Benchmarks, datasets & evaluation

A Regional Benchmark for Deep Learning-Based Hourly Precipitation Nowcasting in Latin America

Adriano Pereira Almeida, Henrique M. J. Barbosa, Sâmia R. Garcia, David John Gagne, Kanghui Zhou, Takuji Kubota, Tomoo USHIO, Shigenori Otsuka, Simon Pfreundschuh, Alan J. P. Calheiros

IEEE Access · 01 January 2026 · China Meteorological Administration (CMA), Colorado State University (incl. CIRA), NSF NCAR / UCAR

Paper

In one sentence. AINPP-PB-LATAM provides a Latin American satellite precipitation nowcasting benchmark (2018–2024) and baselines for five architectures, including AFNO, which excels at continuous skill.

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.

Labels

Topic

Benchmarks, datasets & evaluation, Nowcasting

Type

Benchmark or dataset

Method

Transformer / ViT, CNN / U-Net

Time scale

0–6 h

Domain

Regional

Data

Satellite

Status

Research

Identifiers

DOI:10.1109/access.2026.3670767 OpenAlex:W7133643583

Added

2026-10-22

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.