This open access book explores the latest advancements in simulation performance, driven by model order reduction, informed and augmented machine learning technologies and their combination into the so-called hybrid digital twins. It provides a comprehensive review of three key frameworks shaping modern engineering simulations: physics-based models, data-driven approaches, and hybrid techniques that integrate both. The book examines the limitations of traditional models, the role of data acquisition in uncovering underlying patterns, and how physics-informed and augmented learning techniques contribute to the development of digital twins. Organized into four sections Around Data, Around Learning, Around Reduction, and Around Data Assimilation & Twinning this book offers an essential resource for researchers, engineers, and students seeking to understand and apply cutting-edge simulation methodologies

This book is open access, which means that you have free and unlimited access Addresses scientific machine learning and advanced simulation techniques Structured content for postgraduate-level learning, including 60 hours of lectures and lab assignments Offers a structured learning pathway with theoretical insights and practical applications

Autorentext

Francisco Chinesta – Professor of Computational Physics at Arts et Métiers Institute of Technology, Paris and programme director at CNRS@CREATE, Singapore. His research focuses on computational physics, model order reduction, and hybrid artificial intelligence. Elias Cueto – Professor of Continuum Mechanics at Universidad de Zaragoza. His research covers model order reduction, artificial intelligence and computational mechanics. Victor Champaney – Researcher at Arts et Métiers Institute of Technology, Paris. His work specializes in model order reduction, hybrid modeling and frugal AI techniques. Chady Ghnatios – Professor of Mechanical Engineering at University of North Florida, USA. His research focuses on model order reduction, advanced simulation, machine learning and hybrid modeling. Amine Ammar – Professor of Computational Mechanics at Arts et Métiers Institute of Technology, Angers. His expertise lies in kinetic theory models, model reduction, and computational material forming. Nicolas Hascoët – Associate Professor at Arts et Métiers Institute of Technology, Paris. His research focuses on machine learning and data science for industrial applications. David Gonzalez – Professor of Continuum Mechanics at Universidad de Zaragoza. His research interests include model reduction, real-time computational simulations, and physics-informed AI. Icíar Alfaro – Associate Professor at Universidad de Zaragoza. She specializes in numerical methods, solid mechanics, and physics-informed neural networks. Daniele Di Lorenzo – Researcher at Arts et Métiers Institute of Technology, Paris. His research focuses on inverse analysis, hybrid modeling, and digital twins for structural health monitoring. Angelo Pasquale – Researcher in Computational Mechanics at Arts et Métiers Institute of Technology, Paris. He specializes in AI-enhanced simulations, model order reduction and multiscale modeling. Dominique Baillargeat – Professor at the University of Limoges and Director of CNRS@CREATE at Singapore. His research focuses on high-frequency electronics, nanotechnologies, and advanced modeling and simulation techniques using Hybrid-AI.

Klappentext

This open access book explores the latest advancements in simulation performance, driven by model order reduction, informed and augmented machine learning technologies and their combination into the so-called hybrid digital twins. It provides a comprehensive review of three key frameworks shaping modern engineering simulations: physics-based models, data-driven approaches, and hybrid techniques that integrate both. The book examines the limitations of traditional models, the role of data acquisition in uncovering underlying patterns, and how physics-informed and augmented learning techniques contribute to the development of digital twins. Organized into four sections—Around Data, Around Learning, Around Reduction, and Around Data Assimilation & Twinning—this book offers an essential resource for researchers, engineers, and students seeking to understand and apply cutting-edge simulation methodologies

Inhalt

Abstract.- Extended summary.- Part 1.Around Data.- Part 2.Around Learning.- Part 3. Around Reduction.- Part 4. Around Data Assimilation & Twinning.