Efficient modeling of sub-kilometer surface wind with Gaussian processes and neural networks

arXiv:2405.12614v1 Announce Type: cross
Abstract: Accurately representing surface weather at the sub-kilometer scale is crucial for optimal decision-making in a wide range of applications. This motivates the use of statistical techniques to provide accurate and calibrated probabilistic predictions at a lower cost compared to numerical simulations. Wind represents a particularly challenging variable to model due to its high spatial and temporal variability. This paper presents a novel approach that integrates Gaussian processes (GPs) and neural networks to model surface wind …

abstract applications arxiv cost decision gaussian processes making modeling networks neural networks numerical physics.ao-ph predictions processes scale simulations stat.ap statistical stat.ml surface type weather wind