CN113418841B - Completion method for air quality particulate matter concentration prediction data - Google Patents
Completion method for air quality particulate matter concentration prediction data Download PDFInfo
- Publication number
- CN113418841B CN113418841B CN202110695552.9A CN202110695552A CN113418841B CN 113418841 B CN113418841 B CN 113418841B CN 202110695552 A CN202110695552 A CN 202110695552A CN 113418841 B CN113418841 B CN 113418841B
- Authority
- CN
- China
- Prior art keywords
- data
- particulate matter
- future
- matter concentration
- day
- 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
- 239000013618 particulate matter Substances 0.000 title claims abstract description 105
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000001502 supplementing effect Effects 0.000 claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims description 24
- 230000007787 long-term memory Effects 0.000 claims description 19
- 230000006403 short-term memory Effects 0.000 claims description 19
- 239000002245 particle Substances 0.000 claims description 10
- 230000005855 radiation Effects 0.000 claims description 8
- 238000000462 isostatic pressing Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 2
- 239000000443 aerosol Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
Landscapes
- Chemical & Material Sciences (AREA)
- Dispersion Chemistry (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for complementing air quality particulate matter concentration prediction data, which comprises the following steps of: s1, acquiring weather data and atmospheric data of the same day, and pushing future weather data and atmospheric data of a first time length from the same day to the future; s2, writing a plurality of groups of data into a data set; s3, inputting the data set into a particulate matter concentration prediction model to obtain particulate matter concentration prediction data of the first day in the future; s4, writing the particulate matter concentration prediction data of the first day in the future into a data set according to the method in the step S2 to form a new data set; s5, inputting the new data set into a particulate matter concentration prediction model to obtain particulate matter concentration prediction data of the next day in the future; and S6, repeating the steps S4-S5, and supplementing future particulate matter concentration prediction data. The invention can solve the problem that when the concentration of the particulate matters in the air quality is predicted, the prediction result has larger deviation only by directly predicting according to the data of the same day.
Description
Technical Field
The invention relates to the technical field of environmental protection, in particular to a completion method of air quality particulate matter concentration prediction data.
Background
For environmental protection, environmental protection management will predict the air quality. The existing air quality prediction technology predicts the future air quality through the measured data of the past air quality. The current air quality prediction only can store the data of a certain day needing prediction, the prediction accuracy rate of pollutants without an accumulative effect, such as ozone, is higher, but the prediction effect of the pollutants such as pm2.5 and the like is poor. The reason is that the particles have an accumulation effect, so that the particles are not dispersed at present and accumulated up at the next day, so that direct prediction is performed only according to data at the same day, and a prediction result is easy to have large deviation; at present, the accuracy rate of predicting the concentration of particulate matters in the air quality is only 55%.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method for complementing air quality particulate matter concentration prediction data, and aims to solve the technical problem that when the particulate matter concentration in the air quality is predicted in the prior art, the prediction is directly performed only according to the data of the day, and the deviation of the prediction result is large.
The technical scheme adopted by the invention is as follows:
in a first aspect, a method for supplementing predicted air mass particulate matter concentration data is provided, which includes the following steps:
s1, acquiring weather data and atmospheric data of the same day, and pushing future weather data and future atmospheric data of a first time length from the same day to the future;
s2, writing the highest air temperature, the lowest air temperature and the average air temperature of the equipressure surface of the same day, the difference value between the daily average air temperature of the same day and the ground highest air temperature, the ground average air pressure difference value of the second time duration of the same day and the future and the total surface short wave radiation quantity of the same day into a data set according to the meteorological data of the same day and the meteorological data of the future;
writing the highest value, the lowest value and the average value of the particle concentration of the current day, the highest value, the lowest value and the average value of the particle concentration of the first time length in the future, and the highest score, the lowest score and the average score of the air quality index of the first time length in the future into a data set according to the atmospheric data of the current day and the future atmospheric data;
s3, inputting the data set into a particulate matter concentration prediction model to predict the air quality of the future first day, and obtaining particulate matter concentration prediction data of the future first day;
s4, writing the particulate matter concentration prediction data of the first day in the future into a data set according to the method in the step S2 to form a new data set;
s5, inputting the new data set into a particulate matter concentration prediction model to predict the particulate matter concentration of the next day in the future, and obtaining the particulate matter concentration prediction data of the next day in the future;
and S6, repeating the steps S4-S5, and completing future particulate matter concentration prediction data. According to the technical scheme, the beneficial technical effects of the invention are as follows: the future particulate matter concentration data can be predicted and supplemented according to the existing meteorological data and atmospheric data, and the prediction accuracy of the supplemented particulate matter concentration data prediction data can be improved from 55% to 80%.
