Machine learning ensemble improves weather forecast uncertainty estimates
Sonny-ENS: demystifying machine-learning ensemble weather forecasting
Machine Learning
Summary
Weather forecasts are never certain, and knowing the range of possible outcomes is crucial for decisions like flood warnings and energy trading. The authors introduce Sonny-ENS, a new way to use machine learning that creates multiple weather predictions quickly and with better accuracy than current top models. It uses fewer computing resources than expected and shows that its uncertainty estimates closely follow real atmospheric conditions. This means useful, reliable probabilistic forecasts can now be run on a single GPU server.
What this means in practice
- •For weather forecasting teams: Generate faster and more accurate probabilistic weather forecasts using a resource-efficient machine learning ensemble system on typical GPU hardware.
- •For energy traders: Incorporate improved uncertainty estimates in weather-dependent energy trading models to better manage risk and decision making over 1-10 day periods.
Authors
Minjong Cheon
Abstract
Every weather forecast is uncertain, and decisions from flood warnings to energy trading depend on how well that uncertainty is quantified. Machine-learning (ML) ensembles now quantify it better than the best physics-based ensemble, yet two things about them remain opaque: whether their skill requires hundreds to thousands of accelerator-days of training, and how a network with a simple source of randomness produces a spread that follows the flow. Here we introduce Sonny-ENS, an ensemble of three 68.9-million-parameter networks with Monte Carlo dropout, trained on the continuous ranked probability score (CRPS) in 2.7 A40 GPU-days. On 2022, it has a lower CRPS than the European Centre for Medium-Range Weather Forecasts ensemble (ENS) on 96% of 570 targets and an 8.3% lower mean CRPS at lead times of 1-10 days. It outperforms the operational GenCast on 69% of the targets, and a 51-member, 15-day forecast takes 69 s on one GPU. Ablations identify the ingredients of this skill, and a Kolmogorov-Arnold sparse autoencoder shows that dropout injects uncertainty mainly in the tropics, whereas the spread grows where the atmosphere is baroclinically unstable (spatial correlation 0.91 with the Eady growth rate). Skillful probabilistic weather forecasts are therefore within reach of a single GPU server.