English

DINOv3 as a Frozen Encoder for CRPS-Oriented Probabilistic Rainfall Nowcasting

Computer Vision and Pattern Recognition 2025-11-20 v2 Artificial Intelligence

Abstract

This paper proposes a competitive and computationally efficient approach to probabilistic rainfall nowcasting. A video projector (V-JEPA Vision Transformer) associated to a lightweight probabilistic head is attached to a pre-trained satellite vision encoder (DINOv3-SAT493M) to map encoder tokens into a discrete empirical CDF (eCDF) over 4-hour accumulated rainfall. The projector-head is optimized end-to-end over the Ranked Probability Score (RPS). As an alternative, 3D-UNET baselines trained with an aggregate Rank Probability Score and a per-pixel Gamma-Hurdle objective are used. On the Weather4Cast 2025 benchmark, the proposed method achieved a promising performance, with a CRPS of 3.5102, which represents \approx 26% in effectiveness gain against the best 3D-UNET.

Cite

@article{arxiv.2511.10894,
  title  = {DINOv3 as a Frozen Encoder for CRPS-Oriented Probabilistic Rainfall Nowcasting},
  author = {Luciano Araujo Dourado Filho and Almir Moreira da Silva Neto and Anthony Miyaguchi and Rodrigo Pereira David and Rodrigo Tripodi Calumby and Lukáš Picek},
  journal= {arXiv preprint arXiv:2511.10894},
  year   = {2025}
}
R2 v1 2026-07-01T07:36:48.631Z