Interpretable Machine Learning Approaches for Forecasting and Predicting Air Pollution: A Systematic Review
Abstract Many studies use machine learning to predict atmospheric pollutant levels, prioritizing accuracy over interpretability. This systematic review will focus on reviewing studies that have utilized interpretable machine learning models to enhance interpretability while maintaining high accuracy...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-11-01
|
| Series: | Aerosol and Air Quality Research |
| Subjects: | |
| Online Access: | https://doi.org/10.4209/aaqr.230151 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862826105569280 |
|---|---|
| author | Anass Houdou Imad El Badisy Kenza Khomsi Sammila Andrade Abdala Fayez Abdulla Houda Najmi Majdouline Obtel Lahcen Belyamani Azeddine Ibrahimi Mohamed Khalis |
| author_facet | Anass Houdou Imad El Badisy Kenza Khomsi Sammila Andrade Abdala Fayez Abdulla Houda Najmi Majdouline Obtel Lahcen Belyamani Azeddine Ibrahimi Mohamed Khalis |
| author_sort | Anass Houdou |
| collection | DOAJ |
| description | Abstract Many studies use machine learning to predict atmospheric pollutant levels, prioritizing accuracy over interpretability. This systematic review will focus on reviewing studies that have utilized interpretable machine learning models to enhance interpretability while maintaining high accuracy for air pollution prediction. The search terms “air pollution,” “machine learning,” and “interpretability” were used to identify relevant studies published between 2011 and 2023 from PubMed, Scopus, Web of Science, Science Direct, and JuSER. The included studies were assessed for quality based on an ecological checklist for maximizing reproducibility of ecological niche models. Among the 5,396 identified studies, 480 focused on air pollution prediction, with 56 providing model interpretations. Among the studies, 20 methods were identified: 8 model-agnostic methods, 4 model-specific methods, and 8 hybrid models. Shapley additive explanations was the most commonly used method (46.4%), followed by partial dependence plots (17.4%), both of which are model-agnostic methods. These methods identify important atmospheric features, enhancing researchers’ understanding and making machine learning outcomes more accessible to non-experts. This can enhance prediction and prevention of adverse weather events and air pollution, benefiting public health. |
| format | Article |
| id | doaj-art-8db851a84a2e4156aa2849bf017940fe |
| institution | Kabale University |
| issn | 1680-8584 2071-1409 |
| language | English |
| publishDate | 2023-11-01 |
| publisher | Springer |
| record_format | Article |
| series | Aerosol and Air Quality Research |
| spelling | doaj-art-8db851a84a2e4156aa2849bf017940fe2025-02-09T12:24:15ZengSpringerAerosol and Air Quality Research1680-85842071-14092023-11-0124112110.4209/aaqr.230151Interpretable Machine Learning Approaches for Forecasting and Predicting Air Pollution: A Systematic ReviewAnass Houdou0Imad El Badisy1Kenza Khomsi2Sammila Andrade Abdala3Fayez Abdulla4Houda Najmi5Majdouline Obtel6Lahcen Belyamani7Azeddine Ibrahimi8Mohamed Khalis9Mohammed VI Center for Research & InnovationMohammed VI Center for Research & InnovationGeneral Directorate of Meteorology, Mohammed VI University of Sciences and HealthMohammed VI Center for Research & InnovationCivil Engineering Department, Jordan University of Science and TechnologyGeneral Directorate of MeteorologyMohammed VI Center for Research & InnovationMohammed VI Center for Research & InnovationMohammed VI Center for Research & InnovationMohammed VI Center for Research & InnovationAbstract Many studies use machine learning to predict atmospheric pollutant levels, prioritizing accuracy over interpretability. This systematic review will focus on reviewing studies that have utilized interpretable machine learning models to enhance interpretability while maintaining high accuracy for air pollution prediction. The search terms “air pollution,” “machine learning,” and “interpretability” were used to identify relevant studies published between 2011 and 2023 from PubMed, Scopus, Web of Science, Science Direct, and JuSER. The included studies were assessed for quality based on an ecological checklist for maximizing reproducibility of ecological niche models. Among the 5,396 identified studies, 480 focused on air pollution prediction, with 56 providing model interpretations. Among the studies, 20 methods were identified: 8 model-agnostic methods, 4 model-specific methods, and 8 hybrid models. Shapley additive explanations was the most commonly used method (46.4%), followed by partial dependence plots (17.4%), both of which are model-agnostic methods. These methods identify important atmospheric features, enhancing researchers’ understanding and making machine learning outcomes more accessible to non-experts. This can enhance prediction and prevention of adverse weather events and air pollution, benefiting public health.https://doi.org/10.4209/aaqr.230151Air quality predictionDeep learningSupervised learning |
| spellingShingle | Anass Houdou Imad El Badisy Kenza Khomsi Sammila Andrade Abdala Fayez Abdulla Houda Najmi Majdouline Obtel Lahcen Belyamani Azeddine Ibrahimi Mohamed Khalis Interpretable Machine Learning Approaches for Forecasting and Predicting Air Pollution: A Systematic Review Aerosol and Air Quality Research Air quality prediction Deep learning Supervised learning |
| title | Interpretable Machine Learning Approaches for Forecasting and Predicting Air Pollution: A Systematic Review |
| title_full | Interpretable Machine Learning Approaches for Forecasting and Predicting Air Pollution: A Systematic Review |
| title_fullStr | Interpretable Machine Learning Approaches for Forecasting and Predicting Air Pollution: A Systematic Review |
| title_full_unstemmed | Interpretable Machine Learning Approaches for Forecasting and Predicting Air Pollution: A Systematic Review |
| title_short | Interpretable Machine Learning Approaches for Forecasting and Predicting Air Pollution: A Systematic Review |
| title_sort | interpretable machine learning approaches for forecasting and predicting air pollution a systematic review |
| topic | Air quality prediction Deep learning Supervised learning |
| url | https://doi.org/10.4209/aaqr.230151 |
| work_keys_str_mv | AT anasshoudou interpretablemachinelearningapproachesforforecastingandpredictingairpollutionasystematicreview AT imadelbadisy interpretablemachinelearningapproachesforforecastingandpredictingairpollutionasystematicreview AT kenzakhomsi interpretablemachinelearningapproachesforforecastingandpredictingairpollutionasystematicreview AT sammilaandradeabdala interpretablemachinelearningapproachesforforecastingandpredictingairpollutionasystematicreview AT fayezabdulla interpretablemachinelearningapproachesforforecastingandpredictingairpollutionasystematicreview AT houdanajmi interpretablemachinelearningapproachesforforecastingandpredictingairpollutionasystematicreview AT majdoulineobtel interpretablemachinelearningapproachesforforecastingandpredictingairpollutionasystematicreview AT lahcenbelyamani interpretablemachinelearningapproachesforforecastingandpredictingairpollutionasystematicreview AT azeddineibrahimi interpretablemachinelearningapproachesforforecastingandpredictingairpollutionasystematicreview AT mohamedkhalis interpretablemachinelearningapproachesforforecastingandpredictingairpollutionasystematicreview |