Abstract: At Michelin, the digital twin is at the heart of the group's R&D strategy. Using modern model reduction and machine learning techniques, virtual tires are now used for in-house design, in driving simulators, and to define tire-oriented services for our customers. Beyond tires, simulation and data science play a key role across the product lifecycle. During the talk, we will introduce the global context of simulation and data science usage at Michelin R&D. Then, we will focus on three example applications combining physics-based models, reduced-order modeling, physics-informed machine learning, and data assimilation techniques: (1) predicting rubber mix behavior during the manufacturing phase, (2) assessing tire hydroplaning performance during the design phase, and (3) estimating real-time tire grip during the usage phase. These examples will illustrate how hybrid approaches leveraging physics and data are paving the way toward robust, efficient, and versatile digital twins.