You are here
ENERGY : TTP Digital twins for modern power electronics applied to emerging energy systems
AS2M : Junior Professorship Explainable and Physically Informed Artificial Intelligence for Data-Driven Modelling of Complex Dynamic Systems
Explainable and physically informed artificial intelligence for data-driven modelling of complex dynamic systems
Profile of a Junior Professor whose keywords are : AI/deep learning, dynamical systems, automatic control, neuroscience.
SUPMICROTECH's overall strategy is therefore based around 3 major societal challenges, on which the school and its FEMTO-ST laboratory are positioned, with the shared ambition of developing and advancing knowledge
and technologies in the field of micro- and nanotechnologies: environment, transport and green energy; health and biomedical; digital and artificial intelligence (industry of the future or 4.0).
The profile of the post also fits in more generally with the themes supported by the site policy of the Université Marie et Louis Pasteur (UMLP) through its Institute of Technology, in which SUPMICROTECH is fully integrated. The Lecturer/Researcher recruited will thus be expected to contribute to increasing the pedagogical transformation and international attractiveness of the Masters courses offered by the UMLP Institute of Technology. Participation in the construction of a Research-Training link in the regional higher education and research area will be encouraged, in particular by working on bridges between SUPMICROTECH's engineering courses and the Masters courses at the Institute of Technology. It will be able to benefit from the support of the PIA Graduate School EIPHI project as part of its various calls for projects, whether they concern training or research.
The aim of this CPJ is to set up a research programme on the theme of explainable and physically-informed AI for modelling dynamic systems, and to steer a strong and original vision for the place of AI in the school's scientific and educational project. This research programme aims to develop the next generation of machine learning tools for controlling complex physical or physiological systems, using a data-driven approach to discover physically interpretable models of dynamic systems based on temporal data. For example, the project could be part of the recent emergence of data-driven methods for identifying dynamic systems (e.g. physics-informed neural networks, PDE discovery, operator learning) from the scientific machine learning community. This work could be applied in particular to the modelling of biological systems, to provide new diagnostic or prognostic tools in neuroscience or cancerology, or new micromanipulation techniques for cell characterisation or surgery.
Composition of the application :
o Online application form
o Photo ID
o Proof of possession of a doctorate, as provided for in article L.612-7 of the Education Code, or of a degree whose equivalence is recognised in accordance with the procedure set out in 1° of article 5 of the Decree of 17 December 2021
o Thesis defence and pre-thesis defence reports
o Analytical presentation (CV, work, books, articles, achievements)
The application must be submitted no later than 2 June 2025.
AS2M Director : yann.le.gorrec@ens2m.fr
