Speaker:<\/strong> Tommaso Grassi (Max Planck for Extraterrestrial Physics)<\/p>\n\n\n\n Abstract:<\/p>\n\n\n\n Astrophysical numerical models encounter substantial computational challenges when integrating complex, time-dependent chemistry with physical processes. To address these issues, I will present the use of autoencoders for the dimensionality reduction of chemical networks, enabling efficient solutions with standard ODE solvers while preserving key network features. Additionally, I will discuss the application of interpretable machine learning techniques to connect synthetic spectra with model parameters, facilitating the assessment of information retention in observational data.<\/p>\n","protected":false},"excerpt":{"rendered":"