Wavelet loss improves high resolution weather forecast accuracy and detail
Scale-aware and spatially-localised optimisation of kilometre-scale MLWP models
Machine Learning
Summary
Predicting weather accurately at very fine scales is tough because weather changes at many sizes and places. The authors developed a new way to train weather models using a wavelet-based loss function that looks at weather patterns by their size, location, and direction. This helps keep important details and sharp features in forecasts, like rain intensity, without losing accuracy at specific points. They showed this method works better than older ways on a combined global and regional weather prediction model.
What this means in practice
- •For weather forecasting teams: Train high-resolution weather models that better preserve detailed atmospheric patterns and improve rain forecast sharpness over regional scales.
- •For remote sensing developers: Create enhanced atmospheric data analysis tools using localized scale-and-orientation aware constraints for improved spatial accuracy.
Authors
James Chappell, Sophie Luise Arana, Jack Bowyer, Alejandro Coca-Castro, Evangeline Corcoran, Eric G. Daub, Tom Dunstan, Noushin Eftekhari, Anna-Louise Ellis, J. Scott Hosking, Manvendra Janmaijaya, David Salvador-Jasin, Ben Shipway, Nathan Simpson, Oliver Strickson, David Walters
Abstract
Preserving fine-scale structure without degrading spatial accuracy is a central challenge for kilometre-scale machine-learning weather prediction (MLWP). We introduce a loss based on the dual-tree complex wavelet transform that constrains atmospheric fields jointly by scale, location, and orientation. We evaluate its performance using an experimental joint global--regional FastNet configuration, which produces \SI{1.5}{km} forecasts over the UK alongside $\sim$\SI{31}{km} global forecasts. Relative to both mean-squared error (MSE) and an FFT-based spectral objective, the wavelet loss substantially improves spectral fidelity. Compared with MSE training, it maintains similar pointwise performance, improves neighbourhood-based verification, and produces sharper precipitation fields with more realistic intensity distributions. These results demonstrate that spatially localised wavelet constraints can preserve multiscale atmospheric structure while largely avoiding the loss of pointwise accuracy associated with globally supported spectral objectives.