A large number of medical research studies have shown that particulate air pollution poses a significant risk to health. In urban areas, where 55% of the global population now resides, a figure that according to the United Nations will rise to 70% by 2050, this correlation is under careful evaluation and requires further investigation. According to the international framework of the Sustainable Development Goals of the United Nations 2030 Agenda (target 11.6 on reducing the environmental impact of cities) and the World Health Organisation guidelines, PM concentrations in urban areas must be weighted by population data to assess the impact of particulate matter on the population. This approach is crucial because certain areas may have high PM concentrations without being densely populated, or conversely, areas with lower concentrations may be predominantly inhabited by groups vulnerable to health risks. In this context, it would be essential to be able to obtain information on PM concentrations as well as risk exposure assessments for different population groups at the intra-urban scale. This would help to identify those areas at higher health risk than others due to characteristics related to land use, urban morphology, socio-economic conditions and meteorological conditions. The estimation of PM concentration from satellite data has emerged as a priority objective for upcoming Earth observation missions outlined by major space agencies. This includes the joint NASA/JPL and ASI program set to launch the Multi-Angle Imager for Aerosols (MAIA) sensor into orbit by 2024. This sensor represents a pioneering tool designed to estimate Aerosol Optical Depth (AOD) at the 1 km scale. Subsequent processing of the acquired data will yield measurements of PM concentrations. As part of this collaboration and in response to the above-mentioned needs, ASI has decided to fund the APEMAIA project (Assessment of PM Exposure at the intra-urban scale in preparation for the MAIA mission). The project is designed to investigate the potential of MAIA by developing a multi-modular system for extracting PM concentrations at the intra-urban scale using Artificial Intelligence (AI) techniques. AOD maps derived from the integration of multi-source high-resolution (such as PRISMA, Sentinel-2, Sentinel-3) and medium-resolution data (MISR, MODIS, VIIRS, and simulated data from the upcoming MAIA mission) will be considered. In addition, the system will incorporate additional informative layers related to meteorological variables, land cover, and urban morphology. Furthermore, the dasymetric method will be employed to disaggregate population data, initially provided for wider census areas, and reallocate them to cells within a final reference grid at a higher spatial resolution. The aim is to provide spatialised demographic data both as input for training AI models and for quantifying population exposure to PM at the intra-urban scale. Time series of PM concentrations measured by in-situ monitoring networks will also be used for training and validation of the AI models. The study areas include the metropolitan area of Rome, a primary target for MAIA, and the urban areas of Taranto and Bari, designated as secondary targets.

EO data and AI techniques for measuring PM concentration and exposure at intra-urban scale: the APEMAIA Project

Maria Adamo;Mariella Aquilino;Marica De Lucia;Silvana Fuina;Francesco Carbone;Roberto Bellotti;Alfonso Monaco;Roberto Cilli;Alessandro Fania;Ester Pantaleo;Francesca Intini;
2024-01-01

Abstract

A large number of medical research studies have shown that particulate air pollution poses a significant risk to health. In urban areas, where 55% of the global population now resides, a figure that according to the United Nations will rise to 70% by 2050, this correlation is under careful evaluation and requires further investigation. According to the international framework of the Sustainable Development Goals of the United Nations 2030 Agenda (target 11.6 on reducing the environmental impact of cities) and the World Health Organisation guidelines, PM concentrations in urban areas must be weighted by population data to assess the impact of particulate matter on the population. This approach is crucial because certain areas may have high PM concentrations without being densely populated, or conversely, areas with lower concentrations may be predominantly inhabited by groups vulnerable to health risks. In this context, it would be essential to be able to obtain information on PM concentrations as well as risk exposure assessments for different population groups at the intra-urban scale. This would help to identify those areas at higher health risk than others due to characteristics related to land use, urban morphology, socio-economic conditions and meteorological conditions. The estimation of PM concentration from satellite data has emerged as a priority objective for upcoming Earth observation missions outlined by major space agencies. This includes the joint NASA/JPL and ASI program set to launch the Multi-Angle Imager for Aerosols (MAIA) sensor into orbit by 2024. This sensor represents a pioneering tool designed to estimate Aerosol Optical Depth (AOD) at the 1 km scale. Subsequent processing of the acquired data will yield measurements of PM concentrations. As part of this collaboration and in response to the above-mentioned needs, ASI has decided to fund the APEMAIA project (Assessment of PM Exposure at the intra-urban scale in preparation for the MAIA mission). The project is designed to investigate the potential of MAIA by developing a multi-modular system for extracting PM concentrations at the intra-urban scale using Artificial Intelligence (AI) techniques. AOD maps derived from the integration of multi-source high-resolution (such as PRISMA, Sentinel-2, Sentinel-3) and medium-resolution data (MISR, MODIS, VIIRS, and simulated data from the upcoming MAIA mission) will be considered. In addition, the system will incorporate additional informative layers related to meteorological variables, land cover, and urban morphology. Furthermore, the dasymetric method will be employed to disaggregate population data, initially provided for wider census areas, and reallocate them to cells within a final reference grid at a higher spatial resolution. The aim is to provide spatialised demographic data both as input for training AI models and for quantifying population exposure to PM at the intra-urban scale. Time series of PM concentrations measured by in-situ monitoring networks will also be used for training and validation of the AI models. The study areas include the metropolitan area of Rome, a primary target for MAIA, and the urban areas of Taranto and Bari, designated as secondary targets.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11586/519681
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact