Partial recovery of meter-scale surface weather

2026-02-26

AI Summary

Current weather analyses struggle to resolve the fine-scale spatial variability of near-surface meteorological variables—such as wind, temperature, and humidity—at tens to hundreds of meters, which is strongly modulated by terrain and land surface characteristics. This study addresses this limitation by integrating sparse in situ observations, ERA5 reanalysis data, and high-resolution remote sensing land surface information within a conditional spatial modeling framework. For the first time over the contiguous United States, it demonstrates the statistical reconstructability of continuous near-surface meteorological fields at 10-meter resolution. The resulting reconstructions reduce wind speed errors by 29% and temperature and dew point errors by 6% relative to ERA5, substantially improving the explained spatial variance at individual time steps and successfully capturing fine-scale surface physical features such as urban heat islands and humidity gradients driven by evapotranspiration.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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 interpretable structure, including urban heat islands, evapotranspiration-driven humidity contrasts, and wind speed differences across land cover types. Our findings expand the frontier of weather modeling by demonstrating a computationally feasible approach to continental-scale meter-resolution inference. More broadly, they illustrate how conditioning coarse dynamical models on static fine-scale features can reveal previously unresolved components of the Earth system.

Problem

• meter-scale weather
• near-surface variability
• land cover
• topography
• weather predictability

Innovation

• meter-scale weather
• data fusion
• high-resolution inference
• near-surface atmospheric modeling
• Earth observation