![Author ORCID: We display the ORCID iD icon alongside authors names on our website to acknowledge that the ORCiD has been authenticated when entered by the user. To view the users ORCiD record click the icon. [opens in a new tab]](https://chemrxiv.org/engage/assets/public/chemrxiv/images/logos/orcid.png)
Abstract
With the growing emphasis on sustainability, criticality, and availability in materials research, our study introduces a comprehensive data analytics platform to provide country-specific insights into global elemental production and reserves. Utilizing data from the United States Geological Survey (USGS), our web application incorporates the Herfindahl-Hirschman Index (HHI) to assess market concentration, identifying potential risks and opportunities related to resource availability. The platform features an AI assistant powered by a Retrieval-Augmented Generation (RAG) system, leveraging the past ten years of USGS mineral commodities summaries. This system employs an open-source large language model (LLM) to enable users to query various aspects of raw materials, including reserves, production, market share, usage, price, substitutes, recycling, and more. By retrieving relevant documents and generating accurate, comprehensive responses, our tool addresses a crucial gap in publicly available resources, offering a unified application for detailed material analysis. This platform provides valuable support for material scientists in assessing sustainability, criticality, and market risks, thereby aiding in the development of new materials. Website: https://mineral-ai.net
Supplementary materials
Title
Supplementary Material
Description
The supplementary material includes prompts used for GPT-4 to derive contextual text from the tables, as well as prompts for MatAssist to reformat queries and generate responses. It contains the user queries, sample responses, and ground truths for all 30 queries used in the RAG evaluation metrics.
Actions
