This paper presents a deep learning architecture for nowcasting of precipitation almost globally every 30 min with a 4-hour lead time. The architecture fuses a U-Net and a convolutional long short-term memory (LSTM) neural network and is trained using data from the Integrated MultisatellitE Retrievals for GPM (IMERG) and a few key precipitation drivers from the Global Forecast System (GFS). The impacts of different training loss functions, including the mean-squared error (regression) and the focal-loss (classification), on the quality of precipitation nowcasts are studied. The results indicate that the regression network performs well in capturing light precipitation (below 1.6 mm/hr), but the classification network can outperform the regression network for nowcasting of precipitation extremes (>8 mm/hr), in terms of the critical success index (CSI).. Using the Wasserstein distance, it is shown that the predicted precipitation by the classification network has a closer class probability distribution to the IMERG than the regression network. It is uncovered that the inclusion of the physical variables can improve precipitation nowcasting, especially at longer lead times in both networks. Taking IMERG as a relative reference, a multi-scale analysis in terms of fractions skill score (FSS), shows that the nowcasting machine remains skillful (FSS > 0.5) at the resolution of 10 km compared to 50 km for GFS. For precipitation rates greater than 4~mm/hr, only the classification network remains FSS-skillful on scales greater than 50 km within a 2-hour lead time.

翻译：本文提出了一种深度学习架构，用于在几乎全球范围内以30分钟为间隔、4小时提前期进行降水近实时预测。该架构融合了U-Net和卷积长短期记忆神经网络，并利用GPM多卫星集成数据反演以及全球预报系统中的若干关键降水驱动因子进行训练。研究对比了均方误差（回归）和焦点损失（分类）等不同训练损失函数对降水近实时预测质量的影响。结果表明，回归网络在捕捉弱降水（低于1.6毫米/小时）方面表现良好，但分类网络在临界成功指数指标下，对极端降水（>8毫米/小时）的近实时预测性能优于回归网络。通过使用Wasserstein距离分析，显示分类网络预测的降水量类别概率分布比回归网络更接近IMERG数据。研究发现，引入物理变量可改善降水近实时预测效果，尤其在较长提前期下对两种网络均有改进。以IMERG为相对参考，基于分数技巧得分的多尺度分析表明，该预测机器在10公里分辨率下具有技巧性（FSS>0.5），优于GFS的50公里。对于降水率大于4毫米/小时的情况，仅分类网络能在2小时提前期内保持50公里以上尺度的FSS技巧性。