Estimation of Daily Ground Level Air Pollution in Italian Municipalities with Machine Learning Models Using Sentinel-5P and ERA5 Data
Recent years have witnessed an increasing interest in air pollutants and their effects on human health. More generally, it has become evident how human, animal and environmental health are deeply interconnected within a One Health framework. Ground level air monitoring stations are sparse and thus h...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/7/1206 |
| _version_ | 1827286558278942720 |
|---|---|
| author | Alessandro Fania Alfonso Monaco Ester Pantaleo Tommaso Maggipinto Loredana Bellantuono Roberto Cilli Antonio Lacalamita Marianna La Rocca Sabina Tangaro Nicola Amoroso Roberto Bellotti |
| author_facet | Alessandro Fania Alfonso Monaco Ester Pantaleo Tommaso Maggipinto Loredana Bellantuono Roberto Cilli Antonio Lacalamita Marianna La Rocca Sabina Tangaro Nicola Amoroso Roberto Bellotti |
| author_sort | Alessandro Fania |
| collection | DOAJ |
| description | Recent years have witnessed an increasing interest in air pollutants and their effects on human health. More generally, it has become evident how human, animal and environmental health are deeply interconnected within a One Health framework. Ground level air monitoring stations are sparse and thus have limited coverage due to high costs. Satellite and reanalysis data represent an alternative with high spatio-temporal resolution. The idea of this work is to build an Artificial Intelligence model for the estimation of surface-level daily concentrations of air pollutants over the entire Italian territory using satellite, climate reanalysis, geographical and social data. As ground truth we use data from the monitoring stations of the Regional Environmental Protection Agency (ARPA) covering the period 2019–2022 at municipal level. The analysis compares different models and applies an Explainable Artificial Intelligence approach to evaluate the role of individual features in the model. The best model reaches an average <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.84 ± 0.01 and MAE of 5.00 ± 0.01 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="sans-serif">μ</mi></semantics></math></inline-formula>g/m<sup>3</sup> across all pollutants which compare well with the body of literature. The XAI analysis highlights the pivotal role of satellite and climate reanalysis data. Our work can facilitate One Health surveys and help researchers and policy makers. |
| first_indexed | 2024-04-24T10:35:27Z |
| format | Article |
| id | doaj.art-4191d098e5184312a9461171d47a3aad |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-24T10:35:27Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4191d098e5184312a9461171d47a3aad2024-04-12T13:25:37ZengMDPI AGRemote Sensing2072-42922024-03-01167120610.3390/rs16071206Estimation of Daily Ground Level Air Pollution in Italian Municipalities with Machine Learning Models Using Sentinel-5P and ERA5 DataAlessandro Fania0Alfonso Monaco1Ester Pantaleo2Tommaso Maggipinto3Loredana Bellantuono4Roberto Cilli5Antonio Lacalamita6Marianna La Rocca7Sabina Tangaro8Nicola Amoroso9Roberto Bellotti10Dipartimento Interateneo di Fisica M. Merlin, Università degli Studi di Bari Aldo Moro, Via G. Amendola 173, 70125 Bari, ItalyDipartimento Interateneo di Fisica M. Merlin, Università degli Studi di Bari Aldo Moro, Via G. Amendola 173, 70125 Bari, ItalyDipartimento Interateneo di Fisica M. Merlin, Università degli Studi di Bari Aldo Moro, Via G. Amendola 173, 70125 Bari, ItalyDipartimento Interateneo di Fisica M. Merlin, Università degli Studi di Bari Aldo Moro, Via G. Amendola 173, 70125 Bari, ItalyIstituto Nazionale di Fisica Nucleare (INFN), Sezione di Bari, Via A. Orabona 4, 70125 Bari, ItalyDipartimento Interateneo di Fisica M. Merlin, Università degli Studi di Bari Aldo Moro, Via G. Amendola 173, 70125 Bari, ItalyDipartimento Interateneo di Fisica M. Merlin, Università degli Studi di Bari Aldo Moro, Via G. Amendola 173, 70125 Bari, ItalyDipartimento Interateneo di Fisica M. Merlin, Università degli Studi di Bari Aldo Moro, Via G. Amendola 173, 70125 Bari, ItalyIstituto Nazionale di Fisica Nucleare (INFN), Sezione di Bari, Via A. Orabona 4, 70125 Bari, ItalyIstituto Nazionale di Fisica Nucleare (INFN), Sezione di Bari, Via A. Orabona 4, 70125 Bari, ItalyDipartimento Interateneo di Fisica M. Merlin, Università degli Studi di Bari Aldo Moro, Via G. Amendola 173, 70125 Bari, ItalyRecent years have witnessed an increasing interest in air