Continuing the recent theme of the CosmicAI talks, Dr. Qezlou discusses “surrogate modeling” for inferring cosmological and astrophysical parameters using machine learning. The available and upcoming observations require accurate simulations of the complex physical processes, including the non-linear gravity and gas dynamics. Using these detailed simulations at each Monte Carlo Markov Chain (MCMC) step in an inferential framework is computationally prohibitive.

To overcome this, machine learning (surrogate) models can be trained to learn the map from the parameters of interest to the observables. In particular, Dr. Qezlou highlights a multi-fidelity Gaussian Process framework designed to maximize the constraining power on a high-dimensional input parameter space while minimizing the computational cost.

Dr. Qezlou also demonstrates how these emulators enable unprecedented accuracy in parameter inference, paving the way for robust scientific discoveries with current and future cosmological surveys.