The use of numerical simulation in industry faces several limitations, such as the difficulty in modeling certain physical phenomena or the computational cost which can be very high. In this context, Artificial Intelligence (AI) has emerged as a promising avenue to address this issue and allow a more efficient use of physical simulators in decision making.
In this article, Mouadh Yagoubi (IRT SystemX) and Marc Schoenauer (Inria) focus on the challenges associated with the implementation of AI-enhanced physical simulators, and we will discuss the issues related to their validation for an industrial deployment.
