Thermodynamic Prediction Enabled by Automatic Dataset Building and Machine Learning

TL;DR

This paper demonstrates how large language models can automate literature reviews and how machine learning models can predict thermodynamic properties, significantly accelerating chemistry and materials science research.

Contribution

It introduces an LLM-based tool for extracting chemical data and trains an ML model to predict thermodynamic parameters, showcasing automation in data collection and prediction.

Findings

Successful extraction of chemical information from diverse literature sources

Accurate prediction of thermodynamic parameters using ML models

Demonstration of integrated ML approaches transforming research workflows

Abstract

New discoveries in chemistry and materials science, with increasingly expanding volume of requisite knowledge and experimental workload, provide unique opportunities for machine learning (ML) to take critical roles in accelerating research efficiency. Here, we demonstrate (1) the use of large language models (LLMs) for automated literature reviews, and (2) the training of an ML model to predict chemical knowledge (thermodynamic parameters). Our LLM-based literature review tool (LMExt) successfully extracted chemical information and beyond into a machine-readable structure, including stability constants for metal cation-ligand interactions, thermodynamic properties, and other broader data types (medical research papers, and financial reports), effectively overcoming the challenges inherent in each domain. Using the autonomous acquisition of thermodynamic data, an ML model was trained using the CatBoost algorithm for accurately predicting thermodynamic parameters (e.g., enthalpy of formation) of minerals. This work highlights the transformative potential of integrated ML approaches to reshape chemistry and materials science research.