Further, the particulate matter includes: fine particulate matter PM2.5, respirable particulate matter PM10.
Further, the isostatic pressing surface specifically comprises: a first isostatic pressing surface 850hPa, a second isostatic pressing surface 700hPa, and a third isostatic pressing surface 500 hPa.
Further, the first time period is 72 hours and the second time period is 24 hours.
Further, the particulate matter concentration prediction model comprises a long-term and short-term memory neural network.
Further, the particulate matter concentration prediction model is constructed according to the following steps:
using a data set, taking weather data and atmospheric data of the same day as input of the long-term and short-term memory neural network, taking future weather data and atmospheric data as output of the long-term and short-term memory neural network, training the long-term and short-term memory neural network, and obtaining a particulate matter concentration preliminary prediction long-term and short-term memory neural network;
inputting the weather data and the atmospheric data of the day into a long-term and short-term memory neural network for preliminary prediction of the particulate matter concentration to obtain first prediction data of the future particulate matter concentration;
constructing an original data sequence of a forecasting factor according to the first prediction data of the concentration of the particulate matters in the future;
accumulating the original data sequence to construct a second data sequence;
and establishing a differential equation, and solving the constant of the differential equation by a least square method according to the second data sequence to obtain a particulate matter concentration prediction model. According to the technical scheme, the beneficial technical effects of the invention are as follows: the constructed particle concentration prediction model has a good prediction effect on complex conditions containing uncertain factors, and the required sample data is small.
In a second aspect, an electronic device is provided, comprising:
one or more processors;
storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method for supplementing air mass particulate matter concentration prediction data provided in the first aspect.
In a third aspect, a computer-readable storage medium is provided, in which a computer program is stored, which computer program, when executed by a processor, implements the method for complementing air mass particulate matter concentration prediction data as provided in the first aspect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
FIG. 1 is a flowchart of a method for supplementing predicted data according to embodiment 1 of the present invention;
fig. 2 is a flowchart of a method for constructing a particulate matter concentration prediction model according to embodiment 1 of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
Example 1
The embodiment provides a method for complementing air quality particulate matter concentration prediction data, which specifically includes the following steps, as shown in fig. 1:
s1, acquiring weather data and atmospheric data of the day, and pushing future weather data and future atmospheric data of a first time length from the day to the future.
The meteorological data are obtained through the meteorological observation station, in the technical scheme, the obtained meteorological data comprise temperature, air pressure and surface short wave radiation, and the above elements can influence the concentration of the particulate matters, for example, the air pressure can influence the aggregation and diffusion of the particulate matters; the ground surface short wave radiation can affect the material in the form of aerosol, and the particles are similar to the aerosol in the atmosphere.
The method comprises the steps that atmospheric data are obtained through an environment monitoring station, in the technical scheme, the obtained atmospheric data comprise fine particulate matter PM2.5, inhalable particulate matter PM10 and an air quality index IAQI obtained through calculation of actually measured data of environment monitoring.
In a specific embodiment, the current day refers to any day, such as 6 months and 1 day. The first time length is preferably 72 hours, and is 72 hours from the current day to the future, namely, the meteorological data and the atmospheric data of 6 month 2 days, 6 month 3 days and 6 month 4 days, and the meteorological data and the atmospheric data of 6 month 2 days, 6 month 3 days and 6 month 4 days are the existing prediction data and can be obtained through data disclosed by a meteorological department and an environmental protection department.
