Sort by
Refine Your Search
-
High-pressure XPS measurements may also be envisioned for most promising catalysts. Similarly, are we collaborating with CatTheory on predicting reaction pathways and microkinetic modelling screening
-
, aimed at uncovering the key traits that define successful microbial biofertilizers, and to develop predictive models that can guide the rational design of next-generation BioAg products tailored
-
Postdoctoral Positions in PFAS Analytics, Degradation, and Thermophysical Properties - DTU Chemistry
thermophysical properties vary across the diverse PFAS chemical space and how these properties may be predicted using computational models. These positions offer an excellent opportunity for early‑career
-
considered an advantage if you have: Experience with protein language models (e.g., ESM, ProtT5) Experience with structure prediction frameworks Experience in geometric deep learning or graph neural networks
-
for predicting sand and particle transport struggle with the cross-shore processes (perpendicular to the beach), and they even have difficulties predicting the sign right (offshore transport vs. onshore transport
-
will develop atomistic models and machine-learning potentials to interpret experimental data and predict catalytic performance. The tasks can include Advancing equivariant neural network potentials
-
digital twins be used to provide on-line predictions as to the future expected evolution of these critical properties as the basis for safe reinforcement learning (RL) for on-line optimal control”. In
-
focus on AI and machine learning and should be able to design and validate advanced control strategies for grid-forming inverters, apply AI and machine learning to battery health prediction, and
-
to the Offshore Renewable Energy Systems research group. The Postdoc will be positioned in the Esbjerg Energy Section. Research areas will focus on AI-driven control systems, grid-forming inverter technologies, and
-
on Nanoparticles You will develop atomistic models and machine-learning potentials to interpret experimental data and predict catalytic performance. The tasks can include: Advancing equivariant neural network