Articles | Volume 19, issue 7
https://doi.org/10.5194/gmd-19-2691-2026
https://doi.org/10.5194/gmd-19-2691-2026
Development and technical paper
 | 
10 Apr 2026
Development and technical paper |  | 10 Apr 2026

Machine learning-driven characterization and prescription of aerosol optical properties for atmospheric models

Nilton Évora do Rosário, Karla M. Longo, Pedro H. Toso, Saulo R. Freitas, Marcia A. Yamasoe, Luiz Flávio Rodrigues, Otavio Medeiros, Haroldo Campos Velho, Isilda da Cunha Menezes, and Ana Isabel Miranda

Data sets

Machine learning-driven characterization and prescription of aerosol optical properties for atmospheric models Nilton Evora Rosario https://doi.org/10.5281/zenodo.14825197

Download
Short summary
This study maps aerosol regimes over the Iberian Peninsula using AERONET data and machine learning. Five types were identified, from Saharan dust to smoke, highlighting differences in particle size and absorption. Combining observations with model data improves aerosol representation in climate simulations, reducing uncertainties and enhancing understanding of regional air quality and climate impacts.
Share