A Synthesizability-Guided Pipeline for Materials Discovery

2025-11-03

AI Summary

In computational materials discovery, zero-Kelvin DFT-predicted structures often fail experimental realization due to kinetic or synthetic barriers. Method: This work introduces a synthesis-aware materials discovery paradigm. We develop a novel synthesizability scoring model integrating compositional and structural descriptors—moving beyond conventional energy-based stability criteria. The framework synergistically combines DFT calculations, large-scale database analysis (Materials Project, GNoME, Alexandria), and automated synthesis pathway prediction to systematically assess the experimental realizability of crystal structures. Contribution/Results: Applied to hundreds of unsynthesized candidates, the method identifies high-synthesizability materials; 16 targets were experimentally pursued, with 7 successfully synthesized within three days. This significantly improves both the efficiency and reliability of translating computational predictions into experimental validation. The approach establishes a generalizable methodology for application-driven materials design.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Search and Optimization: Mixed Discrete/Continuous Search
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Computational materials discovery relies on the generation of plausible crystal structures. The plausibility is typically judged through density functional theory methods which, while typically accurate at zero Kelvin, often favor low-energy structures that are not experimentally accessible. We develop a combined compositional and structural synthesizability score which provides an accurate way of predicting which compounds can actually be synthesized in a laboratory. We use it to evaluate non-synthesized structures from the Materials Project, GNoME, and Alexandria, and identified several hundred highly synthesizable candidates. We then predict synthesis pathways, conduct corresponding experiments, and characterize the products across 16 targets, successfully synthesizing 7 of 16. The entire experimental process was completed in only three days. Our results highlight omissions in lists of known synthesized structures, deliver insights into the practical utility of current materials databases, and showcase the central role synthesizability prediction can play in materials discovery.

Problem

• Predicting synthesizable crystal structures for experimental materials discovery
• Evaluating computational materials databases for practical laboratory synthesis
• Developing synthesizability scores to identify experimentally accessible compounds

Innovation

• Developed a combined synthesizability score for materials
• Evaluated unsynthesized structures from major databases
• Predicted synthesis pathways and experimentally validated candidates