Apeliotes: A Diffusion-Based Modeling Framework for km-scale Multi-Level Atmospheric Fields
Machine LearningComputational Engineering, Finance, and Science
Summary
The authors developed Apeliotes, a system that uses machine learning to create detailed weather forecasts at a local scale. Instead of using traditional, slow computer simulations, their model learns from global weather data and then zooms in on smaller regions to predict various weather factors accurately. Their tests show Apeliotes can predict things like wind and temperature very closely to actual measurements. This approach helps provide more detailed weather information in places where such data is hard to get.
Authors
Evangelia Rafaela Frastali, Achyut Paudel, Maryam Golbazi, Frank Liu
Abstract
High-resolution atmospheric data are required to resolve mesoscale and localized meteorological structures, however such datasets remain limited in many regions of the world. Existing high-resolution weather products are typically produced through dynamical downscaling, which is computationally expensive and difficult to scale across locations, variables, and forecast scenarios. These limitations motivate machine-learning-based downscaling systems that can generate multiple weather variables stochastically while producing new high-resolution fields directly. In this paper we present Apeliotes, a framework for high-resolution weather forecasting. Built on the global re-analysis atmospheric data, a pre-trained global weather foundation model, and a regionally trained generative diffusion model, Apeliotes not only provides accurate kilometer-scale weather variables, but also multi-level atmospheric fields which are not directly available in the existing global atmospheric data. Our comprehensive evaluation demonstrates that Apeliotes achieves highly competitive performance. The model predicts vertical wind profile with less than 3\% error between truth and predicted fields, achieving correlations of 0.91 for 10-m wind speed and 0.99 for 2-m temperature, with NRMSE values of 0.42 and 0.17, respectively.