mlsanityData to 7 Oct 2026

Ab Initio Structure Solutions from Nanocrystalline Powder Diffraction Data

arXiv 2406.10796 ↗First posted 16 Jun 2024physics.comp-ph cond-mat.mes-hall cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

A major challenge in materials science is the determination of the structure of nanometer sized objects. Here we present a novel approach that uses a generative machine learning model based on diffusion processes that is trained on 45,229 known structures. The model factors both the measured diffraction pattern as well as relevant statistical priors on the unit cell of atomic cluster structures. Conditioned only on the chemical formula and the information-scarce finite-size broadened powder diffraction pattern, we find that our model, PXRDnet, can successfully solve simulated nanocrystals as small as 10 angstroms across 200 materials of varying symmetry and complexity, including structures from all seven crystal systems. We show that our model can successfully and verifiably determine structural candidates four out of five times, with average error among these candidates being only 7% (as measured by post-Rietveld refinement R-factor). Furthermore, PXRDnet is capable of solving structures from noisy diffraction patterns gathered in real-world experiments. We suggest that data driven approaches, bootstrapped from theoretical simulation, will ultimately provide a path towards determining the structure of previously unsolved nano-materials.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 20 of its 74 references that are in the map. First posted on arXiv 16 Jun 2024.

Builds on

20 of 74 references.

References · 20

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  6. 2020Directional Message Passing for Molecular Graphscited by 556
  7. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 342
  8. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 268
  9. 2023Crystal Structure Prediction by Joint Equivariant Diffusioncited by 142
  10. 2023MatterGen: a generative model for inorganic materials designcited by 98
  11. 2024Space Group Constrained Crystal Generationcited by 71
  12. 2023Scalable Diffusion for Materials Generationcited by 52
8 more
  1. 2022Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraintscited by 30
  2. 2023Towards Symmetry-Aware Generation of Periodic Materialscited by 25
  3. 2023Diffusion probabilistic models enhance variational autoencoder for crystal structure generative modelingcited by 17
  4. 2021A probabilistic deep learning approach to automate the interpretation of multi-phase diffraction spectracited by 11
  5. 2024End-to-End Crystal Structure Prediction from Powder X-Ray Diffractioncited by 10
  6. 2023Spectroscopy-Guided Discovery of Three-Dimensional Structures of Disordered Materials with Diffusion Modelscited by 8
  7. 2020Identification of Crystal Symmetry from Noisy Diffraction Patterns by A Shape Analysis and Deep Learningcited by 6
  8. 2023CrysFormer: Protein Structure Prediction via 3d Patterson Maps and Partial Structure Attentioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 4.

12 papers.

  1. 2025deCIFer: Crystal Structure Prediction from Powder Diffraction Data using Autoregressive Language Modelscited by 5
  2. 2025A Generative Diffusion Model for Amorphous Materialscited by 5
  3. 2025Beyond Structure: Invariant Crystal Property Prediction with Pseudo-Particle Ray Diffractioncited by 4
  4. 2025Generative Models for Crystalline Materialscited by 3
  5. 2025Physically-Constrained Autoencoder-Assisted Bayesian Optimization for Refinement of High-Dimensional Defect-Sensitive Single Crystalline Structurecited by 1
  6. 2025CbLDM: A Diffusion Model for recovering nanostructure from atomic pair distribution functioncited by 0
  7. 2025XDXD: End-to-end crystal structure determination with low resolution X-ray diffractioncited by 0
  8. 2025Representation of Inorganic Synthesis Reactions and Prediction: Graphical Framework and Datasetscited by 0
  9. 2026Machine Learning-Driven Crystal System Prediction for Perovskites Using Augmented X-ray Diffraction Datacited by 0
  10. 2026XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffractioncited by 0
  11. 2026XRDiff: Crystal Structure Prediction from Powder X-Ray Diffraction Data Using Diffusion Modelscited by 0
  12. 2026Symmetry- and Property-Aware Crystal Generation with Reinforcement Learning for Inverse Materials Designcited by 0