A standard U-Net with MAE pre-training followed by short CRPS fine-tuning via Monte Carlo Dropout matches or exceeds GenCast and IFS ENS probabilistic skill at 1.5° resolution while cutting training compute and inference latency by over 10×.
A., Durran, D
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
CONDITIONAL 2representative citing papers
HealDA supplies ML-based initial conditions for AI weather models that produce forecasts trailing ERA5-initialized runs by less than one day of effective lead time, with the skill gap arising mainly from initial error size.
citing papers explorer
-
U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster
A standard U-Net with MAE pre-training followed by short CRPS fine-tuning via Monte Carlo Dropout matches or exceeds GenCast and IFS ENS probabilistic skill at 1.5° resolution while cutting training compute and inference latency by over 10×.
-
HealDA: Highlighting the importance of initial errors in end-to-end AI weather forecasts
HealDA supplies ML-based initial conditions for AI weather models that produce forecasts trailing ERA5-initialized runs by less than one day of effective lead time, with the skill gap arising mainly from initial error size.