Predicting emergence of crystals from amorphous matter with deep learning

• URL: http://arxiv.org/abs/2310.01117v1
• Date: Mon, 2 Oct 2023 11:46:39 GMT
• Title: Predicting emergence of crystals from amorphous matter with deep learning
• Authors: Muratahan Aykol, Amil Merchant, Simon Batzner, Jennifer N. Wei, Ekin Dogus Cubuk
• Abstract summary: Crystallization of amorphous phases into metastable crystals plays a fundamental role in the formation of new matter. We show that crystallization products of amorphous phases can be predicted in any inorganic chemistry by sampling the crystallization pathways of their local structural motifs.
• Score: 9.973423228389908
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Crystallization of the amorphous phases into metastable crystals plays a fundamental role in the formation of new matter, from geological to biological processes in nature to synthesis and development of new materials in the laboratory. Predicting the outcome of such phase transitions reliably would enable new research directions in these areas, but has remained beyond reach with molecular modeling or ab-initio methods. Here, we show that crystallization products of amorphous phases can be predicted in any inorganic chemistry by sampling the crystallization pathways of their local structural motifs at the atomistic level using universal deep learning potentials. We show that this approach identifies the crystal structures of polymorphs that initially nucleate from amorphous precursors with high accuracy across a diverse set of material systems, including polymorphic oxides, nitrides, carbides, fluorides, chlorides, chalcogenides, and metal alloys. Our results demonstrate that Ostwald's rule of stages can be exploited mechanistically at the molecular level to predictably access new metastable crystals from the amorphous phase in material synthesis.

