A Generative Diffusion Model for Probabilistic Ensembles of Precipitation Maps Conditioned on Multisensor Satellite Observations

TL;DR

This paper introduces a diffusion-based generative model that produces probabilistic precipitation maps conditioned on satellite data, accurately capturing spatial properties and uncertainty for improved weather prediction.

Contribution

It presents a novel diffusion model for generating probabilistic precipitation ensembles conditioned on multisensor satellite observations, enhancing spatial coherence and uncertainty quantification.

Findings

Generated ensembles match statistical properties of reference fields.

High spatial coherence with reference precipitation maps (correlation 0.82).

Ensemble dispersion effectively measures estimation uncertainty.

Abstract

A generative diffusion model is used to produce probabilistic ensembles of precipitation intensity maps at the 1-hour 5-km resolution. The generation is conditioned on infrared and microwave radiometric measurements from the GOES and DMSP satellites and is trained with merged ground radar and gauge data over southeastern United States. The generated precipitation maps reproduce the spatial autocovariance and other multiscale statistical properties of the gauge-radar reference fields on average. Conditioning the generation on the satellite measurements allows us to constrain the magnitude and location of each generated precipitation feature. The mean of the 128- member ensemble shows high spatial coherence with the reference fields with 0.82 linear correlation between the two. On average, the coherence between any two ensemble members is approximately the same as the coherence between any ensemble member and the ground reference, attesting that the ensemble dispersion is a proper measure of the estimation uncertainty. From the generated ensembles we can easily derive the probability of the precipitation intensity exceeding any given intensity threshold, at the 5-km resolution of the generation or at any desired aggregated resolution.