Air-pollution prediction in smart city, deep learning approach
Abstract Over the past few decades, due to human activities, industrialization, and urbanization, air pollution has become a life-threatening factor in many countries around the world. Among air pollutants, Particulate Matter with a diameter of less than $$2.5 \mu m$$ 2.5 μ m ( $$PM_{2.5}$$ P M 2.5...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2021-12-01
|
| Series: | Journal of Big Data |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40537-021-00548-1 |
| _version_ | 1819102975452250112 |
|---|---|
| author | Abdellatif Bekkar Badr Hssina Samira Douzi Khadija Douzi |
| author_facet | Abdellatif Bekkar Badr Hssina Samira Douzi Khadija Douzi |
| author_sort | Abdellatif Bekkar |
| collection | DOAJ |
| description | Abstract Over the past few decades, due to human activities, industrialization, and urbanization, air pollution has become a life-threatening factor in many countries around the world. Among air pollutants, Particulate Matter with a diameter of less than $$2.5 \mu m$$ 2.5 μ m ( $$PM_{2.5}$$ P M 2.5 ) is a serious health problem. It causes various illnesses such as respiratory tract and cardiovascular diseases. Hence, it is necessary to accurately predict the $$PM_{2.5}$$ P M 2.5 concentrations in order to prevent the citizens from the dangerous impact of air pollution beforehand. The variation of $$PM_{2.5}$$ P M 2.5 depends on a variety of factors, such as meteorology and the concentration of other pollutants in urban areas. In this paper, we implemented a deep learning solution to predict the hourly forecast of $$PM_{2.5}$$ P M 2.5 concentration in Beijing, China, based on CNN-LSTM, with a spatial-temporal feature by combining historical data of pollutants, meteorological data, and $$PM_{2.5}$$ P M 2.5 concentration in the adjacent stations. We examined the difference in performances among Deep learning algorithms such as LSTM, Bi-LSTM, GRU, Bi-GRU, CNN, and a hybrid CNN-LSTM model. Experimental results indicate that our method “hybrid CNN-LSTM multivariate” enables more accurate predictions than all the listed traditional models and performs better in predictive performance. |
| first_indexed | 2024-12-22T01:43:06Z |
| format | Article |
| id | doaj.art-9676c5ea6f6348f587402b1b0b4bf445 |
| institution | Directory Open Access Journal |
| issn | 2196-1115 |
| language | English |
| last_indexed | 2024-12-22T01:43:06Z |
| publishDate | 2021-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Big Data |
| spelling | doaj.art-9676c5ea6f6348f587402b1b0b4bf4452022-12-21T18:43:08ZengSpringerOpenJournal of Big Data2196-11152021-12-018112110.1186/s40537-021-00548-1Air-pollution prediction in smart city, deep learning approachAbdellatif Bekkar0Badr Hssina1Samira Douzi2Khadija Douzi3FSTM, University Hassan IIFSTM, University Hassan IIFMPR, University Mohammed VFSTM, University Hassan IIAbstract Over the past few decades, due to human activities, industrialization, and urbanization, air pollution has become a life-threatening factor in many countries around the world. Among air pollutants, Particulate Matter with a diameter of less than $$2.5 \mu m$$ 2.5 μ m ( $$PM_{2.5}$$ P M 2.5 ) is a serious health problem. It causes various illnesses such as respiratory tract and cardiovascular diseases. Hence, it is necessary to accurately predict the $$PM_{2.5}$$ P M 2.5 concentrations in order to prevent the citizens from the dangerous impact of air pollution beforehand. The variation of $$PM_{2.5}$$ P M 2.5 depends on a variety of factors, such as meteorology and the concentration of other pollutants in urban areas. In this paper, we implemented a deep learning solution to predict the hourly forecast of $$PM_{2.5}$$ P M 2.5 concentration in Beijing, China, based on CNN-LSTM, with a spatial-temporal feature by combining historical data of pollutants, meteorological data, and $$PM_{2.5}$$ P M 2.5 concentration in the adjacent stations. We examined the difference in performances among Deep learning algorithms such as LSTM, Bi-LSTM, GRU, Bi-GRU, CNN, and a hybrid CNN-LSTM model. Experimental results indicate that our method “hybrid CNN-LSTM multivariate” enables more accurate predictions than all the listed traditional models and performs better in predictive performance.https://doi.org/10.1186/s40537-021-00548-1Air-pollutionPM 2.5Deep learningForecastingLSTMGRU |
| spellingShingle | Abdellatif Bekkar Badr Hssina Samira Douzi Khadija Douzi Air-pollution prediction in smart city, deep learning approach Journal of Big Data Air-pollution PM 2.5 Deep learning Forecasting LSTM GRU |
| title | Air-pollution prediction in smart city, deep learning approach |
| title_full | Air-pollution prediction in smart city, deep learning approach |
| title_fullStr | Air-pollution prediction in smart city, deep learning approach |
| title_full_unstemmed | Air-pollution prediction in smart city, deep learning approach |
| title_short | Air-pollution prediction in smart city, deep learning approach |
| title_sort | air pollution prediction in smart city deep learning approach |
| topic | Air-pollution PM 2.5 Deep learning Forecasting LSTM GRU |
| url | https://doi.org/10.1186/s40537-021-00548-1 |
| work_keys_str_mv | AT abdellatifbekkar airpollutionpredictioninsmartcitydeeplearningapproach AT badrhssina airpollutionpredictioninsmartcitydeeplearningapproach AT samiradouzi airpollutionpredictioninsmartcitydeeplearningapproach AT khadijadouzi airpollutionpredictioninsmartcitydeeplearningapproach |