Explainable AI in (Astro)physics

          @misc{ pirsa_PIRSA:25040098,
            doi = {10.48660/25040098},
            url = {https://pirsa.org/25040098},
            author = {Lucie-Smith, Luisa},
            keywords = {},
            language = {en},
            title = {Explainable AI in (Astro)physics},
            publisher = {Perimeter Institute},
            year = {2025},
            month = {apr},
            note = {PIRSA:25040098 see, \url{https://pirsa.org}}
          }
          

Abstract

Machine learning has significantly improved the way scientists model and interpret large datasets across a broad range of the physical sciences; yet, its "black box" nature often limits our ability to trust and understand its results. Interpretable and explainable AI is ultimately required to realize the potential of machine-assisted scientific discovery. I will review efforts toward explainable AI focusing in particular in applications within the field of Astrophysics. I will present an explainable deep learning framework which combines model compression and information theory to achieve explainability. I will demonstrate its relevance to cosmological large-scale structures, such as dark matter halos and galaxies, as well as the cosmic microwave background, revealing new physical insights derived from these explainable AI models.