Global Precipitation Nowcasting of Integrated Multi-satellitE Retrievals for GPM: A U-Net Convolutional LSTM Architecture
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 106 references that are in the map. First posted on arXiv 20 Jul 2023.
Builds on
16 of 106 references.
References · 16
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
- 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
- 2013Generating Sequences With Recurrent Neural Networkscited by 549
- 2019Video Instance Segmentationcited by 391
- 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 308
- 2021PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learningcited by 181
- 2017Deep Learning for Precipitation Nowcasting: A Benchmark and A New Modelcited by 180
- 2016SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networkscited by 134
- 2020MetNet: A Neural Weather Model for Precipitation Forecastingcited by 128
- 2020SmaAt-UNet: Precipitation Nowcasting using a Small Attention-UNet Architecturecited by 71
4 more
- 2019Machine Learning for Precipitation Nowcasting from Radar Imagescited by 56
- 2021Nowcasting-Nets: Deep Neural Network Structures for Precipitation Nowcasting Using IMERGcited by 10
- 2020Regularized Variational Data Assimilation for Bias Treatment using the Wasserstein Metriccited by 2
- 2022Spatiotemporal Classification with limited labels using Constrained Clustering for large datasetscited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.