Abstract: Atmospheric inversion refers to the task of recovering a potentially spatio-temporal source of atmospheric emissions from concentration measurements. The atmospheric transport of particles is described by a linear equation, resulting in an inverse problem formulation for source estimation. Since this problem is highly ill-posed, obtaining physically meaningful results requires appropriate regularization. In this talk, I will introduce two rather unconventional regularization approaches: a deep image prior for the spatio-temporal source, and a Gaussian process prior for correcting transport model errors.
When: 10:00 a.m. Friday, November 14
Where: The session will occur physically at the Institute of Information Theory and Automation (UTIA) in room 45 (café). For directions to the institute, please refer to the following link: https://zoi.utia.cas.cz/index.php/contact
Language: Czech (if you require English, please let us know in advance)
