On the limitations of deep learning for statistical downscaling of climate change projections: The transferability and the extrapolation issues

On the limitations of deep learning for statistical downscaling of climate change projections: The transferability and the extrapolation issues

Abstract Convolutional neural networks (CNNs) have become one of the state‐of‐the‐art techniques for downscaling climate projections. They are being applied under Perfect‐Prognosis (trained in a historical period with observations) and hybrid approaches (as Regional Climate Models (RCMs) emulators),...

Full description

Bibliographic Details
Main Authors: Alfonso Hernanz, Carlos Correa, Juan‐Carlos Sánchez‐Perrino, Ignacio Prieto‐Rico, Esteban Rodríguez‐Guisado, Marta Domínguez, Ernesto Rodríguez‐Camino
Format: Article
Language:English
Published: Wiley 2024-02-01
Series:Atmospheric Science Letters
Subjects:
convolutional neural networks
deep learning
emulators
EURO‐CORDEX
evaluation
extrapolation
Online Access:https://doi.org/10.1002/asl.1195

Similar Items

Similar Items