Dealing with Uncertainty Quantification, monitoring, and data assimilation in computational mechanics requires the fusion of several strategies for the sake of computational efficiency. Physics-Enhanced Machine Learning [1] (PEML, also referred to as scientific machine learning) nowadays provide a wealth of tools to enhance the integration of information that is typically extracted from real-world data, physics-based models and domain and expert knowledge, thus representing an overarching paradigm when dealing with complex systems in computational mechanics. Recent advances in machine learning, among many algorithmic methods of PEML, have allowed to overcome several bottlenecks often hindered by high dimensionality and significant complexity, opening new horizons for data-driven predictive modelling in computational mechanics, and impacting on efficient numerical strategies often used in UQ, such as surrogate models and reduced order models. However, several issues are still open, such as the integration of learning algorithms within UQ techniques, the use of learning paradigms naturally accounting for uncertainties such as Bayesian and kernel methods, the construction of reliable and robust strategies to handle large-scale problems such as multi-fidelity methods for data fusion, the setting of data assimilation procedures relying on latent dynamics modelling capable to adapt in rapidly evolving phenomena [2]. This minisymposium will gather a broad spectrum of contributions in this very vibrant research area, covering the theoretical analysis, computational techniques, and practical use of machine/deep learning, data assimilation, filtering, monitoring, and UQ techniques, as well as their interaction, all towards efficient and accurate predictions in computational mechanics. REFERENCES [1] A. Cicirello, Physics-Enhanced Machine Learning: a position paper for dynamical system investigations, Journal of Physics: Conference Series, 2909 (2024), 012034. [2] L. Rosafalco, P. Conti, A. Manzoni, S. Mariani and A. Frangi, Online learning in bifurcating dynamic systems via SINDy and Kalman filtering, Nonlinear Dynamics, 113 (2025), 14201-14221.