Multi‐Task Learning for Simultaneous Retrievals of Passive Microwave Precipitation Estimates and Rain/No‐Rain Classification

Abstract

Satellite‐based precipitation estimations provide frequent, large‐scale measurements. Deep learning has recently shown significant potential for improving estimation accuracy. Most studies have employed a two‐stage framework, which is a sequential architecture of a rain/no‐rain binary classification task followed by a rain rate regression task. This study proposes a novel precipitation retrieval framework in which these two tasks are simultaneously trained using multi‐task learning approach (MTL). Furthermore, a novel network architecture and loss function were designed to reap the benefits of MTL. The proposed two‐task model successfully achieved a better performance than the conventional single‐task model possibly due to efficient knowledge transfer between tasks. Furthermore, the product intercomparison showed that our product outperformed existing products in rain rate retrieval and also yielded better skills in the rain/no‐rain retrieval task.

Exploring Variable Synergy in Multi-Task Deep Learning for Hydrological Modeling

“…Li et al (2023) improved streamflow modeling with spatiotemporal DL models and an MTL approach in three basins. Building on these advancements, MTL has been adapted for a variety of hydrological targets, such as soil moisture (satellite and local in situ) (Liu et al, 2023), satellite precipitation estimation (rain/norain classification and rain rate) (Bannai et al, 2023), and aquifer transmissivity and storativity (Vu & Jardani, 2022). However, as the trend of modeling multiple variables has emerged, the precise benefits of MTL and how it behaves in terms of temporal and spatial generalization still not be fully understanded, particularly in scenarios with large-sample basins.…”

Deep Learning for Seasonal Prediction of Summer Precipitation Levels in Eastern China

“…On the one hand, the extreme data might be under-fitting because of their small proportion in the training samples, which would result in their weak forecast skills (Chen & Wang, 2022). On the other hand, these extreme data can greatly increase the training loss (Bannai et al, 2023), and thus mislead the direction of parameters optimization.…”