EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Intercomparison of Machine Learning Models for Spatial Downscaling of Daily Mean Temperature in Complex Terrain

Sudheer Bhakare, Sara Dal Gesso, Marco Venturini, Dino Zardi, Laura Trentini, Michael Matiu, Marcello Petitta

Atmosphere · 07.09.2024 · 15 (9) · 1085

DOI: 10.3390/atmos15091085 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Atmosphere, online erschienen am 07.09.2024. Verfasst von Sudheer Bhakare und 6 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union through the European Social Fund, European Union under NextGenerationEU.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We compare three machine learning models—artificial neural network (ANN), random forest (RF), and convolutional neural network (CNN)—for spatial downscaling of temperature at 2 m above ground (T2M) from a 9 km ERA5-Land reanalysis to 1 km in a complex terrain area, including the Non Valley and the Adige Valley in the Italian Alps. The results suggest that CNN performs better than the other methods across all seasons. RF performs similar to CNN, particularly in spring and summer, but its performance is reduced in winter and autumn. The best performance was observed in summer for CNN (R2 = 0.94, RMSE = 1 °C, MAE = 0.78 °C) and the lowest in winter for ANN (R2 = 0.79, RMSE = 1.6 °C, MAE = 1.3 °C). Elevation is an important predictor for ANN and RF, whereas it does not play a significant role for CNN. Additionally, CNN outperforms others even without elevation as an additional feature. Furthermore, MAE increases with higher elevation for ANN across all seasons. Conversely, MAE decreases with increased elevation for RF and CNN, particularly for summer, and remains mostly stable for other seasons.

Förderung

  • European Union through the European Social Fund
  • European Union under NextGenerationEU

Zitieren

APA

Bhakare, S., Gesso, S. D., Venturini, M., Zardi, D., Trentini, L., Matiu, M., & Petitta, M. (2024). Intercomparison of Machine Learning Models for Spatial Downscaling of Daily Mean Temperature in Complex Terrain. Atmosphere, 15(9), 1085. https://doi.org/10.3390/atmos15091085

Vancouver

Bhakare S, Gesso SD, Venturini M, Zardi D, Trentini L, Matiu M, et al. Intercomparison of Machine Learning Models for Spatial Downscaling of Daily Mean Temperature in Complex Terrain. Atmosphere. 2024;15(9):1085. doi:10.3390/atmos15091085

BibTeX
@article{Bhakare2024,
  author = {Bhakare, Sudheer and Gesso, Sara Dal and Venturini, Marco and Zardi, Dino and Trentini, Laura and Matiu, Michael and Petitta, Marcello},
  title = {Intercomparison of Machine Learning Models for Spatial Downscaling of Daily Mean Temperature in Complex Terrain},
  journal = {Atmosphere},
  year = {2024},
  volume = {15},
  number = {9},
  pages = {1085},
  doi = {10.3390/atmos15091085}
}
Kostenlos starten →