3D-UNet-LSTM: A Deep Learning-Based Radar Echo Extrapolation Model for Convective Nowcasting
Problem
Predicting the very short-term evolution of convective storm systems by extrapolating radar reflectivity images.
Why it matters
Accurate convective nowcasting underpins severe weather warnings that protect lives and property.
What the AI did
A 3D-UNet-LSTM model with an extractor-forecaster architecture: 3D-UNet extracts spatiotemporal features from radar images, and a Seq2Seq network with ConvLSTM layers iteratively generates forecasts.
Results
not stated in source
Impact
The paper proposes a model claimed to combine predictive flexibility with temporal dependency capture, but the abstract gives no measured results.
Record
| Venue | Remote Sensing |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Shiqing Guo, Nengli Sun, Yanle Pei, Qian Li |
| Citations | 40 (OpenAlex, at import time) |
| References | 42 |
| Model or method | 3D-UNet-LSTM (3D-UNet + ConvLSTM Seq2Seq) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/rs15061529 |
| Open access | gold |
| Keywords | radar echo extrapolation, deep learning, convective nowcasting, ConvLSTM, 3D-UNet |
Importance rating
significant — thousands to millions affected
Convective nowcasting supports severe weather warnings protecting lives and property; broad societal benefit but abstract states no scale.
More in Climate & Environment
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Learning skillful medium-range global weather forecasting | 2023 | 1,416 |
8
|
| 2 | Accurate medium-range global weather forecasting with 3D neural networks | 2023 | 1,631 |
8
|
| 3 | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast | 2023 | 355 |
8
|
| 4 | Skilful nowcasting of extreme precipitation with NowcastNet | 2023 | 451 |
8
|
| 5 | Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects | 2023 | 378 |
8
|