Bridging Theory and Experiment in Materials Discovery: Machine-Learning-Assisted Prediction of Synthesizable Structures

2025-05-14

AI Summary

This study addresses the gap between theoretical prediction and experimental synthesis—particularly for metastable materials accessible under kinetic control, which are often overlooked by conventional thermodynamics-driven crystal structure prediction (CSP) methods. To bridge this gap, we propose a *synthesizability-driven* CSP paradigm integrating symmetry-constrained structure generation, Wyckoff-position-based structural encoding, and a graph neural network model trained to assess synthetic feasibility; an experimental feedback fine-tuning mechanism further refines predictions. Structural candidates are rigorously validated via combined DFT-calculated energy barriers and thermodynamic stability criteria. Our approach successfully reproduces 13 known XSe structures and efficiently identifies 92,000 high-synthesizability candidates from 550,000 GNoME entries. It discovers eight previously unknown thermodynamically stable phases in the Hf–X–O system, including HfV₂O₇—a compound exhibiting both high synthesizability and promising phase-transition behavior.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Even though thermodynamic energy-based crystal structure prediction (CSP) has revolutionized materials discovery, the energy-driven CSP approaches often struggle to identify experimentally realizable metastable materials synthesized through kinetically controlled pathways, creating a critical gap between theoretical predictions and experimental synthesis. Here, we propose a synthesizability-driven CSP framework that integrates symmetry-guided structure derivation with a Wyckoff encode-based machine-learning model, allowing for the efficient localization of subspaces likely to yield highly synthesizable structures. Within the identified promising subspaces, a structure-based synthesizability evaluation model, fine-tuned using recently synthesized structures to enhance predictive accuracy, is employed in conjunction with ab initio calculations to systematically identify synthesizable candidates. The framework successfully reproduces 13 experimentally known XSe (X = Sc, Ti, Mn, Fe, Ni, Cu, Zn) structures, demonstrating its effectiveness in predicting synthesizable structures. Notably, 92,310 structures are filtered from the 554,054 candidates predicted by GNoME, exhibiting great potential for promising synthesizability. Additionally, eight thermodynamically favorable Hf-X-O (X = Ti, V, and Mn) structures have been identified, among which three HfV$_2$O$_7$ candidates exhibit high synthesizability, presenting viable candidates for experimental realization and potentially associated with experimentally observed temperature-induced phase transitions. This work establishes a data-driven paradigm for machine-learning-assisted inorganic materials synthesis, highlighting its potential to bridge the gap between computational predictions and experimental realization while unlocking new opportunities for the targeted discovery of novel functional materials.

Problem

• Predicting synthesizable crystal structures beyond thermodynamic stability
• Bridging computational predictions with experimental synthesis in materials discovery
• Identifying metastable materials via machine-learning-assisted structure evaluation

Innovation

• Symmetry-guided structure derivation with Wyckoff encoding
• Structure-based synthesizability evaluation model
• Machine-learning-assisted inorganic materials synthesis