Identifying Atmospheric Nucleation Events Using Machine Learning

• Alvaro Silva-Silva ^[1] ; Javier Andrade-Garda ^[1] ; Daniel Garabato ^[1] ; Sonia Suárez-Garaboa ^[1] ; Elisabeth Alonso-Blanco ^[2] ; Francisco J. Gómez-Moreno ^[2]
  1. [1] Universidade da Coruña

     Universidade da Coruña

     A Coruña, España

     
  2. [2] Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas

     Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas

     Madrid, España

     
• Localización: Proceedings XoveTIC 2025: Impulsando el talento científico / coord. por Manuel Lagos Rodríguez, Hilda Romero-Velo, Álvaro Leitao , Javier Pereira-Loureiro , Manuel Penedo , 2026, ISBN 978-84-9749-925-5, págs. 23-30
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Atmospheric nucleation (New Particle Formation) is not only a key process in aerosoldynamics, but it also assists in regulating the planet’s radiative balance. Accurate detection isessential to understand its implications for both climate and public health. However, manuallyidentifying these events from particle size distributions is a slow and tedious process.This work studies the feasibility of a proposal based on machine learning and computer vision toclassify nucleation events from images (surface plots) of particle distribution time series. To thisend, different preprocessing configurations are explored and both classical models and deepneural networks are tested. Preliminary results show promising performance, highlighting thesystem’s ability to identify positive events with high sensitivity, suggesting a possible future in-tegration into atmospheric monitoring platforms.