CN110852493A - Atmospheric PM2.5 concentration prediction method based on multiple model comparisons - Google Patents
Atmospheric PM2.5 concentration prediction method based on multiple model comparisons Download PDFInfo
- Publication number
- CN110852493A CN110852493A CN201911022394.XA CN201911022394A CN110852493A CN 110852493 A CN110852493 A CN 110852493A CN 201911022394 A CN201911022394 A CN 201911022394A CN 110852493 A CN110852493 A CN 110852493A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- atmospheric
- concentration
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 23
- 231100000719 pollutant Toxicity 0.000 claims abstract description 23
- 238000003062 neural network model Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000012417 linear regression Methods 0.000 claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000010200 validation analysis Methods 0.000 claims description 4
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 4
- 230000008707 rearrangement Effects 0.000 description 2
- 238000003916 acid precipitation Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the field of atmospheric pollution prediction model construction, and particularly relates to an atmospheric PM2.5 concentration prediction method based on multiple model comparisons, which comprises the following steps: (1) collecting pollutant concentration data and meteorological data of a target city; (2) preprocessing the acquired pollutant concentration data and meteorological data; (3) respectively constructing a PM 2.5-multivariate linear regression model, a BP neural network model and a time series model aiming at the acquired pollutant concentration data and meteorological data; (4) comparing all parameters of the three models and determining the model with the highest accuracy; (5) and establishing a winter PM2.5-BP neural network model based on seasons.
Description
Technical Field
The invention belongs to the field of atmospheric pollution prediction model construction, and relates to an atmospheric PM2.5 concentration prediction method based on multiple model comparisons.
Background
With the rapid development of the world industry and economy, countries in the world are still making scientific and technical innovations and breakthroughs in production, and meanwhile, various resource and environmental problems are left. In recent years, various atmospheric environmental problems such as greenhouse effect, acid rain and frequent haze have great influence on the atmospheric environment in the world nowadays. In a country with 14 billion population, the gradual deterioration of the atmospheric environment causes various social problems, such as damage to historical cultural relics and buildings, occurrence of various respiratory diseases, infection of epidemic diseases and the like. The Beichen area of Tianjin City, which is located in the area with high atmospheric environmental pollution in China, Jingjin Ji area, also suffers from huge environmental problems, and needs to be solved urgently. At present, the research on the atmospheric pollutants in China has been widely paid attention to by the public and governments, and many atmospheric environment monitoring sites are also established to monitor the data of the atmospheric pollutants in real time, however, the data of the atmospheric pollutants in China is not fully utilized so far. Aiming at the increasingly serious haze condition, an effective PM2.5 prediction system is built at present.
Disclosure of Invention
The invention aims to provide an atmospheric PM2.5 concentration prediction method based on multiple model comparisons, and by using the method, the PM2.5 condition of a target city can be well predicted.
The technical scheme provided by the invention is an atmospheric PM2.5 concentration prediction method based on multiple model comparisons, which comprises the following steps:
(1) collecting concentration data and meteorological data of various atmospheric conventional pollutants of a target city, wherein the atmospheric conventional pollutant data mainly comprises PM2.5 and O3、PM10、SO2、CO、NO2The meteorological data mainly comprises temperature, wind power and weather, and after the data are acquired, the data are processedEstablishing a database;
(2) reading concentration data and meteorological data of various atmospheric conventional pollutants in a target city from a database, and preprocessing the data;
(3) establishing a multivariate linear regression model, a BP neural network model and a time series model for PM2.5 of a target city;
(4) determining an index system for evaluating the performance of each model, and finally determining a model with the highest prediction accuracy in the models through comprehensive comparison of each index;
(5) on the basis of the condition that the PM2.5 is too high in winter possibly occurring in a target city, establishing a winter database and preprocessing data for various atmospheric conventional pollutant concentration data and meteorological data in winter, and establishing a prediction model for the PM2.5 in winter by using the determined model with the highest prediction precision.
In the step (1), the concentration data and meteorological data of various atmospheric conventional pollutants in the target city come from the local environmental protection bureau and meteorological bureau of the target city.
In the step (1), Excel software is used for establishing the database.
In step (2), the preprocessing method for the data of the multiple linear regression model and the time series comprises the steps of using Excel to carry out consistency check on the obtained data, replacing or reasonably processing invalid values and missing values and using normalization to [0, 1]]The method of (3) normalizes the data, and the formula is as follows:to obtain the true predicted value, we can use the formula nextAnd the prediction value required by us is converted back.
In the step (2) of the method, for the data preprocessing of the BP neural network model, the steps of inserting preprocessing function codes into Python to carry out consistency check, replacing invalid values and missing values or reasonably processing the invalid values and missing values and using normalization to [0, 1] are adopted, and meanwhile, random rearrangement is carried out on the data by utilizing a reindex function.
In the step (3), the data used by the method is all atmospheric conventional pollutant concentration data and meteorological data in the time selected by the target city, software SPSS is used for constructing a multiple linear regression model, and a stepwise regression method and a step-by-step regression method F are usedStatistics>FINThe removal conditions of (1).
In the step (3), the time series model is constructed by using the SPSS software, and the ARIMA model with the structure (p, d, q) is adopted.
In the step (3), a BP neural network model is constructed based on Python, and the structure is as follows: each sample (batch size) entered the model was scaled to the training, test and validation sets to 6: 2: 2, adopting a PM2.5-BP neural network structure with a single hidden layer, wherein the structure is 8-4-1, adopting two types of activation functions of ReLU and Purelin in a hidden layer and an output layer of the neural network respectively, and designing the maximum iteration times and the learning rate according to actual conditions.
In the step (4) of the method, the selected evaluation indexes are Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R)2) The formulas are respectively the following formulas, and the evaluation of each model comprehensively considers the numerical value of each index to determine the finally selected model.
In the step (5), the modeling method of the winter PM 2.5-optimal model of the target city is the same as the modeling methods of the three models in the step (5), and the finally used model depends on the finally selected model.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is the comparison statistics of the performance of each index of the three models.
In fig. 3, (a), (b), and (c) are PM2.5 actual measurement-prediction scattergrams when a multiple linear regression model, a BP neural network model, and a time series model are used, respectively.
FIG. 4 is a comparison of indexes of the PM2.5-BP neural network model and the winter PM2.5-BP neural network model.
Detailed Description
The present invention will be described below with reference to specific examples, but the present invention is not limited thereto.
Taking the northen district of Tianjin City as an example for modeling, PM2.5 of the northen district of Tianjin City from 6 months 1 days in 2018 to 5 months 31 days in 2019 is modeled by applying the model.
The concentration data and meteorological data of various atmospheric conventional pollutants are provided by an ecological environment monitoring center in the North-Chen district in Tianjin and a meteorological office website.
1. Data collection and database creation
Collecting concentration data and meteorological data of various atmospheric conventional pollutants in the North-Chen district of Tianjin City, wherein the atmospheric conventional pollutant data mainly comprises PM2.5 and O3、PM10、SO2、CO、NO2The meteorological data mainly comprises temperature, wind power and weather.
After the data are acquired, establishing a database for each item of data by using Excel.
2. Pre-processing of data
Reading from a databaseThe method comprises the steps of obtaining concentration data and meteorological data of various atmospheric conventional pollutants in the north-hour area of Tianjin, and preprocessing the data. Methods of data preprocessing for multiple linear regression models and time series include consistency checking of the resulting data using Excel, substitution or other reasonable processing of invalid and missing values, and use of normalization to [0, 1]]The method of (3) normalizes the data, and the formula is as follows:to obtain the true predicted value, we can use the formula nextAnd the prediction value required by us is converted back.
For data preprocessing of the BP neural network model, steps of inserting preprocessing function codes into Python to carry out consistency check, substituting invalid values and missing values or carrying out other reasonable processing, using normalization to [0, 1], and simultaneously carrying out random rearrangement on data by utilizing a reindex function are adopted.
3. Establishment of prediction model
The data used for the construction of the prediction model is all atmospheric conventional pollutant concentration data and meteorological data from 6 months 1 days in 2018 to 5 months 31 days in 2019 in the North district of Tianjin City, software SPSS is used for constructing a multiple linear regression model, a stepwise regression method and F are usedStatistics>2.71 rejection conditions.
The time series model was also constructed using the SPSS software and the ARIMA model of structure (14,1,1) was used.
A BP neural network model is constructed based on Python, and the structure is as follows: each sample (batch size) entered the model was set to the ratio of training set, test set and validation set as 201: 68: 68, adopting a PM2.5-BP neural network structure with a single hidden layer, wherein the structure is 8-4-1, adopting two types of activation functions of ReLU and Purelin in a hidden layer and an output layer of the neural network respectively, the maximum iteration number is 6000, and the learning rate is 0.005.
4. Evaluating the performance of each model and determining the optimal model
And (3) evaluating indexes of the selected model performance: mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percent Error (MAPE), and coefficient of determination (R)2) And carrying out comparative evaluation on the performances of the models.
As shown in fig. 2, the final BP neural network data are respectively: 124.90, 11.18, 6.6, 16.37 and 0.92, and as shown in fig. 3(a), (b) and (c), the BP neural network scatter diagram is closer to the trend line, so the BP neural network model is selected as the prediction model used at this time and is used for the model used for the later prediction of the PM2.5 in winter. 5. Construction of winter PM2.5-BP neural network prediction model by using BP neural network model
The ratio of training set, test set and validation set was set to 66: 23: 23, adopting a single-hidden layer winter PM2.5-BP neural network structure, wherein the structure is 8-4-1. In a hidden layer and an output layer of a neural network, two types of activation functions, namely ReLU and Purelin, are respectively adopted, and final parameters are set as follows: the maximum number of iterations is 3000 and the learning rate is 0.003.
