Chair objectives

Scientific machine learning (SciML) has expanded the capabilities of traditional numerical approaches, by simplifying computational modeling and providing cost-effective surrogates. However, SciML surrogates suffer from absence of the explicit error control, computationally intensive training phase, and the lack of reliability in practice.

The chair HAILSED aims to tackle these challenges by (1) developing novel types of SciML surrogates, the architecture of which incorporates physical and geometric constraints explicitly, and whose validation error can be controlled a posteriori,

Principal investigator

  • Alena Kopaničáková (Toulouse-INP/IRIT, Toulouse, France; Università della Svizzera italiana, Lugano, Switzerland)

(2) developing novel training algorithms, that leverage domain-decomposition-based approaches and utilize model parallelism, (3) hybridizing SciML surrogates with state-of-the-art numerical solution methods, which will be achieved by developing AI-equipped nonlinear field-split and domain-decomposition-based preconditioning strategies

Co-chair

Successful realization of the proposed methodologies will pave the way towards efficient and errorcontrolled solutions to large-scale multi-physics and multi-scale problems by effectively combining the efficiency of SciML surrogates with the accuracy and reliability of standard numerical approaches.

This is an absolute necessity in order to apply SciML approaches to real-world industrial applications in the near future.

Le projet de cette chairee est réalisé en collaboration avec des partenaires académiques de l’EPFL (Suisse), de l’Università della Svizzera Italiana (Suisse), KAUST (Arabie Saoudite) et des Sandia National Laboratories (États-Unis). Par ailleurs, les entreprises AIRBUS, VITESCO, et LIEBHERR ont déjà manifesté leur intérêt pour les sujets proposés par la chaire.

Ne manquez rien !

Inscrivez-vous pour recevoir l'actualité d'ANITI chaque mois.

Nous n’envoyons pas de messages indésirables !

en_GBEnglish