The Singapore-French project Descartes (-2026): Intelligent modelling for DEciSion making in CriticAl uRban sysTEmS started in . In short, this project aims at developing a hybrid AI, combining learning, knowledge and reasoning, which has good properties (need for less resources and data, security, robustness, fairness, ethics) and which aims at being applied on industrial applications of the smart city (digital energy, monitoring of structures, air traffic control).
The project brings together 80 permanent researchers (half from France, half from Singapore), with the support of large industrial groups (Thales, EDF, ESI Group, CETIM Matcor, ARIA…). The areas of research cover many disciplines, including data science, engineering, or human sciences.
Within this project, a large number of PhD students (26), post-doctoral fellows (50), and research engineers (20) will be hired between 2022 and 2024. The research will take place mainly in Singapore, at the premises of CNRS et CREATE.
A specific Work Package (WP) of the project, called “Augmented Hybrid Engineering”, deals with engineering aspects, in terms of data assimilation (hardware, sensors), modelling and simulation, as well as command and control on complex physical systems. Fundamental research is conducted, developing methodologies which are agnostic with respect to any potential application or specific physics, even though specific case studies on systems of the smart city are targeted as proofs of concept.
Hybrid-AI represents a modelling and decision-making framework that combines physics-based first principal models with data-driven AI based residual models to accurately model the underlying system dynamics, and deliver safe and explainable decision-making. One main requirement, for effective application of hybrid AI techniques for diagnosis and prognosis on real-life systems, is to be able to perform faster than real-time computations. This is a challenging task, due to the complexity of the considered systems (strong nonlinearities, multiscale aspects, interactions between system components), and this is the topic of the PhD.
In the PhD, we deal with large parametrized dynamical systems that are models describing physical systems (or systems of systems) such as those encountered in smart city. We aim at developing an effective strategy to construct and simulate such complex dynamical systems, for fast predictions. This has to be performed in an offline stage, from all available engineering knowledge (coming from physics-based models and/or from stored sensing data). We wish to address this challenge by merging/coupling reduction techniques (such as POD or PGD) on physics-based models and the data-driven Koopman operator that permits to design and manage complex dynamical systems (without knowing the underlying physics equations). In particular, we plan to build a hybrid twin in which the Koopman operator acts on a correction part of the dynamical system, complementary to the description potentially provided by a given physics-based model. We also plan to tailor the Koopman operator by using physics-based basis functions coming from model reduction.
Quantitative accuracy assessment (certification) of the resulting parametrized hybrid model will be performed, for prognosis and control purposes. Adaptive modelling will also be addressed to compute right at the right cost. The final objective of the PhD is to assess performance and validate the proposed approach on targeted applications of the Descartes programme (digital energy, monitoring of structures, air traffic control).
Strong collaborations with other researchers in the DesCartes project, working on topics of interest (learning from Koopman operator, control synthesis, etc.), will be conducted during the PhD.