45 modelling-complexity-geocomputation PhD positions at Delft University of Technology (TU Delft)
Sort by
Refine Your Search
-
PhD Position on Machine Learning Detection of Positive Tipping Points in the Clean Energy Transition
Infrastructure? No Offer Description Develop machine learning models to detect early signs of abrupt shift towards clean energy technologies and make climate action adaptive to this information. Job description
-
that inherently exhibit complex frictional interfaces. These joints play a critical role in vibration damping and energy dissipation, but the underlying mechanisms remain poorly understood and difficult to model
-
involved, leads to complex logistics problems. The planning of rolling stock circulations and the regular maintenance at the various service locations is typically done by different planners. In addition
-
the initial phase, you will develop and optimize physical and numerical models describing the electron optics of the complete probe-forming column, including the multi-beam generation unit, imaging lenses
-
an important contribution to solving complex technical-social issues, such as energy transition, mobility, digitalisation, water management and (cyber) security. TPM does this with its excellent education and
-
the potential of LLM-based automated refactoring of codebases with the ultimate goal of reducing software complexity and improving code quality. We will investigate how LLMs can support and automate tasks such as
-
AI methods and tools that capture the complexity of the port call process and handle uncertainties caused by the energy transitions. In collaboration with the other researchers, this will include
-
make extensive use of low-fidelity simulations which can provide fast but inaccurate solutions depending on the flow complexity. To close this gap, this PhD will explore machine-learning (ML) methods
-
. However, while the leaky integrate-and-fire (LIF) neuron is the current de-facto neuron model in neuromorphic hardware, it embeds only one single time constant limited to a few tens of milliseconds
-
experimental data, enabling accurate prediction of nonlinear phenomena such as modal interactions and dissipation pathways across scales: from complex structural assemblies to nanomechanical resonators. In