(455h) Using Large Language Model to Collect and Analyze Metal-Organic Framework Property Dataset

This research was focused on the efficient collection of experimental Metal-Organic Framework (MOF) data from scientific literature to address the challenges of accessing hard-to-find data and improving the quality of information available for machine learning studies in materials science. Utilizing a chain of advanced Large Language Models (LLMs), we developed a systematic approach to extract and organize MOF data into a structured format. Our methodology successfully compiled information from more than 40,000 research articles, creating a comprehensive and ready-to-use dataset. A machine learning model trained using both the experimental and the simulation data reveals the advantage of incorporating experimental data over relying solely on simulated data for enhancing the accuracy of machine learning predictions in the field of MOF research. As such, our study illustrates the importance of collecting massive amount of the available experimemntal data to guide the future directions of materials development.