![[2602.23146] Partial recovery of meter-scale surface weather](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.23146] Partial recovery of meter-scale surface weather
Summary
The paper discusses a method for recovering meter-scale surface weather data by integrating sparse surface measurements with high-resolution Earth observation data, improving weather forecasting accuracy.
Why It Matters
Understanding meter-scale weather variability is crucial for accurate weather forecasting and climate modeling. This research demonstrates a novel approach that could enhance predictive capabilities and inform better responses to weather-related challenges.
Key Takeaways
- Meter-scale weather variability can be statistically recovered from existing observations.
- The proposed method reduces wind error by 29% and temperature error by 6%.
- The findings highlight the importance of integrating fine-scale features into weather models.
- Urban heat islands and humidity contrasts are observable through the new method.
- This research expands the frontiers of weather modeling and forecasting.
Computer Science > Machine Learning arXiv:2602.23146 (cs) [Submitted on 26 Feb 2026] Title:Partial recovery of meter-scale surface weather Authors:Jonathan Giezendanner, Qidong Yang, Eric Schmitt, Anirban Chandra, Daniel Salles Civitarese, Johannes Jakubik, Jeremy Vila, Detlef Hohl, Campbell Watson, Sherrie Wang View a PDF of the paper titled Partial recovery of meter-scale surface weather, by Jonathan Giezendanner and 9 other authors View PDF HTML (experimental) Abstract:Near-surface atmospheric conditions can differ sharply over tens to hundreds of meters due to land cover and topography, yet this variability is absent from current weather analyses and forecasts. It is unclear whether such meter-scale variability reflects irreducibly chaotic dynamics or contains a component predictable from surface characteristics and large-scale atmospheric forcing. Here we show that a substantial, physically coherent component of meter-scale near-surface weather is statistically recoverable from existing observations. By conditioning coarse atmospheric state on sparse surface station measurements and high-resolution Earth observation data, we infer spatially continuous fields of near-surface wind, temperature, and humidity at 10 m resolution across the contiguous United States. Relative to ERA5, the inferred fields reduce wind error by 29% and temperature and dewpoint error by 6%, while explaining substantially more spatial variance at fixed time steps. They also exhibit physically int...