pollutants and their effects on human health. More generally, it has become evident how human, animal and environmental health are deeply interconnected within a One Health framework. Ground level air monitoring stations are sparse and thus have limited coverage due to high costs. Satellite and reanalysis data represent an alternative with high spatio-temporal resolution. The idea of this work is to build an Artificial Intelligence model for the estimation of surface-level daily concentrations of air pollutants over the entire Italian territory using satellite, climate reanalysis, geographical and social data. As ground truth we use data from the monitoring stations of the Regional Environmental Protection Agency (ARPA) covering the period 2019–2022 at municipal level. The analysis compares different models and applies an Explainable Artificial Intelligence approach to evaluate the role of individual features in the model. The best model reaches an average <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.84 ± 0.01 and MAE of 5.00 ± 0.01 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="sans-serif">μ</mi></semantics></math></inline-formula>g/m<sup>3</sup> across all pollutants which compare well with the body of literature. The XAI analysis highlights the pivotal role of satellite and climate reanalysis data. Our work can facilitate One Health surveys and help researchers and policy makers.https://www.mdpi.com/2072-4292/16/7/1206air pollutionsatellite datamachine learningexplainable artificial intelligence |
| spellingShingle | Alessandro Fania Alfonso Monaco Ester Pantaleo Tommaso Maggipinto Loredana Bellantuono Roberto Cilli Antonio Lacalamita Marianna La Rocca Sabina Tangaro Nicola Amoroso Roberto Bellotti Estimation of Daily Ground Level Air Pollution in Italian Municipalities with Machine Learning Models Using Sentinel-5P and ERA5 Data Remote Sensing air pollution satellite data machine learning explainable artificial intelligence |
| title | Estimation of Daily Ground Level Air Pollution in Italian Municipalities with Machine Learning Models Using Sentinel-5P and ERA5 Data |
| title_full | Estimation of Daily Ground Level Air Pollution in Italian Municipalities with Machine Learning Models Using Sentinel-5P and ERA5 Data |
| title_fullStr | Estimation of Daily Ground Level Air Pollution in Italian Municipalities with Machine Learning Models Using Sentinel-5P and ERA5 Data |
| title_full_unstemmed | Estimation of Daily Ground Level Air Pollution in Italian Municipalities with Machine Learning Models Using Sentinel-5P and ERA5 Data |
| title_short | Estimation of Daily Ground Level Air Pollution in Italian Municipalities with Machine Learning Models Using Sentinel-5P and ERA5 Data |
| title_sort | estimation of daily ground level air pollution in italian municipalities with machine learning models using sentinel 5p and era5 data |
| topic | air pollution satellite data machine learning explainable artificial intelligence |
| url | https://www.mdpi.com/2072-4292/16/7/1206 |
| work_keys_str_mv | AT alessandrofania estimationofdailygroundlevelairpollutioninitalianmunicipalitieswithmachinelearningmodelsusingsentinel5pandera5data AT alfonsomonaco estimationofdailygroundlevelairpollutioninitalianmunicipalitieswithmachinelearningmodelsusingsentinel5pandera5data AT esterpantaleo estimationofdailygroundlevelairpollutioninitalianmunicipalitieswithmachinelearningmodelsusingsentinel5pandera5data AT tommasomaggipinto estimationofdailygroundlevelairpollutioninitalianmunicipalitieswithmachinelearningmodelsusingsentinel5pandera5data AT loredanabellantuono estimationofdailygroundlevelairpollutioninitalianmunicipalitieswithmachinelearningmodelsusingsentinel5pandera5data AT robertocilli estimationofdailygroundlevelairpollutioninitalianmunicipalitieswithmachinelearningmodelsusingsentinel5pandera5data AT antoniolacalamita estimationofdailygroundlevelairpollutioninitalianmunicipalitieswithmachinelearningmodelsusingsentinel5pandera5data AT mariannalarocca estimationofdailygroundlevelairpollutioninitalianmunicipalitieswithmachinelearningmodelsusingsentinel5pandera5data AT sabinatangaro estimationofdailygroundlevelairpollutioninitalianmunicipalitieswithmachinelearningmodelsusingsentinel5pandera5data AT nicolaamoroso estimationofdailygroundlevelairpollutioninitalianmunicipalitieswithmachinelearningmodelsusingsentinel5pandera5data AT robertobellotti estimationofdailygroundlevelairpollutioninitalianmunicipalitieswithmachinelearningmodelsusingsentinel5pandera5data |