Dr. Yichuan Zhu leads the Computational Geosystems Laboratory in the Civil & Environmental Engineering Department at Temple University. Prior to joining Temple University, he worked as a Post-doctoral fellow at Kentucky Geological Survey where he applied quantitative methods such as machine learning, Bayesian techniques, and spatio-temporal simulations to solve applied Earth science research problems. He earned his Ph.D. in Civil Engineering from Texas A&M University. His research interests include ML/AI in Geotechnical and Geological applications, risk/reliability assessment and management, remote sensing, uncertainty quantification, computational geomechanics, and software development.

Research Interests

  • ML/AI in Geotechnical and Geological applications
  • Engineering Geology
  • Risk/reliability assessment and management
  • Remote sensing and Spatio-temporal analysis
  • Uncertainty quantification
  • Computational geomechanics

Courses Taught




CMT 3333

Soils Mechanics


CEE 3048

Probability, Statistics & Stochastic Methods


Selected Publications

  • Zhu, Y., Dortch, J.M., Massey, M.A., Haneberg, W.C., & Curl, D. (2021). An intelligent swath tool to characterize complex topographic features: Theory and application in the Teton Range, Licking River, and Olympus Mons. Geomorphology, 387, p. 107778. doi: 10.1016/j.geomorph.2021.107778

  • Zhu, Y., Wang, Z., Carpenter, N.S., Woolery, E.W., & Haneberg, W.C. (2021). Mapping Fundamental-Mode Site Periods and Amplifications from Thick Sediments: An Example from the Jackson Purchase Region of Western Kentucky, Central United States. Bulletin of the Seismological Society of America, 111(4), pp. 1868-1884. doi: 10.1785/0120200300

  • Crawford, M.M., Dortch, J.M., Koch, H.J., Killen, A.A., Zhu, J., Zhu, Y., Bryson, L.S., & Haneberg, W.C. (2021). Using landslide-inventory mapping for a combined bagged-trees and logistic-regression approach to determining landslide susceptibility in eastern Kentucky, USA. Quarterly Journal of Engineering Geology and Hydrogeology, 54(4), pp. qjegh2020-qjegh2177. doi: 10.1144/qjegh2020-177