English

Multimodal Atmospheric Super-Resolution With Deep Generative Models

Machine Learning 2025-12-17 v2 Geophysics

Abstract

Score-based diffusion modeling is a generative machine learning algorithm that can be used to sample from complex distributions. They achieve this by learning a score function, i.e., the gradient of the log-probability density of the data, and reversing a noising process using the same. Once trained, score-based diffusion models not only generate new samples but also enable zero-shot conditioning of the generated samples on observed data. This promises a novel paradigm for data and model fusion, wherein the implicitly learned distributions of pretrained score-based diffusion models can be updated given the availability of online data in a Bayesian formulation. In this article, we apply such a concept to the super-resolution of a high-dimensional dynamical system, given the real-time availability of low-resolution and experimentally observed sparse sensor measurements from multimodal data. Additional analysis on how score-based sampling can be used for uncertainty estimates is also provided. Our experiments are performed for a super-resolution task that generates the ERA5 atmospheric dataset given sparse observations from a coarse-grained representation of the same and/or from unstructured experimental observations of the IGRA radiosonde dataset. We demonstrate accurate recovery of the high dimensional state given multiple sources of low-fidelity measurements. We also discover that the generative model can balance the influence of multiple dataset modalities during spatiotemporal reconstructions.

Keywords

Cite

@article{arxiv.2506.22780,
  title  = {Multimodal Atmospheric Super-Resolution With Deep Generative Models},
  author = {Dibyajyoti Chakraborty and Haiwen Guan and Jason Stock and Troy Arcomano and Guido Cervone and Romit Maulik},
  journal= {arXiv preprint arXiv:2506.22780},
  year   = {2025}
}
R2 v1 2026-07-01T03:37:37.957Z