PhD in AI & Digital Twins for Subsurface Energy at Southern Methodist University

The Department of Mechanical Engineering at Southern Methodist University (SMU) in Dallas, Texas, is offering a fully funded PhD opportunity focused on the application of Artificial Intelligence (AI) and Digital Twins for subsurface energy systems. This interdisciplinary research targets the development of data-informed, physics-guided models for the design, monitoring, and optimization of coupled subsurface–surface processes, including geothermal, oil & gas, and subsurface mining. Research areas include the creation of digital twins for wells, reservoirs, and surface facilities to enable real-time prediction, control, and decision support. The project leverages AI/ML techniques such as PINNs, surrogate modeling, data assimilation, and time-series forecasting, integrated with physics-based simulation (e.g., multiphase flow, heat transport, geomechanics). Additional focus areas are uncertainty quantification, sensor fusion, and techno-economic evaluation to accelerate field deployment. Applicants should hold an M.S. (or equivalent) in Mechanical, Energy, Petroleum Engineering, Geosciences, Chemical Engineering, or a related field. Required skills include proficiency in Python and/or MATLAB, experience with simulation/modeling tools (COMSOL, ANSYS, CMG, OpenFOAM), and a background in thermal/fluids, reservoir/surface systems, or subsurface engineering. Strong communication skills and evidence of research potential are essential. Candidates must be residing in the United States. Preferred qualifications include experience with PINNs/surrogates, inverse problems, HPC or cloud-based workflows, multiphase flow, geomechanics, well integrity/monitoring, and prior collaboration with industry or national labs. The position is fully funded, covering tuition and stipend. The start date is open until filled, with early applications encouraged. Interested candidates should email a single PDF application to Prof. Saeed Salehi ([email protected]) and Prof. Alaeddini ([email protected]). For more information, refer to the LinkedIn post or contact the supervisors directly.