Xiaogang Ma Awarded NSF Grant Supplement to Integrate Large Language Models (LLMs) into the Mindat Open Data Interface

September 13, 2024

University of Idaho Associate Professor of Computer Science Xiaogang (Marshall) Ma has been awarded a National Science Foundation (NSF) grant supplement of $140,091 to integrate large language models (LLMs) into the Mindat open data interface to create a more interactive and responsive data platform for the world's largest open database of minerals, rocks, meteorites and the localities they come from (Mindat.org).

The NSF-funded OpenMindat project, led by Ma in collaboration with Mindat creators, is an open data service that is transforming the way mineral data is accessed, shared and utilized by the scientific community. This grant supplement will support the enrichment of Mindat functionality by utilizing LLMs to allow scientists to more easily access information in the database. Dr. Ma’s team, collaborating with Research Computing and Data Services (RCDS) to leverage LLMs, will develop advanced search capabilities, intuitive multi-turn dialogues and comprehensive data analysis to enrich Mindat functionality. Users will experience a more interactive and responsive platform, making the records more accessible and engaging for researchers, educators and enthusiasts worldwide.

This grant supplement is part of the NSF National Artificial Intelligence Research Resource (NAIRR) Pilot program. The project supports the NAIRR Pilot’s aim to connect U.S. researchers and educators to research that employs AI and the computational data and training resources needed to advance AI research. The supplement will provide training opportunities for a postdoctoral fellow for one year within Dr. Ma’s group and contribute to the development of AI research and educational programs at the University of Idaho.

The Institute for Interdisciplinary Data Sciences (IIDS) provides grant management support for the OpenMindat project as well as this NAIRR supplement while the Research and Data Computing Services (RCDS) core collaborates with Dr. Ma's team on the AI research aspects of the project.

Michelle Reagan
IIDS Scientific Design and Communications Specialist