Page 1 — Guangshuai Han

Guangshuai(Jerry) Han

Guangshuai Han develops AI-driven systems that accelerate discovery in materials and device design, with a broader mission of advancing AI-for-science methodologies capable of transforming scientific innovation. His work spans agentic AI, LLM-based scientific reasoning, machine-learning force fields, and interpretable graph neural networks for understanding and designing complex materials systems.

During his PhD, one of his major achievements was pioneering an AI-assisted piezoelectric sensing system that transformed highway infrastructure monitoring. This technology was adopted as a new AASHTO standard, recognized by Time Magazine as one of the Best Inventions of 2023, and successfully transferred into practice as the core technology of a startup company.

Email
Google Scholar
GitHub Page

01 AI for Materials Design and Discovery

My research spans multiple directions in AI-driven materials discovery, from chemical composition design and machine-learning force fields to interpretable graph neural networks. The central focus is on high-entropy materials, where I develop physically inspired algorithms to navigate infinite possibilities and identify optimized designs.

Research Sponsors:

National Science Foundation (NSF)
Advanced Research Projects Agency–Energy (ARPA-E)

Github Page:

Chaos-GPT LLM for high entropy materials: Chaos-GPT
Open-Source Materials Crystallography Database: MatForge
Generative moel for materials design: Mag-VAE
XGNN-Piezo: XGNN-Piezo
High-entropy alloy design: HE_FuelCell_Discovery
MLFF with coordination corrected enthalpies: AI-CCE
High-entropy ceramic design: Cyber_cooking
AFLOW materials discovery: aflow++

Publication:

G. Han, W. Hosler, N. Lu, Y. Feng, “An Explainable Framework for Graph Neural Networks in Materials Discovery: A Piezoelectric Case Study”, npj computational materials. (Under Review)
G. Qiu, G. Han, T. Li, X. Xu, S., Tseng, C. Oses, “Accurate Prediction of Metal Iodide Ground States with an AI-Enhanced Correction Framework“, communication materials. (Invited, Under Review)

G. Han, T. Li, X. Xu, J. Lee, G. Qiu, S. Sequeria, A. Ajith, C. Oses, “The search for high-entropy fuel-cell catalysts using disorder descriptors“, Nano Futures. (Invited, Minor Revision)
C. Oses, T. Li, X. Xu, G. Han, G. Qiu, J. Owens, “Beyond the Four Core Effects: Revisiting Thermoelectrics with a High-Entropy Design”, Materials Horizons, 12, 5946-5956, 2025.

G. Han Y. Sun, Y. Feng, G. Lin, N. Lu, ““Artificial intelligence assisted thermoelectric materials design and discovery”, Advanced Electronic Materials, 2300042, 2023. (Featured as cover page)

G. Han, Y.Sun, Y. Feng, G. Lin, N. Lu. “Machine learning regression guided thermoelectric materials discovery– a review” ES Materials and Manufacturing, 14, pp. 20-35, 2021

INDEX NEXT