Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraints

2022/03/27 by Yong Zhao, Zhao, Yong, Edirisuriya M. Dilanga Siriwardane +11 · 10 citations
Chemistry · Materials Science · #FOS: Computer and information sciences #FOS: Physical sciences #Inorganic Chemistry and Materials #Machine Learning (cs.LG) #Machine Learning in Materials Science #Materials Science (cond-mat.mtrl-sci) #X-ray Diffraction in Crystallography

paper · pdf · doi:10.48550/arxiv.2203.14352

openalex publication_date 2022/03/27 · openalex created_date 2022/07/07 · openalex updated_date 2026/07/28

Abstract

Discovering new materials is a challenging task in materials science crucial to the progress of human society. Conventional approaches based on experiments and simulations are labor-intensive or costly with success heavily depending on experts' heuristic knowledge. Here, we propose a deep learning based Physics Guided Crystal Generative Model (PGCGM) for efficient crystal material design with high structural diversity and symmetry. Our model increases the generation validity by more than 700% compared to FTCP, one of the latest structure generators and by more than 45% compared to our previous CubicGAN model. Density Functional Theory (DFT) calculations are used to validate the generated structures with 1,869 materials out of 2,000 are successfully optimized and deposited into the Carolina Materials Database \urlwww.carolinamatdb.org, of which 39.6% have negative formation energy and 5.3% have energy-above-hull less than 0.25 eV/atom, indicating their thermodynamic stability and potential synthesizability.

Cited by

• LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models
• Generative models for crystalline materials
• Benchmarking GNNs for OOD Materials Property Prediction with Uncertainty Quantification
• Completing the hierarchy of rotational defects in monolayer MoS 2 through symmetry-aware evolutionary search
• L²M³OF: A Large Language Multimodal Model for Metal-Organic Frameworks
• Continuous Uniqueness and Novelty Metrics for Generative Modeling of Inorganic Crystals
• Generative AI for Crystal Structures: A Review
• Autonomous Inorganic Materials Discovery via Multi-Agent Physics-Aware Scientific Reasoning
• Unified machine-learning framework for property prediction and time-evolution simulation of strained alloy microstructure
• Atomistic Generative Diffusion for Materials Modeling

Related

• Evaluating the diversity and utility of materials proposed by generative models
• AI-Assisted Rapid Crystal Structure Generation Towards a Target Local Environment
• Crystal-GFN: sampling crystals with desirable properties and constraints
• Accelerating Materials Discovery with Bayesian Optimization and Graph Deep Learning
• Generative models for crystalline materials