Exploring the Influencing Factors of Surface Ozone Variability by Explainable Machine Learning: A Case Study in the Basilicata Region (Southern Italy)
Exposure to high surface ozone (O<sub>3</sub>) concentrations, which is a major air pollutant and greenhouse gas, constitutes a significant public health concern, especially considering the potential adverse impact of climate change on future O<sub>3</sub> values. The impleme...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/16/5/491 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327437791363072 |
|---|---|
| author | Roberta Valentina Gagliardi Claudio Andenna |
| author_facet | Roberta Valentina Gagliardi Claudio Andenna |
| author_sort | Roberta Valentina Gagliardi |
| collection | DOAJ |
| description | Exposure to high surface ozone (O<sub>3</sub>) concentrations, which is a major air pollutant and greenhouse gas, constitutes a significant public health concern, especially considering the potential adverse impact of climate change on future O<sub>3</sub> values. The implementation of increasingly effective methods to assess the factors determining the formation and variability of O<sub>3</sub> is, therefore, of great significance. In this study, a methodological approach combining both supervised and unsupervised machine learning algorithms (MLAs) with the Shapley additive explanations (SHAP) method was used to understand the key factors behind O<sub>3</sub> variability and to explore the nonlinear relationships linking O<sub>3</sub> to these factors. The SHAP analysis carried out at different event scales indicated (i) the dominant role of the meteorological variables in driving O<sub>3</sub> variability, mainly relative humidity, wind speed, and temperature throughout the study period; (ii) an increase in the contribution of temperature, nitrogen oxides, and carbon monoxide to high O<sub>3</sub> concentrations during a selected pollution event; (iii) the predominant effect of wind speed and relative humidity in shaping the O<sub>3</sub> daily patterns clustered using the <i>k</i>-means technique. The results obtained are expected to be useful for the definition of effective measures to prevent and/or mitigate the health damage associated with ozone exposure. |
| format | Article |
| id | doaj-art-e4e6f9b7948440398fa51d545f4dfd5f |
| institution | Kabale University |
| issn | 2073-4433 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj-art-e4e6f9b7948440398fa51d545f4dfd5f2025-08-20T03:47:53ZengMDPI AGAtmosphere2073-44332025-04-0116549110.3390/atmos16050491Exploring the Influencing Factors of Surface Ozone Variability by Explainable Machine Learning: A Case Study in the Basilicata Region (Southern Italy)Roberta Valentina Gagliardi0Claudio Andenna1Istituto Superiore di Sanità, 00161 Rome, ItalyIstituto Nazionale per l’Assicurazione contro gli Infortuni sul Lavoro (INAIL-DIT), 00143 Rome, ItalyExposure to high surface ozone (O<sub>3</sub>) concentrations, which is a major air pollutant and greenhouse gas, constitutes a significant public health concern, especially considering the potential adverse impact of climate change on future O<sub>3</sub> values. The implementation of increasingly effective methods to assess the factors determining the formation and variability of O<sub>3</sub> is, therefore, of great significance. In this study, a methodological approach combining both supervised and unsupervised machine learning algorithms (MLAs) with the Shapley additive explanations (SHAP) method was used to understand the key factors behind O<sub>3</sub> variability and to explore the nonlinear relationships linking O<sub>3</sub> to these factors. The SHAP analysis carried out at different event scales indicated (i) the dominant role of the meteorological variables in driving O<sub>3</sub> variability, mainly relative humidity, wind speed, and temperature throughout the study period; (ii) an increase in the contribution of temperature, nitrogen oxides, and carbon monoxide to high O<sub>3</sub> concentrations during a selected pollution event; (iii) the predominant effect of wind speed and relative humidity in shaping the O<sub>3</sub> daily patterns clustered using the <i>k</i>-means technique. The results obtained are expected to be useful for the definition of effective measures to prevent and/or mitigate the health damage associated with ozone exposure.https://www.mdpi.com/2073-4433/16/5/491surface ozonemachine learningShapley additive explanation<i>k</i>-means clusteringdaily pattern |
| spellingShingle | Roberta Valentina Gagliardi Claudio Andenna Exploring the Influencing Factors of Surface Ozone Variability by Explainable Machine Learning: A Case Study in the Basilicata Region (Southern Italy) Atmosphere surface ozone machine learning Shapley additive explanation <i>k</i>-means clustering daily pattern |
| title | Exploring the Influencing Factors of Surface Ozone Variability by Explainable Machine Learning: A Case Study in the Basilicata Region (Southern Italy) |
| title_full | Exploring the Influencing Factors of Surface Ozone Variability by Explainable Machine Learning: A Case Study in the Basilicata Region (Southern Italy) |
| title_fullStr | Exploring the Influencing Factors of Surface Ozone Variability by Explainable Machine Learning: A Case Study in the Basilicata Region (Southern Italy) |
| title_full_unstemmed | Exploring the Influencing Factors of Surface Ozone Variability by Explainable Machine Learning: A Case Study in the Basilicata Region (Southern Italy) |
| title_short | Exploring the Influencing Factors of Surface Ozone Variability by Explainable Machine Learning: A Case Study in the Basilicata Region (Southern Italy) |
| title_sort | exploring the influencing factors of surface ozone variability by explainable machine learning a case study in the basilicata region southern italy |
| topic | surface ozone machine learning Shapley additive explanation <i>k</i>-means clustering daily pattern |
| url | https://www.mdpi.com/2073-4433/16/5/491 |
| work_keys_str_mv | AT robertavalentinagagliardi exploringtheinfluencingfactorsofsurfaceozonevariabilitybyexplainablemachinelearningacasestudyinthebasilicataregionsouthernitaly AT claudioandenna exploringtheinfluencingfactorsofsurfaceozonevariabilitybyexplainablemachinelearningacasestudyinthebasilicataregionsouthernitaly |