Physical Attention-Gated Spatial-Temporal Predictive Network for Weather Forecasting
In one sentence. PastNet uses attention-gated convolutions for spatiotemporal forecasting on synthetic and real datasets, outperforming baselines on weather-style prediction.
Abstract
Spatial-temporal sequence prediction is one of the hottest topics in the field of deep learning due to its wide range of potential applications in video-like data processing, specifically weather forecasting. Since most spatial-temporal observations evolve under physical laws, we adopt an attentional gating scheme to leverage the dynamic patterns captured by tailored convolution structures and propose a novel neural network, PastNet, to achieve accurate predictions. By highlighting useful parts of the whole feature map, the gating units help increase the efficiency of the architecture. Extensive experiments conducted on synthetic and real-world datasets reveal that PastNet bears the ability to accomplish this task with better performance than baseline methods.
Labels
- Topic
- Global medium-range NWP
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 6 h–3 days
- Data
- Other
- Status
- Research
- Identifiers
- DOI:10.3390/math11061330 OpenAlex:W4323848639
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.