ChatGPT and the discovery of new materialsPublic Deposited
Downloadable Contentopen in viewer
Materials engineering is an ever-expanding field with broad applications, and Artificial Intelligence (AI) shows great promise for advancing new materials. While previous research has focused on developing new materials, little research has explored the potential of AI in assisting materials engineers, engineer-AI interactions, and its incorporation into decision-making processes. To address this issue, we devised a rubric to assess various AI systems currently on the market based on specific criteria relevant for engineers’ decision-making (e.g. ease of use, trustworthiness, memory, accuracy, and speed). We independently applied this rubric to evaluate eight AI systems: ChatGPT, Elicit, SciSpace Copilot, Writeful X, Paperpal, QuillBot, PaperDigest, and Notion. We then incorporated the rubric into a survey distributed to materials engineers, who provided ratings about their perceptions, decision-making processes, and overall evaluations of these eight systems. Finally, we conducted a case study where an engineering student used AI to write an academic paper on a quaternary alloy system, documenting their firsthand experience and perceptions of AI in materials science. Overall, this study is among the first to provide insights into AI’s potential applications and implications in materials engineering.
- This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.
- Date created
- Resource type
- Rights statement
- Last modified
- In Collection:
Permanent link to this page: https://digital.wpi.edu/show/1n79h767q