A spatial–temporal graph deep learning model for urban flood nowcasting leveraging heterogeneous community features
Problem
Predicting near-future urban flood conditions as an extreme weather event unfolds, to improve situational awareness.
Why it matters
Timely flood predictions can protect lives and property during rapidly developing urban floods.
What the AI did
An attention-based spatial–temporal graph convolution network (ASTGCN) integrates real-time heterogeneous data streams, including physics-based and human-sensed features, to nowcast flood status.
Results
not stated in source
Impact
Evidence supports a deep-learning framework claimed to improve flood nowcasting; adoption not stated in source.
Record
| Venue | Scientific Reports |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Hamed Farahmand, Yuanchang Xu, Ali Mostafavi |
| Citations | 79 (OpenAlex, at import time) |
| References | 92 |
| Model or method | ASTGCN (attention-based spatial–temporal graph convolution network) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41598-023-32548-x |
| Open access | gold |
| Keywords | flood nowcasting, graph neural networks, deep learning, urban flooding, real-time data |
Importance rating
significant — thousands to millions affected
Flood nowcasting to enhance situational awareness during extreme weather; applied to Hurricane Harvey in Harris County, Texas; no quantified scale or outcome metrics stated.
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
|