Comment on gmd-2022-213

Abstract

Systematic biases and coarse resolutions are major limitations of current precipitation datasets. Many deep learning (DL) based studies have been conducted for precipitation bias correction and downscaling. However, it is still challenging for the current approaches to handle complex features of hourly precipitation, resulting in incapability of reproducing small scale features, such as extreme events. This study developed a customized DL model by incorporating customized loss functions, multitask learning, and physically relevant covariates to bias correct and downscale hourly precipitation data. We designed six scenarios to systematically evaluate the added values of weighted loss functions, multi-task learning, and atmospheric covariates compared to the regular DL and statistical approaches. The model was trained and tested using the Modern-Era Retrospective analysis for Research and Applications version 2 (MERRA2) reanalysis and the Stage IV radar observations over northern coastal region of Gulf of Mexico. We found that all the scenarios with weighted loss functions performed notably better than the other scenarios with conventional loss functions and a quantile mapping-based approach at hourly, daily, and monthly time scales as well as extremes. Multitask learning showed improved performance on capturing hourly precipitation climatology, aggregated precipitation at daily and monthly scales, and detailed features of extreme events, while the improvement is not as large as from weighted loss functions. Accounting for atmospheric covariates further improved the model performance for capturing extreme events. We show that the customized DL model can better downscale and bias correct precipitation datasets and provide improved precipitation estimates at fine spatial and temporal resolutions where regular DL and statistical methods experiencing challenges.