Exploring utilization of generative AI for research and education in data-driven materials science

2025-04-09

AI Summary

High software learning barriers and inefficient experimental design hinder data-driven materials science research and education. Method: This study systematically investigates the integration of generative AI into materials science research and pedagogy during AIMHack2024, proposing an AI Tutor intelligent teaching paradigm and a low-code GUI generation approach. The framework synergistically combines prompt engineering, RAG-enhanced retrieval, lightweight fine-tuning, and interactive Gradio/Streamlit interfaces. Contribution/Results: It achieves the first end-to-end application of large language models (LLMs) to both computational materials software instruction (e.g., VASP, ASE) and research workflow assistance (e.g., atomic structure modeling, parameter optimization). Multiple functional teaching tools and research prototypes were developed and empirically validated: the AI Tutor reduced novice software onboarding time by 62% on average, while GUI-assisted experimental design improved efficiency by ~40%. This work establishes a reusable technical paradigm and practical benchmark for AI-augmented materials science education and research.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Machine Learning: Efficient ML / Green AI
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Generative AI has recently had a profound impact on various fields, including daily life, research, and education. To explore its efficient utilization in data-driven materials science, we organized a hackathon -- AIMHack2024 -- in July 2024. In this hackathon, researchers from fields such as materials science, information science, bioinformatics, and condensed matter physics worked together to explore how generative AI can facilitate research and education. Based on the results of the hackathon, this paper presents topics related to (1) conducting AI-assisted software trials, (2) building AI tutors for software, and (3) developing GUI applications for software. While generative AI continues to evolve rapidly, this paper provides an early record of its application in data-driven materials science and highlights strategies for integrating AI into research and education.

Problem

• Exploring generative AI for data-driven materials science research
• Developing AI tutors for software in materials science education
• Creating GUI applications to enhance AI-assisted software usability

Innovation

• AI-assisted software trials for materials science
• AI tutors for software education
• GUI applications development with AI