S2, writing the highest air temperature, the lowest air temperature and the average air temperature of the equipressure surface of the same day, the difference value between the daily average air temperature of the same day and the ground highest air temperature, the ground average air pressure difference value of the second time duration of the same day and the future and the total surface short wave radiation quantity of the same day into a data set according to the meteorological data of the same day and the meteorological data of the future;
and writing the highest value, the lowest value and the average value of the particulate matter concentration 24 hours the day, the highest value, the lowest value and the average value of the particulate matter concentration for the first time length in the future, and the highest score, the lowest score and the average score of the air quality score index for the first time length in the future into a data set according to the atmospheric data and the future atmospheric data of the day.
Various data are written into the data set, specifically as follows:
(1) The highest air temperature, the lowest air temperature and the average air temperature of the same-pressure surface in the same day
Because of the temperature variation of the altitude position that the isobaric surface corresponds, can produce the air current velocity of flow change, and then can influence the reservation of particulate matter, the air current velocity of flow is big more, and the particulate matter dissipates to be fast more. In a specific embodiment, the first isopotential surface is selected to be a 850hPa isopotential surface, the second isopotential surface is selected to be a 700hPa isopotential surface, and the third isopotential surface is selected to be a 500hPa isopotential surface.
Reading the highest air temperature and the lowest air temperature corresponding to the first equal-pressure surface, the highest air temperature and the lowest air temperature corresponding to the second equal-pressure surface, and the highest air temperature and the lowest air temperature corresponding to the third equal-pressure surface within 24 hours of the day according to meteorological data of the day; and calculating the average air temperature corresponding to each equal-pressure surface according to the highest air temperature and the lowest air temperature. The 3 groups of the highest air temperature, the lowest air temperature and the average air temperature are written into the data set.
(2) Difference between average air temperature and highest air temperature on ground
And reading the daily average air temperature and the ground highest air temperature of the current day according to the meteorological data of the current day, calculating the difference value between the daily average air temperature and the ground highest air temperature, and writing the difference value into a data set.
(3) Average air pressure difference value of ground of the second time length of the day and the future
In a specific embodiment, the second time period is 24 hours, the ground average air pressure of the day and the ground average air pressure of 24 hours in the future of the day before the day are read according to the weather data of the day and the weather data of the future, the ground average air pressure difference value of the day and the ground average air pressure difference value of 24 hours in the future are calculated, and the difference value is written into the data set. The meteorological data of 72 hours in the future of the first time length read in step S1 includes meteorological data of the ground average air pressure of 24 hours in the future of the second time length.
(4) Total amount of surface short wave radiation of the day
And calculating the total surface short wave radiation amount of the current day according to the current day meteorological data, and writing the total surface short wave radiation amount of the current day into a data set.
(5) Particulate matter concentration 24 hours a day
And reading the highest value and the lowest value of the particulate matter concentration 24 hours of the day according to the atmospheric data of the day, calculating the average value of the particulate matter concentration 24 hours of the day according to the highest value and the lowest value, and writing the highest value, the lowest value and the average value of the particulate matter concentration 24 hours of the day into a data set. The particulate matter includes fine particulate matter PM2.5, inhalable particulate matter PM10.
(6) Future first time duration particulate matter concentration
In a specific embodiment, the first time period is 72 hours, the highest value and the lowest value of the particulate matter concentration in the future 72 hours are read according to atmospheric data estimated from the day to the future for 72 hours, the average value of the particulate matter concentration in the future 72 hours is calculated according to the highest value and the lowest value, and the highest value, the lowest value and the average value of the particulate matter concentration in the future 72 hours are written into the data set. The particulate matter includes fine particulate matter PM2.5, inhalable particulate matter PM10.
(7) Highest score, lowest score and average score of future first time-length air quality score
In a specific embodiment, the first duration is 72 hours, the air quality score of 72 hours in the future is read according to the atmospheric data pushed 72 hours in the future from the current day, the highest score and the lowest score of the air quality score of 72 hours in the future are obtained, the average score of the air quality score of 72 hours in the future is calculated according to the highest score and the lowest score of the air quality score of 72 hours in the future, and the highest score, the lowest score and the average score of the air quality score of 72 hours in the future are written into the data set.
In this step, the weather data and the atmospheric data of the day, the future weather data and the atmospheric data are read, and the data of a time period of 24 hours from the zero point of the day is taken as the data of the day.
And S3, inputting the data set into a particulate matter concentration prediction model to predict the air quality of the first day in the future, and obtaining the particulate matter concentration prediction data of the first day in the future.
In a specific embodiment, as shown in fig. 2: the modeling process of the particulate matter concentration prediction model is as follows:
1. and using the data set, taking the weather data and the atmospheric data of the same day as the input of the long-term and short-term memory neural network, taking the future weather data and the future atmospheric data as the output of the long-term and short-term memory neural network, training the long-term and short-term memory neural network, and obtaining the preliminary prediction long-term and short-term memory neural network of the particulate matter concentration.
In a specific embodiment, the data set is divided into a training set and a verification set, an LSTM neural network (long-short term memory neural network) is selected, the LSTM neural network obtains a current output through a current input and an output at a previous time, and the learning at the current time can be performed by using information learned at the previous time. The LSTM neural network is selected to find the correlation between the weather data of the day and the future weather data and the correlation between the weather data of the day and the future atmosphere data. And (4) obtaining a preliminary prediction long-term and short-term memory neural network of the concentration of the particulate matters through training. The method of training the neural network is performed using any one of the methods available in the art.
2. Inputting the weather data and the atmospheric data of the day into a long-term and short-term memory neural network for preliminary prediction of the particulate matter concentration to obtain first prediction data of the future particulate matter concentration
Weather data and atmospheric data of a certain day are input into the long-term and short-term memory neural network for preliminary prediction of particulate matter concentration, and first prediction data of the future particulate matter concentration of the certain day can be obtained. The first prediction data of the particulate matter concentration obtained in the step is different from future atmospheric data disclosed by an environmental protection department in data concentration because meteorological data and atmospheric data are introduced at the same time.
The first prediction data of the particulate matter concentration obtained by the step has more uncertain factors, and because the part of training data of the long-term and short-term memory neural network for preliminary prediction of the particulate matter concentration is prediction data rather than actual measurement data. In order to eliminate this uncertainty, the following steps are continued to construct a particulate matter concentration prediction model.
3. Constructing an original data sequence of a forecasting factor according to the first prediction data of the concentration of the particulate matters in the future
In this embodiment, the measured particle concentration data x on the day is selected i And the first prediction data x of the particulate matter concentration on the future day of the day i+1 For example, the difference between the measured particle concentration data of day 1 and day 2 is selected as the prediction factor. In a specific embodiment, the number of the prediction factors is preferably 14, and the more sufficient sample size can make the predicted result more accurate. Constructing the raw data sequence of predictors using multiple predictors, e.g., let 14 x i As a predictor, of the original data sequence { x } 1 ,x 2 ,……x n In a particular embodiment, n is preferably 14.
4. Accumulating the original data sequence to construct a second data sequence
The original data sequence is accumulated as follows:
{y 1 ,y 2 ,……y n and each item of y is obtained by the equal weight accumulation of all original data sequences before the moment, so that the constructed second data sequence stores the characteristics of the original data sequence and the relation between the original data sequence and time, and can be suitable for predicting future data.
5. Establishing a differential equation, and solving the constant of the differential equation by a least square method according to the second data sequence to obtain a particulate matter concentration prediction model
In the present embodiment, let the second data sequence satisfy dy/dt + ay = b
In the above equation, y is the second data sequence, t is time, a is a constant coefficient, and b is a constant input number, and the constants a and b can be estimated from the values of the second data sequence by the least square method. After the estimated values of the constants a and b are obtained, the differential equation is converted into an air quality data prediction model, and the particulate matter concentration of a certain day in the future can be predicted by combining the time t.
The particulate matter concentration prediction model constructed by the method has a good prediction effect on complex conditions containing uncertain factors, and the required sample data is small.
