# Improving global precipitation forecasts with an AI weather model trained on satellite observations

arXiv: https://arxiv.org/abs/2609.03210 · HTML: https://mlsanity.com/paper/2609.03210/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 42 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale](https://mlsanity.com/paper/2507.12144/) (2025)
- [Can AI weather models predict out-of-distribution gray swan tropical cyclones?](https://mlsanity.com/paper/2410.14932/) (2024)
- [A Practical Probabilistic Benchmark for AI Weather Models](https://mlsanity.com/paper/2401.15305/) (2024)
- [An Operational Deep Learning System for Satellite-Based High-Resolution Global Nowcasting](https://mlsanity.com/paper/2510.13050/) (2025)
- [Decision-oriented benchmarking to transform AI weather forecast access: Application to the Indian monsoon](https://mlsanity.com/paper/2602.03767/) (2026)

## Abstract (arXiv)

Precipitation forecasts shape decision-making across the global economy, particularly in sectors such as agriculture. However, unlike variables such as temperature, precipitation is highly intermittent and localized, making it difficult to forecast. While recent advances in AI weather prediction systems have enabled them to surpass physical models on globally averaged metrics, improvements in mean error rarely translate to actionable forecasts of severe flooding or dry crop fields. Furthermore, most of these models are trained and evaluated against a reanalysis data product, ERA5, which has well-known biases. Here we retrain AIFS, ECMWF's widely-used, open-source operational 0.25deg probabilistic graph-transformer weather model, on satellite-based precipitation observations. Our model, Laxmi, improves global probabilistic accuracy by 19% and resolves systematic distributional biases in ERA5. Specifically, Laxmi reduces drizzle overprediction by 33% for amounts less than 3 mm per day. It also mitigates extreme rainfall underprediction, improving the global 95th percentile Brier skill score by 57%. Across a case study of 10 Indian tropical storms, Laxmi delivered the most accurate forecast of 150 mm event-total precipitation in 7 events, compared to 1 for AIFS and 2 for the leading physical model, IFS. Our results demonstrate that incorporating observation-based precipitation data directly into training can substantially improve forecasts.