Related papers

• MolCrystalFlow: Molecular Crystal Structure Prediction via Flow Matching [6.02313590078714]
  We present MolCrystalFlow, a flow-based generative model for molecular crystal structure prediction.<n>The framework disentangles intramolecular complexity from intermolecular packing by embedding molecules as rigid bodies.<n>We benchmark our model against state-of-the-art generative models for large-size periodic crystals and rule-based structure generation methods.
  arXiv  Detail & Related papers  (2026-02-17T21:22:08Z)
• OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction [63.318434943975255]
  We introduce OXtal, a large-scale 100M parameter all-atom diffusion model that learns the conditional joint distribution over intramolecular conformations and periodic packing.<n>By leveraging a large dataset of 600K experimentally validated crystal structures, OXtal achieves orders-of-improvement over prior ab initio machine learning CSP methods.<n> OXtal attains over 80% packing similarity rate, demonstrating its ability to model both thermodynamic and kinetic regularities of molecular crystallization.
  arXiv  Detail & Related papers  (2025-12-07T20:46:30Z)
• Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation [82.91073155506277]
  Key step is to convert 3D crystal structures into 1D sequences to be processed by language models (LMs) Mat2Seq converts 3D crystal structures into 1D sequences and ensures that different mathematical descriptions of the same crystal are represented in a single unique sequence. Experimental results show that, with language models, Mat2Seq achieves promising performance in crystal structure generation as compared with prior methods.
  arXiv  Detail & Related papers  (2025-02-28T20:02:53Z)
• CrystalGRW: Generative Modeling of Crystal Structures with Targeted Properties via Geodesic Random Walks [1.2141052067494946]
  We introduce CrystalGRW, a diffusion-based generative model that can predict stable phases validated by density functional theory. CrystalGRW demonstrates the ability to generate realistic crystal structures that are close to their ground states with accuracy comparable to existing models. These features help accelerate materials discovery and inverse design by offering stable, symmetry-consistent crystal candidates for experimental validation.
  arXiv  Detail & Related papers  (2025-01-15T18:26:35Z)
• A Generation Framework with Strict Constraints for Crystal Materials Design [8.736399863675524]
  We present a new constrained generation framework that takes multiple constraints as input and enables the generation of crystal structures with specific chemical and properties.<n>Our method generates crystal structures with a probability of meeting the target properties that is more than twice that of existing approaches.
  arXiv  Detail & Related papers  (2024-11-13T09:36:50Z)
• AlphaCrystal-II: Distance matrix based crystal structure prediction using deep learning [4.437756445215657]
  We present AlphaCrystal-II, a novel knowledge-based solution that exploits the abundant inter-atomic interaction patterns found in existing crystal structures. By leveraging the wealth of inter-atomic relationships of known crystal structures, our approach demonstrates remarkable effectiveness and reliability in structure prediction.
  arXiv  Detail & Related papers  (2024-04-07T05:17:43Z)
• UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment [51.49238426241974]
  This paper introduces UAlign, a template-free graph-to-sequence pipeline for retrosynthesis prediction. By combining graph neural networks and Transformers, our method can more effectively leverage the inherent graph structure of molecules.
  arXiv  Detail & Related papers  (2024-03-25T03:23:03Z)
• Space Group Informed Transformer for Crystalline Materials Generation [2.405914457225118]
  We introduce CrystalFormer, a transformer-based autoregressive model specifically designed for space group-controlled generation of crystalline materials. The incorporation of space group symmetry significantly simplifies the crystal space, which is crucial for data and compute efficient generative modeling of crystalline materials.
  arXiv  Detail & Related papers  (2024-03-23T06:01:45Z)
• Field-based Molecule Generation [50.124402120798365]
  We show how the flexibility of this method provides crucial advantages over the prevalent, point-cloud based methods. We tackle optical isomerism (enantiomers), a previously omitted molecular property that is crucial for drug safety and effectiveness.
  arXiv  Detail & Related papers  (2024-02-24T17:13:58Z)
• Stoichiometry Representation Learning with Polymorphic Crystal Structures [54.65985356122883]
  Stoichiometry descriptors can reveal the ratio between elements involved to form a certain compound without any structural information. We propose PolySRL, which learns the probabilistic representation of stoichiometry by utilizing the readily available structural information.
  arXiv  Detail & Related papers  (2023-11-17T20:34:28Z)
• Scalable Diffusion for Materials Generation [99.71001883652211]
  We develop a unified crystal representation that can represent any crystal structure (UniMat) UniMat can generate high fidelity crystal structures from larger and more complex chemical systems. We propose additional metrics for evaluating generative models of materials.
  arXiv  Detail & Related papers  (2023-10-18T15:49:39Z)
• Data-Driven Score-Based Models for Generating Stable Structures with Adaptive Crystal Cells [1.515687944002438]
  This work aims at the generation of new crystal structures with desired properties, such as chemical stability and specified chemical composition. The novelty of the presented approach resides in the fact that the lattice of the crystal cell is not fixed. A multigraph crystal representation is introduced that respects symmetry constraints, yielding computational advantages.
  arXiv  Detail & Related papers  (2023-10-16T02:53:24Z)
• Crystal-GFN: sampling crystals with desirable properties and constraints [103.79058968784163]
  We introduce Crystal-GFN, a generative model of crystal structures that sequentially samples structural properties of crystalline materials. In this paper, we use as objective the formation energy per atom of a crystal structure predicted by a new proxy machine learning model trained on MatBench. The results demonstrate that Crystal-GFN is able to sample highly diverse crystals with low (median -3.1 eV/atom) predicted formation energy.
  arXiv  Detail & Related papers  (2023-10-07T21:36:55Z)
• Real-space detection and manipulation of topological edge modes with ultracold atoms [56.34005280792013]
  We demonstrate an experimental protocol for realizing chiral edge modes in optical lattices. We show how to efficiently prepare particles in these edge modes in three distinct Floquet topological regimes. We study how edge modes emerge at the interface and how the group velocity of the particles is modified as the sharpness of the potential step is varied.
  arXiv  Detail & Related papers  (2023-04-04T17:36:30Z)
• A data-driven interpretation of the stability of molecular crystals [0.0]
  Predicting the stability of crystal structures formed from molecular building blocks is a non-trivial scientific problem. We introduce a structural descriptor tailored to the prediction of the binding energy for a curated dataset of organic crystals. We then interpret this library using a low-dimensional representation of the structure-energy landscape.
  arXiv  Detail & Related papers  (2022-09-21T23:32:53Z)
• The limit of spin lifetime in solid-state electronic spins [77.34726150561087]
  We provide a complete first-principles picture of spin relaxation that includes up to two-phonon processes. We study a vanadium-based molecular qubit and reveal that the spin lifetime at high temperature is limited by Raman processes.
  arXiv  Detail & Related papers  (2020-04-08T14:27:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.