The first memory 402 is used to store various types of data to support operation at the electronic device 400, which may include, for example, instructions for any application or method operating on the electronic device 400, as well as application-related data, such as contact data, transceived messages, pictures, audio, video, and the like. The first Memory 402 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia component 403 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the first memory 402 or transmitted through the first communication component 405. The audio assembly further comprises at least one speaker for outputting audio signals. The first input/output interface 404 provides an interface between the first processor 401 and other interface modules, which may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The first communication component 405 is used for wired or wireless communication between the electronic device 400 and other devices. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near Field Communication, NFC for short), 2G, 3G, 4G, NB-IOT, eMTC, or other 4G, etc., or one or a combination of several thereof, is not limited herein. The corresponding first communication component 405 may thus comprise: wi-Fi module, bluetooth module, NFC module, etc.
In an exemplary embodiment, the electronic device 400 may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, ASIC), digital signal processor (Digital Signal Processor, DSP), digital signal processing device (Digital Signal Processing Device, DSPD), programmable logic device (Programmable Logic Device, PLD), field programmable gate array (Field Programmable Gate Array, FPGA), controller, microcontroller, microprocessor, or other electronic components for performing the pollution weather condition prediction method described above.
In another exemplary embodiment, a computer readable storage medium is also provided that includes program instructions that, when executed by the first processor, implement the steps of the pollution weather condition prediction method described above. For example, the computer readable storage medium may be the first memory 402 including program instructions described above that are executable by the first processor 401 of the electronic device 400 to perform the pollution weather condition prediction method described above.
Fig. 5 is a block diagram of an electronic device 500, according to an example embodiment. For example, electronic device 500 may be provided as a server. Referring to fig. 5, the electronic device 500 includes a second processor 522, which may be one or more in number, and a second memory 532 for storing computer programs executable by the second processor 522. The computer program stored in the second memory 532 may include one or more modules each corresponding to a set of instructions. Further, the second processor 522 may be configured to execute the computer program to perform the pollution weather condition prediction method described above.
In addition, the electronic device 500 may further include a power supply component 525 and a second communication component 550, the power supply component 525 may be configured to perform power management of the electronic device 500, and the second communication component 550 may be configured to enable communication of the electronic device 500, e.g., wired or wireless communication. In addition, the electronic device 500 may also include a second input/output (I/O) interface 558. The electronic device 500 may operate based on an operating system stored in the second memory 532.
In another exemplary embodiment, a computer readable storage medium is also provided that includes program instructions that, when executed by the second processor 522, implement the steps of the pollution weather condition prediction method described above. For example, the non-transitory computer readable storage medium may be the second memory 532 described above that includes program instructions executable by the second processor 522 of the electronic device 500 to perform the pollution weather condition prediction method described above.
In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable apparatus, the computer program having code portions for performing the above-described pollution weather condition prediction method when executed by the programmable apparatus.
The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solutions of the present disclosure within the scope of the technical concept of the present disclosure, and all the simple modifications belong to the protection scope of the present disclosure.
In addition, the specific features described in the foregoing embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, the present disclosure does not further describe various possible combinations.
Moreover, any combination between the various embodiments of the present disclosure is possible as long as it does not depart from the spirit of the present disclosure, which should also be construed as the disclosure of the present disclosure.
Claims (10)
1. A method for predicting pollution weather conditions, comprising:
taking historical meteorological data of a plurality of different first time periods and a fixed pollution source emission list as input parameters of an air quality model to obtain first historical pollutant concentrations of different first time periods; the pollution source emission list is pollutant emission amounts of pollution sources in a target area;
Taking the first historical pollutant concentrations in different first time periods as input parameters of a statistical prediction model to obtain future pollutant concentrations; the statistical prediction model is used for predicting and obtaining the future pollutant concentration according to the historical pollutant concentration;
and obtaining a same-ratio change rate according to the first historical pollutant concentration and the future pollutant concentration, wherein the same-ratio change rate is used for representing future meteorological data influencing the future pollutant concentration and is used for comparing specific values of historical meteorological data preference or deviation influencing the first historical pollutant concentration.
