Dr Derek (Guotao) Ma

Biography

Dr. Derek G. Ma is an Assistant Professor at the University of Warwick. Dr Ma’s research sits at the interface of AI, stochastic modelling, uncertainty quantification, and risk analytics, with applications across geosystems, natural hazards, and emerging energy and financial risk problems. His interdisciplinary work, recognised through a prestigious Early Career Fellowship, focuses on applying data science and physics-informed modelling to the analysis, prediction, and management of risk.

He was awarded Global Talent status by the Royal Academy of Engineering and has contributed to policy advisory work with the Welsh Government’s Coal Tips Safety Taskforces prior to taking up his permanent academic position at the University of Warwick. He also serves as a corresponding member of ISSMGE TC309, the technical committee on Machine Learning and Big Data.

Dr Ma is recognised for his innovative contributions to stochastic computational modelling, uncertainty quantification, and risk analysis across both research and applied consulting contexts. His broader academic mission is to develop data-driven and physics-informed modelling tools that improve how uncertainty, risk, and resilience are understood, predicted, and managed in complex physical, environmental, and financial systems.

• Visiting Academic (2017) from University of Canterbury (Christchrch, New Zealand)
• Data Scientist Degree - Machine Learning (2021) from Udacity (United States)
• Ph.D. in Computational Geomechanics and Applied Probability (2021) from the School of Engineering, University of Warwick (Coventry, UK)
• Global Talent - Royal Academy of Engineering (UK)
• Early Career Fellow in Interdisciplinary Research (2022) of the Institute of Advanced Study, University of Warwick (Coventry, UK)
• Policy Advisor (2022), Coal Tips Safety Taskforce, Welsh Government (Wales, UK)
• Associate Fellow (2023) of the Institute of Advanced Study, University of Warwick (Coventry, UK)

Research Interests

Derek’s research focuses on AI-informed stochastic modelling, computational risk analysis and data-driven engineering. His work combines random fields, Bayesian inference, uncertainty quantification, computer vision, machine learning and numerical modelling to understand complex systems with strong spatial heterogeneity, randomness and risk.

Research portfolio includes:

• AI-informed Random Fields and Risk Assessment of Stochastic Systems
  • Developing data-driven and physics-informed stochastic modelling approaches to characterise spatial variability, uncertainty, and risk in complex engineering systems.
• Visual AI and Computer Vision for Geomaterials (e.g., Perception-based modelling)
  • Applying perception-based modelling, image processing, segmentation analysis, and computer vision techniques to study material behaviour.
• Energy Risk Pricing and Decision-Making
  • Exploring computational risk analytics, catastrophe insuranceLink opens in a new window, catastrophe bondsLink opens in a new window, and emerging financial risk models for energy and climate-related decision-making.

Teaching Interests

Derek teaches and supervises across engineering mathematics, project-based learning and degree apprenticeship education. His teaching is strongly aligned with mathematical modelling, analytical reasoning, data-driven engineering and industry-facing engineering education.

• ES1A1 Engineering Mathematics CEDA – Module Leader
• ES1A8 Engineering Mathematics EMDA – Module Leader
• Maths Bridging Programme – Module Leader
• ES327 Individual Project – Project Supervisor for Year 3 and Year 4 students
• ES196 Statics and Structures – Laboratory and tutorial teaching
• ES1A4 Engineering Structures – Laboratory teaching
• Tutorials for Year 2–4 students
• Tutorials and academic support for CEDA degree apprentices

Previous Contributions:

• ES192 Engineering Design
• ES3B6 Geotechnical Engineering
• ES2G7 Design Surveying and Field Practice

Derek’s teaching philosophy is to help students build strong mathematical foundations, connect theory with engineering practice, and develop the confidence to apply analytical and computational methods to real-world engineering problems.

Selected Publications

• Liu, X., Li, X., Ma, G.*, and Rezania, M., 2025. Characterization of spatially varying soil properties using an innovative constraint seed method. Computers and Geotechnics, 183, p.107184.
• Wang, Y., Ma, G.*, and Rezania, M., 2025. A granular anisotropic model of underground rockburst considering the effect of radial stresses. Tunnelling and Underground Space Technology, 155, p.106202.
• Li, W., Ma, G., Jiang, M., Rezania, M. and Zhu, H., 2025. An adversarial multi-source transfer learning method for the stability analysis of methane hydrate-bearing sediments. Computers and Geotechnics, 177, p.106868.
• Ma, G., Rezania, M., Nezhad, M.M. and Phoon, K.K., 2024. Multivariate copula-based framework for stochastic analysis of landslide runout distance. Reliability Engineering & System Safety, p.110270.
• Liu, X., Ma, G.*, Rezania, M., Li, X., and Jiang, S. H. 2024. An improved BUS approach for Bayesian inverse analysis of soil parameters incorporating extensive field data. Computers and Geotechnics, 174, 106641.
• Jiang, S., Li, J., Ma, G.*, and Rezania, M., 2024. Probabilistic assessment of 3D slope failures in spatially variable soils by cooperative stochastic material point method. Computers and Geotechnics, 172, p.106413.
• Jiang, S., Liu, X., Ma, G.*, Rezania, M., 2023. Stability analysis of heterogeneous infinite slopes under rainfall-infiltration by means of an improved Green-Ampt model. Canadian Geotechnical Journal.
• Xi, C., Hu, X., Ma, G.*, Rezania, M., Liu, B. and He, K., 2022. Predictive model of regional coseismic landslides' permanent displacement considering uncertainty. Landslides, 19(10), pp.2513-2534.
• Ma, G., Rezania, M., Mousavi Nezhad, M. and Hu, X., 2022. Uncertainty quantification of landslide runout motion considering soil interdependent anisotropy and fabric orientation. Landslides, 19(5), pp.1231-1247.
• Ma, G., Rezania, M. and Nezhad, M.M., 2022. Effects of spatial autocorrelation structure for friction angle on the runout distance in heterogeneous sand collapse. Transportation Geotechnics, 33, p.100705.
• Ma, G., Rezania, M., Mousavi Nezhad, M. and Shi, B., 2022. Post-failure analysis of landslides in spatially varying soil deposits using stochastic material point method. Rock and Soil Mechanics, 43(7), pp.2003-2014.
• Ma, G., Rezania, M. and Nezhad, M.M., 2022. Stochastic assessment of landslide influence zone by material point method and generalized geotechnical random field theory. ASCE - International Journal of Geomechanics, 22(4), p.04022002.
• Ma, G., Rezania, M. and Nezhad, M.M., 2022. Probabilistic post-failure analysis of landslides using stochastic material point method with non-stationary random fields. In 20th International Conference on Soil Mechanics and Geotechnical Engineering (ICSMGE 2022). Sydney.
• Ma, G., Hu, X., Yin, Y., Luo, G. and Pan, Y., 2018. Failure mechanisms and development of catastrophic rockslides triggered by precipitation and open-pit mining in Emei, Sichuan, China. Landslides, 15(7), pp.1401-1414.

Selected Projects

• Shanghai Jiao Tong University-Warwick Joint Seed Fund (Prof. Lulu Zhang): Next Level Risk Assessment of Landslides using Machine Learning-Based Reliability Modelling
• Fudan-Warwick Joint Seed Fund (Prof. Jian Pu): AI-driven Deep Learning Prediction for Subsurface Characterisation Using Random Fields

Academic Recognition and Service

• Global Talent, Royal Academy of Engineering, UK
• Early Career Fellow, Institute of Advanced Study, University of Warwick
• Associate Fellow, Institute of Advanced Study, University of Warwick
• Policy Advisor, Welsh Government Coal Tips Safety Taskforce
• Corresponding Member, ISSMGE TC309: Machine Learning and Big Data in Geotechnics
• Nominee, School of Engineering Staff Award – Brilliant Newcomer 2024