By contrast, as shown in fig. 4, the indexes of the prediction model constructed for the PM2.5 in winter are generally better than those of the PM2.5-BP neural network model of the whole year, and the Mean Square Error (MSE), the Root Mean Square Error (RMSE), the Mean Absolute Error (MAE), the Mean Absolute Percentage Error (MAPE) and the coefficient of determination (R)2) 125.56, 11.21, 2.49, 11.12, 0.97, respectively.
Claims (7)
1. The atmospheric PM2.5 concentration prediction method based on multiple model comparisons is characterized by comprising the following steps:
(1) collecting concentration data and meteorological data of various atmospheric conventional pollutants of a target city, wherein the atmospheric conventional pollutant data mainly comprises PM2.5 and O3、PM10、SO2、CO、NO2The meteorological data mainly comprise temperature, wind power and weather, and after the data are obtained, a database is established for each data;
(2) reading concentration data and meteorological data of various atmospheric conventional pollutants in a target city from a database, and preprocessing the data;
(3) establishing a multivariate linear regression model, a BP neural network model and a time series model for PM2.5 of a target city;
(4) determining an index system for evaluating the performance of each model, and finally determining a model with the highest prediction accuracy in the models through comprehensive comparison of each index;
(5) on the basis of the condition that the PM2.5 is too high in winter possibly occurring in a target city, establishing a winter database and preprocessing data for various atmospheric conventional pollutant concentration data and meteorological data in winter, and establishing a prediction model for the PM2.5 in winter by using the determined model with the highest prediction precision.
2. The method for predicting the concentration of the atmospheric PM2.5 based on the comparison of multiple models as claimed in claim 1, wherein in the step (1), the concentration data and the meteorological data of the atmospheric conventional pollutants in the target city are obtained from the local environmental protection bureau and the meteorological bureau of the target city, and Excel software is used for establishing the database.
3. The method for predicting the concentration of PM2.5 in the atmosphere based on multiple model comparisons according to claim 1, wherein in the step (2), the method for preprocessing the data of the multiple linear regression model and the time series comprises the steps of using Excel to carry out consistency check on the obtained data, replacing or reasonably processing invalid values and missing values and using normalization to [0, 1]The method of (3) normalizes the data, and the formula is as follows:
4. The method for predicting the concentration of the atmospheric PM2.5 based on multiple model comparisons according to claim 1, wherein in the step (2), the preprocessing of the data of the BP neural network model adopts the steps of inserting a preprocessing function code into Python to perform consistency check, replacing invalid values and missing values or other reasonable processing, and normalizing to [0, 1] and simultaneously randomly rearranging the data by using a reindex function.
5. The atmospheric PM2.5 concentration prediction method based on multiple model comparisons according to claim 1, characterized by: in the step (3), the used data are all atmospheric conventional pollutant concentration data and meteorological data in the time selected by the target city, a software SPSS is used for constructing a multiple linear regression model, and a stepwise regression method and a F are usedStatistics>FINThe removal conditions of (1).
6. The atmospheric PM2.5 concentration prediction method based on multiple model comparisons according to claim 1, characterized by: in the step (3), a time sequence model is constructed by using SPSS software, and an ARIMA model with a structure of (p, d, q) is adopted; a BP neural network model is constructed based on Python, and the structure is as follows: each sample (batch size) entered the model was scaled to the training, test and validation sets to 6: 2: 2, adopting a PM2.5-BP neural network structure with a single hidden layer, wherein the structure is 8-4-1, adopting two types of activation functions of ReLU and Purelin in a hidden layer and an output layer of the neural network respectively, and designing the maximum iteration times and the learning rate according to actual conditions.
7. The atmospheric PM2.5 concentration prediction method based on multiple model comparisons according to claim 1, characterized by: in the step (4), the selected evaluation indexes are Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R)2) The formulas are respectively the following formulas, and the evaluation of each model comprehensively considers the numerical value of each index to determine the finally selected modelType (2):
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911022394.XA CN110852493A (en) | 2019-10-25 | 2019-10-25 | Atmospheric PM2.5 concentration prediction method based on multiple model comparisons |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911022394.XA CN110852493A (en) | 2019-10-25 | 2019-10-25 | Atmospheric PM2.5 concentration prediction method based on multiple model comparisons |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110852493A true CN110852493A (en) | 2020-02-28 |
Family
ID=69597907
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911022394.XA Pending CN110852493A (en) | 2019-10-25 | 2019-10-25 | Atmospheric PM2.5 concentration prediction method based on multiple model comparisons |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110852493A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111289414A (en) * | 2020-03-12 | 2020-06-16 | 徐州工业职业技术学院 | PM2.5 pollution monitoring and predicting method |
CN111489015A (en) * | 2020-03-20 | 2020-08-04 | 天津大学 | Atmosphere O based on multiple model comparison and optimization3Concentration prediction method |
CN111680404A (en) * | 2020-05-25 | 2020-09-18 | 中国科学院城市环境研究所 | Atmospheric element mercury concentration prediction method constructed based on site monitoring data |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106529081A (en) * | 2016-12-03 | 2017-03-22 | 安徽新华学院 | PM2.5 real-time level prediction method and system based on neural net |
CN107300550A (en) * | 2017-06-21 | 2017-10-27 | 南京大学 | A kind of method based on BP neural network model prediction atmosphere heavy metal concentration |
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 |
-
2019
- 2019-10-25 CN CN201911022394.XA patent/CN110852493A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106529081A (en) * | 2016-12-03 | 2017-03-22 | 安徽新华学院 | PM2.5 real-time level prediction method and system based on neural net |
CN107300550A (en) * | 2017-06-21 | 2017-10-27 | 南京大学 | A kind of method based on BP neural network model prediction atmosphere heavy metal concentration |
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 |
Non-Patent Citations (3)
Title |
---|
YILIAO SONG 等: "The forecasting research of early warning systems for atmospheric pollutants: A case in Yangtze River Delta region", 《ATMOSPHERIC ENVIRONMENT》 * |
敖希琴 等: "基于多元时间序列的PM2.5预测方法", 《重庆工商大学学报(自然科学版)》 * |
范剑辉 等: "基于不同的神经网络模型PM2.5浓度预测对比", 《青海环境》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111289414A (en) * | 2020-03-12 | 2020-06-16 | 徐州工业职业技术学院 | PM2.5 pollution monitoring and predicting method |
CN111489015A (en) * | 2020-03-20 | 2020-08-04 | 天津大学 | Atmosphere O based on multiple model comparison and optimization3Concentration prediction method |
CN111680404A (en) * | 2020-05-25 | 2020-09-18 | 中国科学院城市环境研究所 | Atmospheric element mercury concentration prediction method constructed based on site monitoring data |
CN111680404B (en) * | 2020-05-25 | 2022-06-21 | 中国科学院城市环境研究所 | Atmospheric element mercury concentration prediction method constructed based on site monitoring data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109214592B (en) | Multi-model-fused deep learning air quality prediction method | |
CN110363347B (en) | Method for predicting air quality based on neural network of decision tree index | |
CN110852493A (en) | Atmospheric PM2.5 concentration prediction method based on multiple model comparisons | |
CN110766222B (en) | PM2.5 concentration prediction method based on particle swarm parameter optimization and random forest | |
CN106529081A (en) | PM2.5 real-time level prediction method and system based on neural net | |
CN111369057A (en) | Air quality prediction optimization method and system based on deep learning | |
CN111489015A (en) | Atmosphere O based on multiple model comparison and optimization3Concentration prediction method | |
CN112465243A (en) | Air quality forecasting method and system | |
CN111898820B (en) | PM 2.5-hour concentration combination prediction method and system based on trend clustering and integrated tree | |
CN115269675A (en) | Time-space analysis method for atmospheric pollution in industrial park | |
CN106845080B (en) | Based on the modified Scene Tourist meteorological disaster intelligent Forecasting of difference | |
CN108399470B (en) | Indoor PM2.5 prediction method based on multi-example genetic neural network | |
CN112732691A (en) | Atmospheric environment prediction method based on multiple model comparison | |
CN110334438A (en) | A kind of air pollutant emission inventory inversion method and equipment | |
CN113987912A (en) | Pollutant on-line monitoring system based on geographic information | |
CN115829105A (en) | Photovoltaic power prediction method based on historical data feature search | |
CN112348264A (en) | Carbon steel corrosion rate prediction method based on random forest algorithm | |
CN111860974B (en) | Drought multistage prediction method based on state space and joint distribution | |
CN115526298A (en) | High-robustness comprehensive prediction method for concentration of atmospheric pollutants | |
CN113985496B (en) | Storm surge intelligent forecasting method based on LSTM-GM neural network model | |
CN117216480B (en) | Near-surface ozone remote sensing estimation method for deep coupling geographic space-time information | |
CN114741972A (en) | Construction method of seasonal prediction model of air pollutant concentration | |
CN115775042B (en) | Crop heavy metal enrichment risk prediction method and system based on Bayesian theory | |
CN110766219A (en) | Haze prediction method based on BP neural network | |
CN111242369A (en) | PM2.5 data prediction method based on multiple fusion convolution GRU |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200228 |
|
WD01 | Invention patent application deemed withdrawn after publication |