2. The method of claim 1, wherein the deriving the future contaminant concentration using the first historical contaminant concentrations for different ones of the first time periods as input parameters to a statistical prediction model comprises:
and taking the second historical pollutant concentrations belonging to the same second time period in the first historical pollutant concentrations of different first time periods as input parameters of a statistical prediction model corresponding to the second time period to obtain future pollutant concentrations corresponding to different second time periods, wherein the time range of the second time period is smaller than that of the first time period.
3. The method according to claim 2, wherein the method further comprises:
and fitting according to the second historical pollutant concentrations in different second time periods to obtain statistical prediction models corresponding to the different second time periods.
4. A method according to claim 3, wherein fitting a statistical prediction model corresponding to a different second time period from a second historical contaminant concentration of the different second time period comprises:
fitting to obtain an autoregressive order, a differential order and a moving average order according to the second historical pollutant concentrations in the same second time period in different first time periods;
and obtaining a statistical prediction model corresponding to the second time period according to the autoregressive order, the differential order and the moving average order.
5. The method of claim 2, wherein deriving the rate of change of the same ratio from the first historical contaminant concentration and the future contaminant concentration comprises:
and obtaining the same-ratio change rate according to the second historical pollutant concentration belonging to the same second time period in the first historical pollutant concentrations of different first time periods and the future pollutant concentration of the second time period, wherein the same-ratio change rate is used for representing a specific value of preference or deviation of future meteorological data affecting the future pollutant concentration compared with the historical meteorological data affecting the second historical pollutant concentration.
6. The method according to claim 1, wherein the method further comprises:
and taking the topographic data and the initial meteorological data in different first time periods as input parameters of a mesoscale model to obtain the historical meteorological data in different first time periods.
7. The method according to claim 2, wherein the method further comprises:
changing an initial field of the air quality model at intervals of a preset time period; the preset duration is less than the duration of the second time period.
8. A pollution weather condition prediction device, comprising:
the first prediction module is configured to take historical meteorological data of a plurality of different first time periods and a fixed pollution source emission list as input parameters of an air quality model to obtain first historical pollutant concentrations of the different first time periods; the pollution source emission list is pollutant emission amounts of pollution sources in a target area;
the second prediction module is configured to take the first historical pollutant concentrations in different first time periods as input parameters of a statistical prediction model to obtain future pollutant concentrations in different first time periods; the statistical prediction model is used for predicting and obtaining the future pollutant concentration according to the historical pollutant concentration;
A rate of change of identity determination module configured to derive a rate of change of identity from the first historical contaminant concentration and the future contaminant concentration, the rate of change of identity being indicative of future meteorological data affecting the future contaminant concentration, the identity affecting a specific value of historical meteorological data preference or deviation of the first historical contaminant concentration.
9. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the program when executed by a processor realizes the steps of the method according to any of claims 1-7.
10. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410094388.XA CN117612645B (en) | 2024-01-23 | 2024-01-23 | Pollution weather condition prediction method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410094388.XA CN117612645B (en) | 2024-01-23 | 2024-01-23 | Pollution weather condition prediction method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117612645A CN117612645A (en) | 2024-02-27 |
| CN117612645B true CN117612645B (en) | 2024-04-09 |
Family
ID=89944726
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410094388.XA Active CN117612645B (en) | 2024-01-23 | 2024-01-23 | Pollution weather condition prediction method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117612645B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150031577A (en) * | 2013-09-16 | 2015-03-25 | 주식회사 에니텍 | Method of Inverse Calculation for The Amount of Air Pollutants Emissions |
| AU2019100364A4 (en) * | 2019-04-05 | 2019-05-09 | Shenyuan Huang | A Method of Air Quality Prediction Using Long Short-Term Memory Neural Network |
| CN111626624A (en) * | 2020-05-29 | 2020-09-04 | 四川省环境政策研究与规划院 | Air quality improvement evaluation method |
| CN114819696A (en) * | 2022-05-12 | 2022-07-29 | 中科三清科技有限公司 | Method and device for determining pollutant concentration influence factors and electronic equipment |
| CN116205541A (en) * | 2023-04-27 | 2023-06-02 | 北京英视睿达科技股份有限公司 | Method and device for evaluating influence of local pollution source on environmental air quality |
-
2024
- 2024-01-23 CN CN202410094388.XA patent/CN117612645B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150031577A (en) * | 2013-09-16 | 2015-03-25 | 주식회사 에니텍 | Method of Inverse Calculation for The Amount of Air Pollutants Emissions |
| AU2019100364A4 (en) * | 2019-04-05 | 2019-05-09 | Shenyuan Huang | A Method of Air Quality Prediction Using Long Short-Term Memory Neural Network |
| CN111626624A (en) * | 2020-05-29 | 2020-09-04 | 四川省环境政策研究与规划院 | Air quality improvement evaluation method |
| CN114819696A (en) * | 2022-05-12 | 2022-07-29 | 中科三清科技有限公司 | Method and device for determining pollutant concentration influence factors and electronic equipment |
| CN116205541A (en) * | 2023-04-27 | 2023-06-02 | 北京英视睿达科技股份有限公司 | Method and device for evaluating influence of local pollution source on environmental air quality |
Non-Patent Citations (1)
| Title |
|---|
| 段耀勇等主编.《文科应用数学》.西南交通大学出版社,2021,(第1版),169-174,198-199. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117612645A (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chang et al. | An LSTM-based aggregated model for air pollution forecasting | |
| Maraun et al. | Statistical downscaling and bias correction for climate research | |
| Arhami et al. | Predicting hourly air pollutant levels using artificial neural networks coupled with uncertainty analysis by Monte Carlo simulations | |
| CN112766549A (en) | Air pollutant concentration forecasting method and device and storage medium | |
| Ghaemi et al. | LaSVM-based big data learning system for dynamic prediction of air pollution in Tehran | |
| CN116227749B (en) | Method and device for determining pollutant emission amount, storage medium and electronic equipment | |
| CN109116444B (en) | PCA-kNN-based air quality model PM2.5Forecasting method | |
| WO2015159101A1 (en) | A method and system for analysing environmental data | |
| Aznarte | Probabilistic forecasting for extreme NO2 pollution episodes | |
| CN110705115A (en) | Meteorological forecasting method and system based on deep belief network | |
| CN117871790B (en) | Roadside monitoring station data analysis and traffic tracing method based on multiple data fusion | |
| CN116013426A (en) | Site ozone concentration prediction method with high space-time resolution | |
| CN116611547A (en) | Atmospheric pollutant source forecasting method, device, equipment and storage medium | |
| Can et al. | CENSE Project: general overview | |
| CN117612645B (en) | Pollution weather condition prediction method and device, storage medium and electronic equipment | |
| Agarwal et al. | Forecasting PM2. 5 concentrations using statistical modeling for Bengaluru and Delhi regions | |
| Kim et al. | Using the National Digital Forecast Database for model-based building controls | |
| CN115482930A (en) | Numerical forecasting method, system and storage medium for influence of ozone pollution on human health | |
| CN115238245B (en) | Pollutant monitoring method and device, storage medium and electronic equipment | |
| CN114741976B (en) | Displacement prediction method, device and equipment and readable storage medium | |
| CN115858506A (en) | Refining environment air cleanliness prediction method and device, electronic equipment and storage medium | |
| CN115238596A (en) | Data processing method and device, readable storage medium and electronic equipment | |
| Keppel-Aleks et al. | A functional response metric for the temperature sensitivity of tropical ecosystems | |
| CN116739191B (en) | Hot spot grid identification method and device, storage medium and electronic equipment | |
| CN117252489B (en) | Ozone pollution source evaluation method, device, medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |