Job announcements relevant to people interested in electronic structure calculations…
Due to the large number of posts recently, there is currently a delay of several weeks between posts being submitted and the corresponding emails being distributed to all users. Please bear with us while we try to improve this. In the meantime – and until this notice is removed – it would assist us considerably if you could submit only important and/or urgent posts and thus help to reduce the size of the mail queue. Under no circumstances should you resend posts multiple times when you find the emails are not distributed immediately.
In light of the Russian military offensive in Ukraine, we request that announcements relating to events, jobs and other activities associated with institutions supported by the Russian and Belarusian states are not posted to the Psi-k forum.
Post doctoral position at CEA/DES/IRESNE (Cadara ... (No replies)
Back to Job listings...
«Generative deep learning modelling of atomic transport properties in chemically disordered nuclear fuels »
Machine learning is nowadays of common use in materials science to improve the predictive capabilities of physical models. Machine learning interatomic potentials (MLIP) trained on electronic structure calculations have become the standard tools for running efficient yet physically accurate molecular dynamics simulations. More recently, generative deep learning models are explored to learn a hidden property distribution in an unsupervised manner, and generate new structures according to this hidden distribution. This is of particular interest for chemically disordered solid solutions, whose properties depend on the distribution of chemical species in the crystal lattice In this case, the number of possible configurations is so high that an exhaustive sampling of this space is beyond the reach of conventional methods. An example is given by uranium plutonium mixed oxides (MOX), a type of nuclear fuel that allows for a drastic reduction of the volume and radiotoxicity of spent fuel waste. The goal of this project is to combine MLIPs and generative methods to address atomic diffusion properties in MOX .The candidate will explore the use of various models (e.g. autoencoders) to find the collective variables that best describe the atomic diffusion trajectories, and to select the most representative atomic structures among the many possible ones. The most appropriate model will then be used to determine the diffusion coefficients of host species and fission products, which are essential for predicting the irradiation induced microstructure evolution and thus the in reactor behaviour of MOX fuels.
The work will be carried out at the Nuclear Fuel Department of the CEA, in a scientific environment characterised by a high level of expertise in materials modelling, and in close collaboration with other CEA teams in the Paris region specialised in machine learning methods. The results will be promoted through scientific publications and participation in international conferences.
References
https://doi.org/10.1126/science.aaw1147
https://doi.org/10.1021/acs.jctc.0c00355
https://doi.org/10.1103/PhysRevMaterials.5.103803
Contact
Luca MESSINA
IRESNE | DEC I SESC I LM2C
[email protected]