Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Field
-
for all. This PhD project aims to develop, physics-informed surrogate models to support the design and optimisation of deep geothermal energy systems under subsurface uncertainty. Focusing initially
-
EPSRC ReNU+ CDT PhD Studentship: Physics-informed machine learning for deep geothermal systems under uncertainty. Award Summary 100% fees covered, and a minimum tax-free annual living allowance
-
scenarios while accounting for uncertainty in key subsurface properties. An averaged continuum approach based on Darcy’s law and heat conservation aims to enable efficient simulation at reservoir scale, with
-
change, market dynamics, and daily grid variations. These factors contribute to heightened structural and control complexity, along with multiple layers of uncertainty. In this context, Hybrid Power Plants
-
under uncertainty (Studentship code MSP106) Learning to sample: Meta-optimisation of gradient flows using reinforcement learning (Studentship code MSP107) Dynamic Bayesian modelling of endurance sports
-
exceeding $2.5 million. Research activities are conducted in multiple research laboratories at the Department and research centers in the College and the University. Job Description: The Department
-
with unknown but presumably large prediction uncertainties, their broad application is hindered. This is especially a problem in application areas that require robust and trustworthy solutions, such as in
-
potential (PPST) and therefore, in accordance with regulations, requires your arrival to be authorized by the competent authority of the MESR. This PhD project will investigate modeling uncertainties in flame
-
reservoirs; and (ii) evaluating reservoir performance under a range of operational scenarios while explicitly accounting for uncertainty and variability in key subsurface properties such as porosity
-
uncertainty, modality dropout, and noise propagation, which can degrade robustness and erode trust in model outcomes. This project aims to create a unified framework for building lightweight, data-efficient