Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Program
-
Employer
- University of Sheffield
- CNRS
- NIST
- ;
- Argonne
- Auburn University
- ICN2
- IFP Energies nouvelles (IFPEN)
- Institute of Fluid Flow Machinery Polish Academy of Science
- Michigan State University
- Monash University
- Nature Careers
- The Peace Research Institute Oslo (PRIO)
- UNIVERSITY OF SOUTHAMPTON
- University of Glasgow
- University of Kansas Medical Center
- University of Nebraska Lincoln
- University of Nebraska–Lincoln
- University of Nottingham
- University of Reading;
- University of Tasmania
- Université Paris-Saclay GS Chimie
- 12 more »
- « less
-
Field
-
predicting pollutant dispersion in complex environments like industrial sites remains difficult due to fluctuating wind conditions and obstacles. This PhD project offers a unique opportunity to develop
-
traitement avec un minimum d'effets secondaires, en tenant compte des profils métaboliques génotypiques et phénotypiques individuels. L'état du métabolisme cellulaire est évalué par un ensemble de différents
-
., feature engineering, spatiotemporal modeling, Bayesian calibration, ensemble methods) to improve prediction accuracy and uncertainty quantification. Disseminate research findings through presentations
-
, including renewable energy sources and energy storage systems.Development of predictive models and soft sensors for monitoring the technical condition and operational parameters of energy infrastructure (e.g
-
of conflict prediction. Lead the design and improvement of ensemble routines and validation protocols in the VIEWS forecasting system. Publish research findings in top peer-reviewed journals and contribute
-
Position Summary The Dickson, Feig, Vermaas, Wei, Woldring laboratories together form Team Green, a collaborative research effort funded by DARPA to predict protein structural ensembles, ligand
-
/unsupervised learning (regression, classification, clustering), ensemble methods, and deep learning architectures (CNNs, RNNs). Experience with explainable AI (e.g., SHAP, LIME) and radiomics preferred
-
Expertise: Familiarity with supervised/unsupervised learning (regression, classification, clustering), ensemble methods, and deep learning architectures (CNNs, RNNs). Experience with explainable AI (e.g
-
voltitude.co.uk . What You’ll Be Doing Assessing the collection of data from airborne platforms and different techniques used to quantify observation impact on forecasts. Developing code based on ensemble
-
surrogates of electronic Hamiltonians. The postdoctoral researcher will develop graph neural networks based on the MACE architecture to predict Hamiltonian elements for 2D materials and van der Waals