Prediction of Air Pollutant Concentration Based on One-Dimensional Multi-Scale CNN-LSTM Considering Spatial-Temporal Characteristics: A Case Study of Xi’an, China
Air pollution has become a serious problem threatening human health. Effective prediction models can help reduce the adverse effects of air pollutants. Accurate predictions of air pollutant concentration can provide a scientific basis for air pollution prevention and control. However, the previous a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/12/12/1626 |
| _version_ | 1797506636475006976 |
|---|---|
| author | Hongbin Dai Guangqiu Huang Jingjing Wang Huibin Zeng Fangyu Zhou |
| author_facet | Hongbin Dai Guangqiu Huang Jingjing Wang Huibin Zeng Fangyu Zhou |
| author_sort | Hongbin Dai |
| collection | DOAJ |
| description | Air pollution has become a serious problem threatening human health. Effective prediction models can help reduce the adverse effects of air pollutants. Accurate predictions of air pollutant concentration can provide a scientific basis for air pollution prevention and control. However, the previous air pollution-related prediction models mainly processed air quality prediction, or the prediction of a single or two air pollutants. Meanwhile, the temporal and spatial characteristics and multiple factors of pollutants were not fully considered. Herein, we establish a deep learning model for an atmospheric pollutant memory network (LSTM) by both applying the one-dimensional multi-scale convolution kernel (ODMSCNN) and a long-short-term memory network (LSTM) on the basis of temporal and spatial characteristics. The temporal and spatial characteristics combine the respective advantages of CNN and LSTM networks. First, ODMSCNN is utilized to extract the temporal and spatial characteristics of air pollutant-related data to form a feature vector, and then the feature vector is input into the LSTM network to predict the concentration of air pollutants. The data set comes from the daily concentration data and hourly concentration data of six atmospheric pollutants (PM<sub>2.5</sub>, PM<sub>10</sub>, NO<sub>2</sub>, CO, O<sub>3</sub>, SO<sub>2</sub>) and 17 types of meteorological data in Xi’an. Daily concentration data prediction, hourly concentration data prediction, group data prediction and multi-factor prediction were used to verify the effectiveness of the model. In general, the air pollutant concentration prediction model based on ODMSCNN-LSTM shows a better prediction effect compared with multi-layer perceptron (MLP), CNN, and LSTM models. |
| first_indexed | 2024-03-10T04:35:21Z |
| format | Article |
| id | doaj.art-1289deefd1e543358d158c133e60579c |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-10T04:35:21Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-1289deefd1e543358d158c133e60579c2023-11-23T03:46:28ZengMDPI AGAtmosphere2073-44332021-12-011212162610.3390/atmos12121626Prediction of Air Pollutant Concentration Based on One-Dimensional Multi-Scale CNN-LSTM Considering Spatial-Temporal Characteristics: A Case Study of Xi’an, ChinaHongbin Dai0Guangqiu Huang1Jingjing Wang2Huibin Zeng3Fangyu Zhou4School of Management, Xi’an University of Architecture and Technology, Xi’an 710055, ChinaSchool of Management, Xi’an University of Architecture and Technology, Xi’an 710055, ChinaCollege of Vocational and Technical Education, Guangxi Science & Technology of Normal University, Laibin 546199, ChinaSchool of Management, Xi’an University of Architecture and Technology, Xi’an 710055, ChinaSchool of Applied English, Chengdu Institute Sichuan International Studies University, Chengdu 611844, ChinaAir pollution has become a serious problem threatening human health. Effective prediction models can help reduce the adverse effects of air pollutants. Accurate predictions of air pollutant concentration can provide a scientific basis for air pollution prevention and control. However, the previous air pollution-related prediction models mainly