And S4, writing the particulate matter concentration prediction data of the first day in the future into a data set according to the method in the step S2 to form a new data set.
The new data set is formed to include the present day particulate matter concentration prediction data and the future first day particulate matter concentration prediction data. In a specific embodiment, since a part of the parameters used in the air quality prediction model includes future meteorological data and future atmospheric data, the obtained current-day particulate matter concentration data is not the current-day particulate matter concentration measured data, but the current-day particulate matter concentration predicted data.
And S5, inputting the new data set into a particulate matter concentration prediction model to predict the particulate matter concentration of the next day in the future, and obtaining the particulate matter concentration prediction data of the next day in the future.
And S6, repeating the steps S4-S5, and supplementing future particulate matter concentration prediction data.
In this step, since the current meteorological data has only the predicted data of 14 days in the future at most, the predicted data of the particulate matter concentration of 14 days in the future can be supplemented in a specific embodiment.
Through the technical scheme that this embodiment provided, can predict and complement future particulate matter concentration data according to current meteorological data, atmospheric data, particulate matter concentration data prediction data after the completion, its prediction accuracy can promote to 80% from 55%.
Example 2
Provided is an electronic device including:
one or more processors;
storage means for storing one or more programs;
when executed by one or more processors, the one or more programs cause the one or more processors to implement the method of supplementing air mass particulate matter concentration prediction data provided in example 1.
Example 3
There is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements the complementing method of the air mass particulate matter concentration prediction data provided in embodiment 1.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (6)
1. A completion method for air quality particulate matter concentration prediction data is characterized by comprising the following steps:
s1, acquiring weather data and atmospheric data of the same day, and pushing future weather data and future atmospheric data of a first time length from the same day to the future;
s2, writing the highest air temperature, the lowest air temperature and the average air temperature of the equipressure surface of the same day, the difference value between the daily average air temperature of the same day and the ground highest air temperature, the ground average air pressure difference value of the second time duration of the same day and the future and the total surface short wave radiation quantity of the same day into a data set according to the meteorological data of the same day and the meteorological data of the future; the first duration is greater than the second duration;
writing the highest value, the lowest value and the average value of the particle concentration of the current day, the highest value, the lowest value and the average value of the particle concentration of the first time length in the future, and the highest score, the lowest score and the average score of the air quality index of the first time length in the future into a data set according to the atmospheric data of the current day and the future atmospheric data;
s3, inputting the data set into a particulate matter concentration prediction model to predict the air quality of the first day in the future, and obtaining the particulate matter concentration prediction data of the first day in the future;
the particulate matter concentration prediction model is constructed according to the following steps:
using a data set, taking weather data and atmospheric data of the same day as input of the long-term and short-term memory neural network, taking future weather data and atmospheric data as output of the long-term and short-term memory neural network, training the long-term and short-term memory neural network, and obtaining a particulate matter concentration preliminary prediction long-term and short-term memory neural network;
inputting the weather data and the atmospheric data of the day into a long-term and short-term memory neural network for preliminarily predicting the concentration of the particulate matters to obtain first predicted data of the concentration of the particulate matters in the future;
constructing an original data sequence of a forecasting factor according to the first prediction data of the concentration of the particulate matters in the future;
accumulating the original data sequence to construct a second data sequence;
establishing a differential equation, and solving constants of the differential equation through a least square method according to the second data sequence to obtain a particulate matter concentration prediction model;
s4, writing the particulate matter concentration prediction data of the first day in the future into a data set according to the method in the step S2 to form a new data set;
s5, inputting the new data set into a particulate matter concentration prediction model to predict the particulate matter concentration of the next day in the future, and obtaining the particulate matter concentration prediction data of the next day in the future;
and S6, repeating the steps S4-S5, and supplementing future particulate matter concentration prediction data.
2. The method of supplementing air quality particulate matter concentration prediction data according to claim 1, wherein the particulate matter includes: fine particulate matter PM2.5, respirable particulate matter PM10.
