Complementing Dynamical Downscaling With Super‐Resolution Convolutional Neural Networks
Abstract Despite advancements in Artificial Intelligence (AI) methods for climate downscaling, significant challenges remain for their practicality in climate research. Current AI‐methods exhibit notable limitations, such as limited application in downscaling Global Climate Models (GCMs), and accura...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-02-01
|
| Series: | Geophysical Research Letters |
| Online Access: | https://doi.org/10.1029/2024GL111828 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Despite advancements in Artificial Intelligence (AI) methods for climate downscaling, significant challenges remain for their practicality in climate research. Current AI‐methods exhibit notable limitations, such as limited application in downscaling Global Climate Models (GCMs), and accurately representing extremes. To address these challenges, we implement an AI‐based methodology using super‐resolution convolutional neural networks (SRCNN), trained and evaluated on 40 years of daily precipitation data from a reanalysis and a high‐resolution dynamically downscaled counterpart. The dynamical downscaled simulations, constrained using spectral nudging, enable the replication of historical events at a higher resolution. This allows the SRCNN to emulate dynamical downscaling effectively. Modifications, such as incorporating elevation data and data pre‐processing enhances overall model performance, while using exponential and quantile loss functions improve the simulation of extremes. Our findings show SRCNN models efficiently and skillfully downscale precipitation from GCMs. Future work will expand this methodology to downscale additional variables for future climate projections. |
|---|---|
| ISSN: | 0094-8276 1944-8007 |