processed air quality prediction, or the prediction of a single or two air pollutants. Meanwhile, the temporal and spatial characteristics and multiple factors of pollutants were not fully considered. Herein, we establish a deep learning model for an atmospheric pollutant memory network (LSTM) by both applying the one-dimensional multi-scale convolution kernel (ODMSCNN) and a long-short-term memory network (LSTM) on the basis of temporal and spatial characteristics. The temporal and spatial characteristics combine the respective advantages of CNN and LSTM networks. First, ODMSCNN is utilized to extract the temporal and spatial characteristics of air pollutant-related data to form a feature vector, and then the feature vector is input into the LSTM network to predict the concentration of air pollutants. The data set comes from the daily concentration data and hourly concentration data of six atmospheric pollutants (PM<sub>2.5</sub>, PM<sub>10</sub>, NO<sub>2</sub>, CO, O<sub>3</sub>, SO<sub>2</sub>) and 17 types of meteorological data in Xi’an. Daily concentration data prediction, hourly concentration data prediction, group data prediction and multi-factor prediction were used to verify the effectiveness of the model. In general, the air pollutant concentration prediction model based on ODMSCNN-LSTM shows a better prediction effect compared with multi-layer perceptron (MLP), CNN, and LSTM models.https://www.mdpi.com/2073-4433/12/12/1626ODMSCNNLSTMatmospheric pollutant concentration predictiondeep learningtemporal and spatial characteristics |
| spellingShingle | Hongbin Dai Guangqiu Huang Jingjing Wang Huibin Zeng Fangyu Zhou Prediction of Air Pollutant Concentration Based on One-Dimensional Multi-Scale CNN-LSTM Considering Spatial-Temporal Characteristics: A Case Study of Xi’an, China Atmosphere ODMSCNN LSTM atmospheric pollutant concentration prediction deep learning temporal and spatial characteristics |
| title | Prediction of Air Pollutant Concentration Based on One-Dimensional Multi-Scale CNN-LSTM Considering Spatial-Temporal Characteristics: A Case Study of Xi’an, China |
| title_full | Prediction of Air Pollutant Concentration Based on One-Dimensional Multi-Scale CNN-LSTM Considering Spatial-Temporal Characteristics: A Case Study of Xi’an, China |
| title_fullStr | Prediction of Air Pollutant Concentration Based on One-Dimensional Multi-Scale CNN-LSTM Considering Spatial-Temporal Characteristics: A Case Study of Xi’an, China |
| title_full_unstemmed | Prediction of Air Pollutant Concentration Based on One-Dimensional Multi-Scale CNN-LSTM Considering Spatial-Temporal Characteristics: A Case Study of Xi’an, China |
| title_short | Prediction of Air Pollutant Concentration Based on One-Dimensional Multi-Scale CNN-LSTM Considering Spatial-Temporal Characteristics: A Case Study of Xi’an, China |
| title_sort | prediction of air pollutant concentration based on one dimensional multi scale cnn lstm considering spatial temporal characteristics a case study of xi an china |
| topic | ODMSCNN LSTM atmospheric pollutant concentration prediction deep learning temporal and spatial characteristics |
| url | https://www.mdpi.com/2073-4433/12/12/1626 |
| work_keys_str_mv | AT hongbindai predictionofairpollutantconcentrationbasedononedimensionalmultiscalecnnlstmconsideringspatialtemporalcharacteristicsacasestudyofxianchina AT guangqiuhuang predictionofairpollutantconcentrationbasedononedimensionalmultiscalecnnlstmconsideringspatialtemporalcharacteristicsacasestudyofxianchina AT jingjingwang predictionofairpollutantconcentrationbasedononedimensionalmultiscalecnnlstmconsideringspatialtemporalcharacteristicsacasestudyofxianchina AT huibinzeng predictionofairpollutantconcentrationbasedononedimensionalmultiscalecnnlstmconsideringspatialtemporalcharacteristicsacasestudyofxianchina AT fangyuzhou predictionofairpollutantconcentrationbasedononedimensionalmultiscalecnnlstmconsideringspatialtemporalcharacteristicsacasestudyofxianchina |