3. The method for supplementing air mass particulate matter concentration prediction data according to claim 1, wherein the isobaric surface specifically comprises: a first isostatic pressing surface 850hPa, a second isostatic pressing surface 700hPa, and a third isostatic pressing surface 500 hPa.
4. The method of supplementing air mass particulate matter concentration prediction data according to claim 1, wherein the first time period is 72 hours and the second time period is 24 hours.
5. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of complementing air mass particulate matter concentration prediction data of any one of claims 1-4.
6. A computer-readable storage medium storing a computer program, characterized in that: the computer program, when executed by a processor, implements the method of complementing air mass particulate matter concentration prediction data of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110695552.9A CN113418841B (en) | 2021-06-23 | 2021-06-23 | Completion method for air quality particulate matter concentration prediction data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110695552.9A CN113418841B (en) | 2021-06-23 | 2021-06-23 | Completion method for air quality particulate matter concentration prediction data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113418841A CN113418841A (en) | 2021-09-21 |
| CN113418841B true CN113418841B (en) | 2023-01-31 |
Family
ID=77717566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110695552.9A Active CN113418841B (en) | 2021-06-23 | 2021-06-23 | Completion method for air quality particulate matter concentration prediction data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113418841B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115096374B (en) * | 2022-08-22 | 2022-11-11 | 中工重科智能装备有限责任公司 | Intelligent dust removal prediction compensation method and system in casting |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017020039A1 (en) * | 2015-07-30 | 2017-02-02 | 3Datx Corporation | Particulate calibration and generation simulator for particle measurement and number |
| CN107192645A (en) * | 2016-03-14 | 2017-09-22 | 曹芃 | A kind of multi-rotor unmanned aerial vehicle air pollution detecting system and method |
| CN109543911A (en) * | 2018-11-29 | 2019-03-29 | 中国农业科学院农业信息研究所 | A kind of solar radiation prediction technique and system |
| CN110363347A (en) * | 2019-07-12 | 2019-10-22 | 江苏天长环保科技有限公司 | The method of neural network prediction air quality based on decision tree index |
| CN110738354A (en) * | 2019-09-18 | 2020-01-31 | 北京建筑大学 | Method and device for predicting particulate matter concentration, storage medium and electronic equipment |
| CN110929793A (en) * | 2019-11-27 | 2020-03-27 | 谢国宇 | Time-space domain model modeling method and system for ecological environment monitoring |
| CN110940761A (en) * | 2019-11-26 | 2020-03-31 | 四川省生态环境监测总站 | Method for reducing degradation rate of p, p' -DDT (dichloro-diphenyl-trichloroethane) in organochlorine pesticide analysis process |
| CN112418512A (en) * | 2020-11-19 | 2021-02-26 | 中国环境科学研究院 | Based on PM2.5Air quality prediction method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102338869B (en) * | 2011-06-20 | 2013-06-05 | 北京师范大学 | Inversion method and system of downlink shortwave radiation and photosynthetically active radiation data |
| KR20200056098A (en) * | 2018-11-14 | 2020-05-22 | 한국전자통신연구원 | Method calculating absorbed shortwave radiation and apparatus for the same |
| CN110796284B (en) * | 2019-09-20 | 2022-05-17 | 平安科技（深圳）有限公司 | Method and device for predicting pollution level of fine particulate matters and computer equipment |
| US11170390B2 (en) * | 2020-02-27 | 2021-11-09 | Intercontinental Exchange Holdings, Inc. | Integrated weather graphical user interface |
-
2021
- 2021-06-23 CN CN202110695552.9A patent/CN113418841B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017020039A1 (en) * | 2015-07-30 | 2017-02-02 | 3Datx Corporation | Particulate calibration and generation simulator for particle measurement and number |
| CN107192645A (en) * | 2016-03-14 | 2017-09-22 | 曹芃 | A kind of multi-rotor unmanned aerial vehicle air pollution detecting system and method |
| CN109543911A (en) * | 2018-11-29 | 2019-03-29 | 中国农业科学院农业信息研究所 | A kind of solar radiation prediction technique and system |
