A regional benchmark for deep learning-based hourly precipitation nowcasting in Latin America
Almeida, A. P., Barbosa, H. M., Garcia, S. R., Gagne, D. J., Zhou, K., et al. (2026). A regional benchmark for deep learning-based hourly precipitation nowcasting in Latin America. IEEE Access, doi:https://doi.org/10.1109/access.2026.3670767
| Title | A regional benchmark for deep learning-based hourly precipitation nowcasting in Latin America |
|---|---|
| Genre | Article |
| Author(s) | A. P. Almeida, H. M. Barbosa, S. R. Garcia, David John Gagne, K. Zhou, T. Kubota, T. Ushio, S. Otsuka, S. Pfreundschuh, A. J. Calheiros |
| Abstract | Accurate short-term precipitation forecasting is critical for Latin America, but the region lacks a standardized framework to evaluate data-driven approaches due to the sparse coverage in the ground. This study introduces the Artificial Intelligence for Nowcasting Pilot Project (AINPP) Precipitation Benchmark (AINPP-PB-LATAM), providing curated datasets and a scalable, optimized training pipeline designed to accelerate deep learning development in high-performance computing environments. Beyond establishing a baseline using seven years of satellite-based data (2018–2024), the framework reduces engineering barriers, enabling researchers to focus on fine-tuning strategies to extract the full predictive capacity of models for regional specificities. As a demonstration use case, we trained and evaluated five deep learning architectures, AFNO, Inception-V4, ResNet-50, U-Net, and Xception, comparing them against Lagrangian Persistence and the operational AI Nowcast. The results reveal critical trade-offs: spectral methods like AFNO excel in continuous skill by capturing large-scale dependencies, while convolutional architectures offer robust categorical performance. However, pixel-wise optimization challenges persist, with systematic under-prediction of heavy rainfall. By providing open-access code and optimized baseline implementations for distributed computing, AINPP-PB-LATAM establishes a scalable foundation for collaborative research, facilitating the advancement of operational AI-based nowcasting and transferability assessments in data-scarce regions. |
| Publication Title | IEEE Access |
| Publication Date | Jan 1, 2026 |
| Publisher's Version of Record | https://doi.org/10.1109/access.2026.3670767 |
| OpenSky Citable URL | https://n2t.net/ark:/85065/d72b93kg |
| OpenSky Listing | View on OpenSky |
| CISL Affiliations | MILES |