Sort by
Refine Your Search
-
Listed
-
Category
-
Employer
-
Field
-
according to their background and interests. Applicants should have strong quantitative and computational skills (e.g., text or image analysis, natural language processing, large-scale data methods) and a
-
frequent cloud contamination. This scale mismatch prevents a coherent representation of radiative–thermal processes at the urban scale. This PhD will develop physics-informed deep learning models for data
-
of heat transfer and turbulence physics in wall-bounded flows through numerical simulations, data-driven modelling, and machine learning techniques. Key goals include optimising convective heat transfer
-
parameters to identify regimes that ensure both flame stability and low pollutant emissions. Machine learning techniques have recently shown promise for Design of Experiments (DoE) and interpretation of large
-
. The project proposes an innovative approach to model sea ice dynamics from the ice floe scale to the basin scale, leveraging hybrid data assimilation and machine learning methods to shape a physically robust
-
well as decentralized machine learning algorithms for large-scale clouds with dynamique parameters. -- Conception of machine learning algorithmes for resource allocation -- Numerical experiments -- Drafting research
-
Inria, the French national research institute for the digital sciences | Montbonnot Saint Martin, Rhone Alpes | France | about 1 month ago
-tutelle agreement, further strengthening the international dimension of their training and research. Assignment. Effectively protecting personal data is challenging. A large number of protection mechanisms
-
experimental data (from ex-situ and in-situ measurement). Therefore, she/he will develop a way to optimize/guide the experiments trough artificial intelligence approach (machine/deep learning) that he will
-
Arts et Métiers Institute of Technology (ENSAM) | Paris 15, le de France | France | about 2 months ago
. This issue can have safety implications, particularly in closed-loop setups. Physically Informed Machine Learning (PIML), and in particular Physics-Informed Neural Networks (PINN), are less dependent on data
-
: electronic structure calculations (plane wave DFT if possible), statistical thermodynamics, molecular dynamics. Skills in Python, bash scripting, Fortran 90 and machine-learning would be appreciated. The PIIM