Saved in:
Bibliographic Details
Main Authors: Filho, Luciano Araujo Dourado, Neto, Almir Moreira da Silva, Miyaguchi, Anthony, David, Rodrigo Pereira, Calumby, Rodrigo Tripodi, Picek, Lukáš
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.10894
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911275851710464
author Filho, Luciano Araujo Dourado
Neto, Almir Moreira da Silva
Miyaguchi, Anthony
David, Rodrigo Pereira
Calumby, Rodrigo Tripodi
Picek, Lukáš
author_facet Filho, Luciano Araujo Dourado
Neto, Almir Moreira da Silva
Miyaguchi, Anthony
David, Rodrigo Pereira
Calumby, Rodrigo Tripodi
Picek, Lukáš
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10894
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DINOv3 as a Frozen Encoder for CRPS-Oriented Probabilistic Rainfall Nowcasting
Filho, Luciano Araujo Dourado
Neto, Almir Moreira da Silva
Miyaguchi, Anthony
David, Rodrigo Pereira
Calumby, Rodrigo Tripodi
Picek, Lukáš
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title DINOv3 as a Frozen Encoder for CRPS-Oriented Probabilistic Rainfall Nowcasting
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.10894