Welcome to the Wen Group at the University of Electronic Science and Technology of China!
We push the boundaries of artificial intelligence and data-driven computational methods to power discovery in the physical and materials sciences.
News
September 20, 2026
Our paper Atomistic machine learning with irreducible Cartesian natural tensors has been published in Nature Communications. Congratulations to Qun and Boyu! https://doi.org/10.1038/s41467-026-77263-z
September 1, 2026
Welcome a new cohort of graduate students, Mingxiang Zhang, Junfei Yang, and Ran Zhang, to the group!
August 5, 2026
Our paper on guided synthesis of EMT zeolites by machine learning appears in Physical Review Materials. https://doi.org/10.1103/v2yp-ylxm
More...
People
Principal Investigator
Mingjian Wen (文明健)
Professor, Institute of Fundamental and Frontier Sciences, UESTC
mjwen@uestc.edu.cn
Mingjian tracks how atoms move and interact with each other on weekdays and cheers for soccer games on weekends. He seems to be tied to spherical objects.
Postdocs
Yuliang Guo (郭育良)
yuliangguo@uestc.edu.cn
Yuliang develops computational engines for the physical world and makes music for the emotional one. He pursues reason through science and feeling through music - apparently, he needs both to feel complete.
You
Come and join us.
Ph.D. Students
Wei-Fan Huang
whuang25@uh.edu
Wei-Fan received his B.S. and M.S. in Chemical Engineering from National Cheng Kung University in Taiwan in 2018 and 2021. His research focuses on developing machine learning models and their applications in molecular simulation of battery materials.
Emmanuel A. Olanrewaju
eolanrew@uh.edu
Emmanuel loves computational work to understand and design materials for renewable energy applications. He currently works on data-driven understanding of the stability of zeolites.
Qun Chen (陈群)
qunchen@std.uestc.edu.cn
Qun received her M.S. from Shanghai University. She works on building foundation machine learning models that enable accurate and efficient atomistic simulations across diverse chemical and materials systems.
Cong Wang (王聪)
202411210402@std.uestc.edu.cn
Cong studies magnetic behaviors of functional materials, employing multiscale computational approaches to uncover their fundamental properties and underlying physical mechanisms.
Mingxiang Zhang (张明翔)
zhangmx@std.uestc.edu.cn
Mingxiang works on the theory of magnetic materials, particularly altermagnetism and magnetic anisotropy, and uses first-principles calculations to uncover the physical mechanisms behind these phenomena.
M.S. Students
Jiahui Pan (潘佳荟)
202521210106@std.uestc.edu.cn
Jiahui is dedicated to applying molecular dynamics to study battery materials, aiming to deepen the understanding of electrochemical processes and improve battery performance.
Haoyang Wang (汪浩洋)
202522020823@std.uestc.edu.cn
Haoyang holds a B.S. in Space Physics from the University of Science and Technology of China. His research focuses on the application of first-principles theory to study and design magnetic materials.
Junfei Yang (杨俊飞)
202621210422@std.uestc.edu.cn
Junfei obtained his bachelor's degree from UESTC. He uses machine learning atomistic simulations to understand how materials grow in processes like remote epitaxy.
Ran Zhang (张冉)
202621210421@std.uestc.edu.cn
Ran studies porous materials for energy applications. She uses computational modeling and machine learning to understand these materials at a fundamental level and to design new ones.
Undergraduates
Qiyao Gao (高启尧)
qiyao_gao@std.uestc.edu.cn
Qiyao majors in Electronic Information Engineering at UESTC. His research interest lies in applying deep learning to materials science.
Boyu Wang (王博宇)
bywang@std.uestc.edu.cn
Boyu is currently pursuing a B.S. at UESTC. His research focuses on the development of machine learning models and their applications in materials science.
Alumni...
Research
AI for Materials Science
Machine learning methods, particularly deep learning, have significantly expanded our toolbox for constructing predictive and generative scientific models. These models make it possible to accurately and efficiently explore the gigantic design space of new materials and chemicals.
Our group pioneers the development of novel AI algorithms that integrate core physical principles to create such models and advance their capabilities. These algorithms enable both the precise forecasting of material properties and the intelligent design of new compounds with targeted functions.
Accelerated Reliable Atomistic Simulations
Atomistic simulations are a powerful computational technique for exploring material behavior at the atomic scale. At the core of any atomistic simulation lies a description of the interactions between atoms that produces the forces governing their motion.
We develop both physics-based and machine learning interatomic potentials to model these interactions. To ensure the robustness of these models, we also develop analysis frameworks, such as those for uncertainty quantification and propagation, to make atomistic simulations more reliable, reproducible, and accessible.
Energy Storage Systems
Renewable energy storage is essential for building a sustainable future, with advanced batteries playing a critical role in enabling reliable grid integration of solar and wind power. Our research develops the fundamental science needed for next-generation, grid-scale storage systems.
We apply theoretical and multiscale computational methods to investigate key challenges in battery systems, including ion transport mechanisms, interface phenomena, and degradation processes across multiple scales.
High-throughput Materials Discovery
Quantum chemical theory and computations are powerful tools for understanding and designing materials. Conventional approaches that manually perform the calculations are difficult to manage complex materials science workflows and difficult to fully utilize modern high-performance computing resources.
Building on top of the software stack that powers the Materials Project, we develop high-throughput materials discovery pipelines for density functional theory (DFT) and machine learning techniques, and apply them to search for materials for renewable energy and information applications.
Codes
CarNet
Cartesian Natural Tensor Networks - atomistic machine learning for interatomic potentials, scalar properties, tensorial properties and beyond.
GitHub
MatTen
An equivariant graph neural model for predicting tensorial properties of crystals such as the elasticity tensor.
GitHub
BonDNet
A graph neural network machine learning model for the prediction of bond dissociation energies.
GitHub
KLIFF
A fitting package that can be used to develop both physics-based and machine learning interatomic potentials.
GitHub
Openings
Postdocs
We are looking for motivated postdocs in the areas of AI for Science, Energy Storage Materials, and Ferroic Materials. For more information, see https://muchong.com/t-16584158-1
Graduate Students
Our group welcomes new PhD and Master's students from diverse academic backgrounds each year. We highly value interdisciplinary collaboration and strongly encourage applicants with backgrounds in Materials Science, Computer Science, Physics, Chemistry, Solid Mechanics, and related fields.
Undergraduate Students
We welcome undergraduates at UESTC to join our group for research opportunities.