| CN110363347A (en) * | 2019-07-12 | 2019-10-22 | 江苏天长环保科技有限公司 | The method of neural network prediction air quality based on decision tree index |
| CN110738354A (en) * | 2019-09-18 | 2020-01-31 | 北京建筑大学 | Method and device for predicting particulate matter concentration, storage medium and electronic equipment |
| CN110940761A (en) * | 2019-11-26 | 2020-03-31 | 四川省生态环境监测总站 | Method for reducing degradation rate of p, p' -DDT (dichloro-diphenyl-trichloroethane) in organochlorine pesticide analysis process |
| CN110929793A (en) * | 2019-11-27 | 2020-03-27 | 谢国宇 | Time-space domain model modeling method and system for ecological environment monitoring |
| CN112418512A (en) * | 2020-11-19 | 2021-02-26 | 中国环境科学研究院 | Based on PM2.5Air quality prediction method |
Non-Patent Citations (4)
| Title |
|---|
| Fusion Method Combining Ground-Level Observations with Chemical Transport Model Predictions Using an Ensemble Deep Learning Framework: Application in China to Estimate Spatiotemporally-Resolved PM2.5 Exposure Fields in 2014–2017;Baolei Lyu 等;《Environ. Sci. Technol》;20190606;第53卷(第13期);第7306-7315页 * |
| Hydrometeorological Drivers of Particulate Matter Using Bayesian Model Averaging;Seulchan Lee 等;《IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium》;20191231;第7634-7637页 * |
| 应用机器学习算法的成都市冬季空气污染预报研究;孙苏琪 等;《气象与环境学报》;20200430;第36卷(第2期);第98-104页 * |
| 济南城市群采暖季大气流场及其对污染物输送影响模拟研究;李厚宇;《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》;20190115(第1期);第B027-132页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113418841A (en) | 2021-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109615226B (en) | Operation index abnormity monitoring method | |
| Zhang et al. | A feature selection and multi-model fusion-based approach of predicting air quality | |
| US20150317589A1 (en) | Forecasting system using machine learning and ensemble methods | |
| Vandal et al. | Quantifying uncertainty in discrete-continuous and skewed data with Bayesian deep learning | |
| CN108230049A (en) | The Forecasting Methodology and system of order | |
| CN111091196B (en) | Passenger flow data determination method and device, computer equipment and storage medium | |
| US20140222228A1 (en) | Forecast System and Method of Electric Power Demand | |
| CN110147902A (en) | A kind of multinomial operation indicator joint method for monitoring abnormality | |
| CN109472283B (en) | Dangerous weather prediction method and device based on multiple incremental regression tree model | |
| Biard et al. | Automated detection of weather fronts using a deep learning neural network | |
| Baran et al. | Joint probabilistic forecasting of wind speed and temperature using Bayesian model averaging | |
| Ashkboos et al. | Ens-10: A dataset for post-processing ensemble weather forecasts | |
| CN113418841B (en) | Completion method for air quality particulate matter concentration prediction data | |
| CN115600717A (en) | Federal learning-based industry-divided power load prediction method, equipment and storage medium | |
| CN112232535A (en) | Flight departure average delay prediction method based on supervised learning | |
| CN110807508B (en) | Bus peak load prediction method considering complex weather influence | |
| CN113449257A (en) | Power distribution network line loss prediction method, control device, and storage medium | |
| Baran et al. | Truncated generalized extreme value distribution‐based ensemble model output statistics model for calibration of wind speed ensemble forecasts | |
| CN115204444A (en) | Photovoltaic power prediction method based on improved cluster analysis and fusion integration algorithm | |
| CN114708007A (en) | Intelligent decomposition method and system for store sales plan | |
| CN115658695A (en) | Intelligent management form generation method based on construction engineering project | |
| Barve et al. | Air quality index forecasting using parallel dense neural network and LSTM cell | |
| CN114692981A (en) | Medium-and-long-term runoff forecasting method and system based on Seq2Seq model | |
| CN116960962A (en) | Mid-long term area load prediction method for cross-area data fusion | |
| Zhang et al. | Extreme wind power forecast error analysis considering its application in day‐ahead reserve capacity planning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |