Continuous latent representations for modeling precipitation with deep learning
This addresses simulation and bias correction issues in hydrology, but appears incremental as it builds on existing transformation approaches.
The paper tackles the challenge of modeling sparse and discontinuous precipitation data by developing a smooth, continuous latent variable called pseudo-precipitation (PP) using deep learning, and applies it to downscale precipitation from 100 km to 25 km resolution.
The sparse and spatio-temporally discontinuous nature of precipitation data presents significant challenges for simulation and statistical processing for bias correction and downscaling. These include incorrect representation of intermittency and extreme values (critical for hydrology applications), Gibbs phenomenon upon regridding, and lack of fine scales details. To address these challenges, a common approach is to transform the precipitation variable nonlinearly into one that is more malleable. In this work, we explore how deep learning can be used to generate a smooth, spatio-temporally continuous variable as a proxy for simulation of precipitation data. We develop a normally distributed field called pseudo-precipitation (PP) as an alternative for simulating precipitation. The practical applicability of this variable is investigated by applying it for downscaling precipitation from \(1\degree\) (\(\sim\) 100 km) to \(0.25\degree\) (\(\sim\) 25 km).