Nanzhe Wang

This fully funded PhD opportunity at Heriot-Watt University, offered through the Iapetus Doctoral Training Partnership, focuses on the integration of artificial intelligence and geoscience for the advancement of geothermal energy systems. The project, titled 'Intelligent Geothermal Energy Development: AI-Enhanced Modelling and Decision-Making Under Uncertainty,' aims to develop innovative AI-driven frameworks for modelling, exploration, and management of geothermal reservoirs. The research combines scientific machine learning, reinforcement learning, surrogate reservoir modelling, and uncertainty quantification to optimize geothermal reservoir management and exploration strategies. The interdisciplinary supervisory team includes experts from Heriot-Watt University, Durham University, and Queen Mary University of London, covering AI, subsurface engineering, heat and mass transfer, and environmental science. The student will receive comprehensive training in AI, machine learning, numerical simulation, and geoscience, with opportunities for field trips, conference participation, and engagement with industry partners. The project supports the UK Geothermal Strategy and AI sector objectives, with broader applications in subsurface technologies such as carbon storage and mineral exploration. Funding covers tuition, stipend, and research support for 3.5 years. UK home students should apply by January 5th, while international applicants must contact the primary supervisor by December 8th due to limited places. Applicants should have a strong background in a relevant discipline and a keen interest in interdisciplinary research. For more details and to apply, visit the provided links or contact Dr. Nanzhe Wang for informal enquiries.

Heriot-Watt University, under the supervision of Assistant Professor Nanzhe Wang, is recruiting PhD students for research in AI-enabled geoenergy and subsurface systems. The research focuses on integrating artificial intelligence, physics-based modelling, scientific machine learning, and probabilistic algorithms to address challenges in subsurface energy systems. Applications include geological carbon storage, geothermal energy, subsurface hydrocarbon reservoirs, and groundwater systems, all supporting the energy transition and net-zero goals. Key research topics include hybrid physics–AI modelling and inversion for geoenergy and subsurface flow systems, multi-source and multi-scale data assimilation, uncertainty quantification, digital twins for subsurface energy systems using generative AI and surrogate models, uncertainty-aware decision-making and control, and active learning for efficient inversion and optimization. The research is highly interdisciplinary, combining computer science, earth science, and environmental science. Applicants should have a strong background in engineering, data science, geoscience, applied mathematics, physics, or computer science, with programming skills in Python, MATLAB, or PyTorch/TensorFlow. Experience or interest in subsurface flow modelling, geoenergy, and AI/machine learning is desirable. Candidates must be self-funded or have external funding, with possible routes including the China Scholarship Council (CSC), PTDF Overseas Scholarship Scheme (Nigeria), LPDP Overseas Scholarships (Indonesia), Bangabandhu Science and Technology Fellowship Trust (Bangladesh), or other sponsorships. Academic support letters are available for suitable candidates seeking funding. To apply, interested candidates should contact Dr. Wang by email with a brief CV, academic transcripts, a short description of research interests, and funding status. The position is based in Edinburgh, Scotland, United Kingdom, at Heriot-Watt University.

Professor Nanzhe Wang at Heriot-Watt University is recruiting PhD students for research in AI-enabled geoenergy and subsurface systems. The research focuses on integrating physics-based modelling and artificial intelligence to address uncertainty quantification, data assimilation, and decision-making in subsurface energy systems. Applications include geological carbon storage, geothermal energy, hydrocarbon reservoirs, and groundwater systems, all of which are critical for supporting the energy transition and achieving net-zero goals. PhD research topics include hybrid physics–AI modelling and inversion for geoenergy and subsurface flow systems, multi-source and multi-scale data assimilation, digital twins for subsurface energy systems using generative AI and surrogate models, uncertainty-aware decision-making and control for subsurface operations, and active learning for efficient inversion and optimisation. The ideal candidate will have a background in engineering, data science, geoscience, applied mathematics, physics, or computer science, with programming skills in Python, MATLAB, PyTorch, or TensorFlow, and an interest or experience in subsurface systems, geoenergy, and AI/ML. Funding is available through various external scholarships, including the China Scholarship Council (CSC) for Chinese students, PTDF Overseas Scholarship Scheme (Nigeria), LPDP Overseas Scholarships (Indonesia), Bangabandhu Science & Technology Fellowship Trust (Bangladesh), and other national or industrial sponsorships. Eligible candidates can receive academic support letters for their funding applications. To apply, candidates should email Professor Wang with their CV, academic transcripts, a summary of research interests, and funding status. This opportunity is ideal for students interested in AI, earth science, environmental science, and the application of advanced computational methods to energy and sustainability challenges.

PhD Studentship Opportunity: Machine Learning for Groundwater Pollution at Heriot-Watt University, Edinburgh, UK. This fully funded PhD is offered through the Iapetus DTP NERC Doctoral Training Partnership (DTP) Studentship Competition 2026–27. The project title is Reconstructing Groundwater Pollution Release Histories under Geological Uncertainty Using Machine Learning and Adaptive Monitoring . The research combines several high-impact areas: groundwater flow and contaminant transport modelling, machine learning and AI surrogate modelling, Bayesian inversion, data assimilation, uncertainty quantification, reinforcement learning, and adaptive monitoring design. It is well suited to students interested in environmental science, hydrogeology, geoscience, geoenergy, computational modelling, applied mathematics, and AI for subsurface systems. Host and supervision: The host institution is Heriot-Watt University in Edinburgh, UK. The supervisory team includes Dr Nanzhe Wang (Heriot-Watt University), Dr Marco Bianchi (British Geological Survey), and Dr Yihuai Zhang (University of Glasgow). Funding: The studentship is competitive and fully funded for 3.5 years, covering tuition fees at the UK Home rate, a stipend, and research and training support. International fee arrangements depend on host university policy. Eligibility: Applicants with backgrounds in hydrogeology, geoscience, geoenergy, environmental science, computational modelling, machine learning, applied mathematics, or related disciplines are welcome. The opportunity is aimed at PhD candidates. Home and sponsored international applicants may apply; international applicants must contact the supervisor in advance, and each supervisory team can shortlist a maximum of one international applicant. Application window: Applications open on 6 November 2026. The deadline for Home and sponsored international applicants is 5 January 2027 at 12:00 noon GMT. International applicants must email [email protected] by Monday, 7 December 2026. How to apply: Read the project page via the application link, check eligibility, and submit your application within the stated window. International applicants should first contact Dr Nanzhe Wang by email before applying.