Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning

TLDR

The Materials Genome Initiative has generated numerous computationally designed materials and extensive data resources for screening transformative compounds in energy storage, catalysis, thermoelectrics, and hydrogen storage. The authors aim to address the synthesis bottleneck in high‑throughput materials design by developing an NLP‑based method to automatically extract synthesis parameters from thousands of publications. They built a framework that extracts synthesis conditions from over 12,000 manuscripts on metal oxides, then uses machine learning to predict key parameters for titania nanotube hydrothermal synthesis and validates these predictions against known mechanisms. The approach successfully predicts synthesis outcomes for unseen material systems, outperforming heuristic strategies and demonstrating transfer learning capability.

Abstract

In the past several years, Materials Genome Initiative (MGI) efforts have produced myriad examples of computationally designed materials in the fields of energy storage, catalysis, thermoelectrics, and hydrogen storage as well as large data resources that are used to screen for potentially transformative compounds. The bottleneck in high-throughput materials design has thus shifted to materials synthesis, which motivates our development of a methodology to automatically compile materials synthesis parameters across tens of thousands of scholarly publications using natural language processing techniques. To demonstrate our framework’s capabilities, we examine the synthesis conditions for various metal oxides across more than 12 thousand manuscripts. We then apply machine learning methods to predict the critical parameters needed to synthesize titania nanotubes via hydrothermal methods and verify this result against known mechanisms. Finally, we demonstrate the capacity for transfer learning by using machine learning models to predict synthesis outcomes on materials systems not included in the training set and thereby outperform heuristic strategies.