{"ID":6449107,"CreatedAt":"2026-07-11T22:35:29.080528172Z","UpdatedAt":"2026-07-11T22:35:29.080528172Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2104.04392","arxiv_id":"2104.04392","title":"Deep learning for visualization and novelty detection in large X-ray diffraction datasets","abstract":"We apply variational autoencoders (VAE) to X-ray diffraction (XRD) data analysis on both simulated and experimental thin-film data. We show that crystal structure representations learned by a VAE reveal latent information, such as the structural similarity of textured diffraction patterns. While other artificial intelligence (AI) agents are effective at classifying XRD data into known phases, a similarly conditioned VAE is uniquely effective at knowing what it does not know, rapidly identifying novel phases and mixtures. These capabilities demonstrate that a VAE is a valuable AI agent for materials discovery and understanding XRD measurements both on-the-fly and during post hoc analysis.","url_abs":"https://arxiv.org/abs/2104.04392v1","url_pdf":"https://arxiv.org/pdf/2104.04392v1","authors":"Lars Banko, Phillip M. Maffettone, Dennis Naujoks, Daniel Olds, Alfred Ludwig","published":"2021-04-09T14:31:22Z","has_code":false}