Seminars at FGG
Retrieving Exoplanetary atmosphere using Artificial Intelligence - from classical to a quantum approach
Speaker: Tiziano Zingales (Universita' di Padova (Italy))
Date and time: 2024-02-08 11:30
Atmospheric retrievals on exoplanets usually involve computationally intensive Bayesian frameworks. Large parameter spaces and increasingly complex atmospheric models create a computational bottleneck forcing a trade-off between statistical sampling accuracy and model complexity. We introduce ExoGAN, the Exoplanet Generative Adversarial Network, a deep-learning algorithm able to recognise molecular features, atmospheric trace-gas abundances, and planetary parameters using unsupervised learning. Finally, we introduce an advanced generative network, based on ExoGAN, which takes advantage of Quantum Computing algorithms to reach even higher efficiencies and precision.