# Integrating GNSS-Derived Zenith Wet Delay into a Weather Foundation Model Improves Precipitation Forecasting

arXiv: https://arxiv.org/abs/2607.05658 · HTML: https://mlsanity.com/paper/2607.05658/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 47 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 7 of 7)

- [FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2202.11214/) (2022)
- [ClimaX: A foundation model for weather and climate](https://mlsanity.com/paper/2301.10343/) (2023)
- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [Validating Deep Learning Weather Forecast Models on Recent High-Impact Extreme Events](https://mlsanity.com/paper/2404.17652/) (2024)
- [Numerical models outperform AI weather forecasts of record-breaking extremes](https://mlsanity.com/paper/2508.15724/) (2025)
- [Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting](https://mlsanity.com/paper/2605.00850/) (2026)
- [Finetuning a Weather Foundation Model with Lightweight Decoders for Unseen Physical Processes](https://mlsanity.com/paper/2506.19088/) (2025)

## Abstract (arXiv)

Global Navigation Satellite Systems (GNSS), best known for positioning, also serve weather science, as atmospheric water vapour delays their signals. This delay, the Zenith Wet Delay (ZWD), is a direct, all-weather measure of column moisture. Although assimilated into numerical weather prediction for decades, ZWD is not yet used by leading Machine Learning Weather Models (MLWM), despite addressing a known deficiency: the underestimation of severe precipitation. Here we present the first integration of GNSS-derived ZWD into Aurora, a state-of-the-art weather foundation model. Our extended Aurora learns ZWD with skill comparable to its pretrained variables. More importantly, including ZWD systematically improves forecasts when fine-tuning for 6-hour accumulated precipitation. Gains grow with severity, reaching an 8.8% increase in Equitable Threat Score at the 99th percentile, while the precipitation power spectrum becomes more realistic at synoptic and planetary scales. GNSS observations therefore encode information that MLWM can exploit for high-impact precipitation.