Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Employer
- Technical University of Denmark
- Cranfield University
- NTNU - Norwegian University of Science and Technology
- ; The University of Manchester
- Monash University
- ; University of Warwick
- Chalmers University of Technology
- Curtin University
- Forschungszentrum Jülich
- SciLifeLab
- University of Groningen
- Utrecht University
- ; Brunel University London
- ; St George's, University of London
- AALTO UNIVERSITY
- DAAD
- Erasmus University Rotterdam
- Ghent University
- Harper Adams University
- ICN2
- Imperial College London
- KNAW
- Leibniz
- Norwegian Meteorological Institute
- Radboud University
- University of Cambridge
- University of Newcastle
- University of Nottingham
- University of Sheffield
- University of Southern Denmark
- University of Twente
- University of Utah
- Vrije Universiteit Brussel
- Wageningen University and Research Center
- 24 more »
- « less
-
Field
-
predictably to in-context demonstrations? What controls their ability to generalize, even when it contradicts their training? This project will involve developing a theoretical framework to explain in-context
-
to mechanical forces. We work with leading international groups on modeling and also conduct simulations at DTU. Our overarching goal is to understand and predict the mechanical behavior of metals during plastic
-
and machine learning to establish a modeling framework that uses omic data for providing effective degradation rates of biomolecules and predictions of their impact on soil organic matter turnover
-
: Computational Modelling: Employing simulation tools (e.g., GEANT4, light transport) to explore novel metamaterial designs, predict performance, and optimise key parameters such as timing resolution, light yield
-
with microstructural features and failure mechanisms Development of models to describe degradation mechanisms and predict component lifetime Presentation of research findings at project meetings
-
resulting properties. However, two significant challenges persist in this domain. First, the extrapolation of ML predictions beyond the range of existing data remains problematic, as models often struggle
-
control system that enhances Annual Energy Production (AEP), reduces mechanical stress, and improves fault detection using machine learning (ML) and physics-based modelling. The candidate will gain hands
-
load predictions for wind turbines, specifically the foundations, with the ultimate objective of including structural health information in windfarm asset management to optimise structural lifetime
-
recovery in critical applications, including aerospace, healthcare, and industrial automation. Research Focus Areas: Predictive Analytics for Fault Detection: Develop AI models that predict potential system
-
AI models. Identifying relevant modalities to enhance prediction performance, with a focus on multi-spectral sensors, will be a key research area. Additionally, anomaly detection for modalities other