Xinchao Liu

Xinchao Liu

Visiting Assistant Professor

Office: 260H McCain Hall
xinchao.liu@msstate.edu
P 662.325.7625
Google Scholar

Xinchao Liu received his B.E. and M.S. degrees in Aircraft Design & Engineering and Aircraft Airworthiness Technology & Management from Nanjing University of Aeronautics and Astronautics in China. He received his Ph.D. in Industrial Engineering and a Ph.D. minor in Operations Research from the Georgia Institute of Technology. Throughout his Ph.D., he gained industry experience at Walmart Global Tech and IBM T.J. Watson Research Center.

His research interests are AI/ML-enhanced scientific and engineering simulations, uncertainty quantification, and optimal experimental design. He focuses on integrating domain/physics knowledge with statistical machine learning to advance inference, prediction, and decision-making in complex engineering systems. The application area includes aviation safety, biomanufacturing, nondestructive testing, and emission source identification.

His publications have appeared in journals such as Technometrics, ASME Journal of Manufacturing and Engineering, AIAA Journal, and Aerospace Science and Technology. He has received multiple academic awards, including the 2024 IISE Data Analytics and Information Systems (DAIS) Best Student Paper, 2022 INFORMS Quality, Statistics and Reliability (QSR) Best Paper Finalist and 2021 INFORMS QSR Best Student Poster.

Education

  • Ph.D., Industrial Engineering, Georgia Institute of Technology, Atlanta, Georgia, 2025.
  • M.S., Aircraft Airworthiness Technology and Management, Nanjing University of Aeronautics and Astronautics, Nanjing, China, 2019.
  • B.E., Aircraft Design and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China, 2016.

Research Interests

  • AI/ML-Enhanced Scientific & Engineering Modeling and Digital Twins
    • Surrogate Modeling: physics-aware statistical machine learning, adaptive reduced order modeling.
    • Digital Twin Modeling: advanced sensing, cyber-physical integration, real-time calibration.
  • Uncertainty Quantification & Optimal Experimental Design
    • Inverse Problems: amortized variational inference, inverse physics-informed neural network.
    • Optimization: design of computer experiments, A-/D-optimality, adaptive sampling/sequential design.
  • Human-Machine Collaboration in Nondestructive Testing
    • Collaborative Intelligence & Robotic Inspection: Human-in-the-loop AI for detection and decision.

Applications

  • Small Unmanned Aircraft Systems (sUAS)
  • Ultrasonic Nondestructive Testing and Evaluation
  • Biomanufacturing, Composite Structures and 3D Printing
  • Optimal Sensor Allocation for Atmospheric and Water Inverse Modeling