← Back to all news
arXiv Machine Learning By Zhuoran Yang, Christopher M. Collins, Bei Peng, Luke M. Daniels, Matthew J. Rosseinsky, Vladimir V. Gusev

PXtal: Learning to Align Powder X-Ray Diffraction and Crystal Structures under Information Asymmetry across Modalities

Read the original on arXiv Machine Learning →

PXtal is a new framework that learns aligned representations for powder X‑ray diffraction (PXRD) patterns and crystal structures, addressing the information asymmetry inherent in compressing 3D crystal data into 1D diffraction patterns. It employs Unbalanced Optimal Transport to adjust cross‑modal coupling and uses a coupling‑level generalized Kullback‑Leibler divergence to supervise the transport plan. Across six test sets—including four zero‑shot transfer scenarios—PXtal consistently outperforms baseline models in retrieving crystal candidates from PXRD data, especially when similar diffraction patterns correspond to distinct crystals, and its encoders transfer effectively to downstream materials science tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jul 10

MatBind: A Shared Embedding Space for Multimodal Materials Characterization

arXiv:2607. 08470v1 Announce Type: new Abstract: Fully characterizing a crystalline material requires integrating heterogeneous data sources -- atomic structures, diffraction patterns, electronic density of states, and natural language -- each of which captures a different facet of the same physical object.

By Le Yang (Institute for Advanced Simulations), Anoop K. Chandran (J\"ulich Supercomputing Centre, Forschungszentrum J\"ulich), Jona \"Ostreicher (Institute of Nanotechnology, Karlsruhe Institute of Technology), Evgenii Sovetkin (J\"ulich Supercomputing Centre, Forschungszentrum J\"ulich), Adrian Mirza (Helmholtz-Zentrum Berlin f\"ur Materialien und Energie, Helmholtz Institute for Polymers in Energy Applications Jena), Sebastien Bompas (Institute for Advanced Simulations), Bashir Kazimi (Institute for Advanced Simulations), Pascal Friederich (Institute of Nanotechnology, Karlsruhe Institute of Technology), Stefan Kesselheim (J\"ulich Supercomputing Centre, Forschungszentrum J\"ulich, 1. Physikalisches Institut, University of Cologne), Kevin Maik Jablonka (Helmholtz Institute for Polymers in Energy Applications Jena, Center for Energy and Environmental Chemistry Jena, Friedrich Schiller University Jena), Stefan Sandfeld (Institute for Advanced Simulations, Faculty 5 - Georesources and Materials Engineering, RWTH Aachen University)
ragmultimodalsafety
More like this →
arXiv Machine Learning
Sep 14

Inferring Dislocation Microstructures from X-ray Diffraction via Cross-Modal Contrastive Learning

The paper presents a cross‑modal learning framework that predicts three‑dimensional dislocation density fields directly from X‑ray diffraction data. By pairing simulated dislocation density fields with virtual diffraction patterns and embedding them into a shared 2‑D latent space via contrastive learning, the authors achieve strong alignment between structural and diffraction representations. Experiments show that model performance improves rapidly with dataset size, reaching near‑saturation with about 500 representative observations out of 10,000, and the predicted structures capture the dominant spatial features of the underlying microstructures.

By Benjamin Udofia, Nicolas Bertin, Markus Stricker
diffusionmultimodalsafety
More like this →
arXiv AI
Oct 7

XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction

XDecomposer is a prior‑free framework that jointly decomposes and identifies multiphase X‑ray diffraction patterns without requiring candidate phase lists, structural templates, or knowledge of the number of phases. It treats multiphase analysis as a set prediction problem, inferring an unordered set of phase‑resolved components, their mixture proportions, and structural representations within a single architecture. Experiments on simulated and experimental data demonstrate improved reconstruction accuracy and phase identification across diverse chemical systems, with strong generalization to unseen mixtures.

By Hanyu Gao, Bin Cao, Yunyue Su, Tong-Yi Zhang, Qiang Liu
More like this →