Precipitation nowcasting of satellite data using physically-aligned neural networks
Catão, Antônio, Poveda, Melvin, Voltarelli, Leonardo, Orenstein, Paulo
–arXiv.org Artificial Intelligence
Accurate short-term precipitation forecasts predominantly rely on dense weather-radar networks, limiting operational value in places most exposed to climate extremes. We present TUPANN (Transferable and Universal Physics-Aligned Nowcasting Network), a satellite-only model trained on GOES-16 RRQPE. Unlike most deep learning models for nowcasting, TUPANN decomposes the forecast into physically meaningful components: a variational encoder-decoder infers motion and intensity fields from recent imagery under optical-flow supervision, a lead-time-conditioned MaxViT evolves the latent state, and a differentiable advection operator reconstructs future frames. We evaluate TUPANN on both GOES-16 and IMERG data, in up to four distinct climates (Rio de Janeiro, Manaus, Miami, La Paz) at 10-180min lead times using the CSI and HSS metrics over 4-64 mm/h thresholds. Comparisons against optical-flow, deep learning and hybrid baselines show that TUPANN achieves the best or second-best skill in most settings, with pronounced gains at higher thresholds. Training on multiple cities further improves performance, while cross-city experiments show modest degradation and occasional gains for rare heavy-rain regimes. The model produces smooth, interpretable motion fields aligned with numerical optical flow and runs in near real time due to the low latency of GOES-16. These results indicate that physically aligned learning can provide nowcasts that are skillful, transferable and global.
arXiv.org Artificial Intelligence
Nov-12-2025
- Country:
- Africa (0.04)
- Asia
- Middle East > Jordan (0.04)
- Russia (0.04)
- Europe
- Italy > Calabria
- Catanzaro Province > Catanzaro (0.04)
- Netherlands > South Holland
- Delft (0.04)
- Portugal > Braga
- Braga (0.04)
- Russia (0.04)
- Switzerland (0.04)
- Italy > Calabria
- North America
- Canada > Ontario
- Toronto (0.04)
- United States
- California > San Francisco County
- San Francisco (0.14)
- Florida (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- California > San Francisco County
- Canada > Ontario
- South America
- Bolivia > La Paz Department
- Pedro Domingo Murillo Province > La Paz (0.04)
- Brazil
- Amazonas > Manaus (0.04)
- Rio de Janeiro > Rio de Janeiro (0.36)
- Bolivia > La Paz Department
- Genre:
- Research Report (1.00)
- Industry:
- Energy (0.47)
- Technology: