SoftSEEPS enhances precipitation forecasts with differentiable scoring
SoftSEEPS improves ML-based precipitation forecasting
Machine Learning
Summary
Forecasting rainfall is tricky, and standard ways to measure the accuracy of forecasts are often not easy for computers to use when learning. The authors created SoftSEEPS, a new method that smooths out a popular evaluation score so a machine learning model can train directly with it. They tested this on weather data to improve rain predictions from a simpler forecasting model. Their approach works well when combined with traditional error measures without losing much accuracy.
What this means in practice
- •For weather forecasting teams: Improve rainfall prediction accuracy by training models directly on a differentiable approximation of a precipitation forecast evaluation score.
- •For climate impact analysts: Use enhanced precipitation forecasts to better model hydrological impacts and extreme weather risks through improved machine learning training techniques.
Authors
Jost Arndt, Utku Isil, Noelia Otero, Rodrigo Almeida, Wojciech Samek, Jackie Ma
Abstract
In this paper we have developed a differentiable approximation of the well-known SEEPS score, which we name SoftSEEPS. This allows the training of a Machine Learning model to forecast precipitation directly. We test SoftSEEPS on the IMERG dataset (0.1 degree resolution) by training a decoder for precipitation on the latent space of a pre-trained low-resolution forecasting model. Combining SoftSEEPS and RMSE in a joint objective is possible with marginal trade-offs in either metric.