SatRain is a new open benchmark that combines multi-sensor satellite observations with gauge-corrected radar references and a standardized evaluation protocol for machine learning-based precipitation estimation and detection.
Title resolution pending
2 Pith papers cite this work, alongside 863 external citations. Polarity classification is still indexing.
2
Pith papers citing it
863
external citations · external index
representative citing papers
JWS is a single-stage diffusion model for precipitation nowcasting that operates directly in pixel space, using Masked Asynchronous Diffusion and a simple distributional objective for efficient few-step generation, achieving state-of-the-art results on SEVIR and MeteoNet.
citing papers explorer
-
A Benchmark Dataset for Satellite-Based Estimation and Detection of Rain
SatRain is a new open benchmark that combines multi-sensor satellite observations with gauge-corrected radar references and a standardized evaluation protocol for machine learning-based precipitation estimation and detection.
-
Just Weather Scoring: Efficient End-to-end Nowcasting with Distributional Diffusion
JWS is a single-stage diffusion model for precipitation nowcasting that operates directly in pixel space, using Masked Asynchronous Diffusion and a simple distributional objective for efficient few-step generation, achieving state-of-the-art results on SEVIR and MeteoNet.