Diffusion-Based Refinement for Kilometer-Scale Probabilistic Precipitation Nowcasting
Abstract
Localized extreme precipitation is a major trigger of urban flash floods and landslides, yet producing nowcasts that combine fine spatial detail with probabilistic uncertainty remains challenging. Here we introduce exPreCast-ENS, a conditional residual diffusion framework that transforms the deterministic 4 km radar nowcaster exPreCast into a 1 km probabilistic ensemble while correcting systematic forecast errors. Conditioning on both the forecast and preceding radar observations lets the ensemble-mean correct the baseline rather than perturb it, while members represent unresolved fine-scale variability. Over the Korean Peninsula, skill improves with ensemble size. In two high-impact events in 2023, a 30-member ensemble recovers 38-47% of heavy-rain pixels missed by exPreCast while retaining approximately 95% of its correct detections and alarming on under 1% of the pixels it correctly left clear. The method generates a 1-h forecast in 3.4 s on a single GPU and yields consistent improvements on the French regional MeteoNet radar dataset.
Related
- Precipitation nowcasting model based on multi-source data fusion and efficient additive attention
- Wet-Biased Data Pipelines Mislead the Training and Evaluation of Generative Precipitation Nowcasting
- GenONet: A Generative operator Network for High-Resolution Precipitation Nowcasting
- SwAIther-Precip: Lead-Time-Aware Bias Correction Enables Kilometer-Scale Downscaling of Global AI Precipitation Forecasts over Switzerland
- Efficient Analog-Initialized Latent Transport for Spatially Coherent Probabilistic Downscaling from Global to Kilometer Scales
BibTeX
@misc{park2026diffusionbased,
title = {{Diffusion-Based Refinement for Kilometer-Scale Probabilistic Precipitation Nowcasting}},
author = {Dohyun Park and Changhoon Song and Tengyuan Chang and Yoo-Geun Ham and Youngjoon Hong},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.30205},
eprint = {2608.30205},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.30205},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Diffusion-Based Refinement for Kilometer-Scale Probabilistic Precipitation Nowcasting
AU - Dohyun Park
AU - Changhoon Song
AU - Tengyuan Chang
AU - Yoo-Geun Ham
AU - Youngjoon Hong
PY - 2026
DA - 2026/08/31
PB - arXiv
DO - 10.48550/arxiv.2608.30205
UR - https://arxiv.org/abs/2608.30205
AB - Localized extreme precipitation is a major trigger of urban flash floods and landslides, yet producing nowcasts that combine fine spatial detail with probabilistic uncertainty remains challenging. Here we introduce exPreCast-ENS, a conditional residual diffusion framework that transforms the deterministic 4 km radar nowcaster exPreCast into a 1 km probabilistic ensemble while correcting systematic forecast errors. Conditioning on both the forecast and preceding radar observations lets the ensemble-mean correct the baseline rather than perturb it, while members represent unresolved fine-scale variability. Over the Korean Peninsula, skill improves with ensemble size. In two high-impact events in 2023, a 30-member ensemble recovers 38-47% of heavy-rain pixels missed by exPreCast while retaining approximately 95% of its correct detections and alarming on under 1% of the pixels it correctly left clear. The method generates a 1-h forecast in 3.4 s on a single GPU and yields consistent improvements on the French regional MeteoNet radar dataset.
ER -