English

Data-Driven Invertible Neural Surrogates of Atmospheric Transmission

Machine Learning 2024-05-01 v1 Computer Vision and Pattern Recognition Atmospheric and Oceanic Physics

Abstract

We present a framework for inferring an atmospheric transmission profile from a spectral scene. This framework leverages a lightweight, physics-based simulator that is automatically tuned - by virtue of autodifferentiation and differentiable programming - to construct a surrogate atmospheric profile to model the observed data. We demonstrate utility of the methodology by (i) performing atmospheric correction, (ii) recasting spectral data between various modalities (e.g. radiance and reflectance at the surface and at the sensor), and (iii) inferring atmospheric transmission profiles, such as absorbing bands and their relative magnitudes.

Keywords

Cite

@article{arxiv.2404.19605,
  title  = {Data-Driven Invertible Neural Surrogates of Atmospheric Transmission},
  author = {James Koch and Brenda Forland and Bruce Bernacki and Timothy Doster and Tegan Emerson},
  journal= {arXiv preprint arXiv:2404.19605},
  year   = {2024}
}

Comments

Manuscript accepted for presentation and publication at the 2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)