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.

Bhakare, S., Dal Gesso, S., Venturini, M., Zardi, D., Trentini, L., Matiu, M., et al. (2024). Intercomparison of Machine Learning Models for Spatial Downscaling of Daily Mean Temperature in Complex Terrain. ATMOSPHERE, 15(9) [10.3390/atmos15091085].

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

Petitta M.
2024-01-01

Abstract

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.
2024
Bhakare, S., Dal Gesso, S., Venturini, M., Zardi, D., Trentini, L., Matiu, M., et al. (2024). Intercomparison of Machine Learning Models for Spatial Downscaling of Daily Mean Temperature in Complex Terrain. ATMOSPHERE, 15(9) [10.3390/atmos15091085].
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/11590/492056
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact