SoftSEEPS improves ML-based precipitation forecasting

Jost Arndt, Utku Isil, Noelia Otero, Rodrigo Almeida, Wojciech Samek +1

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.