Simulation and artificial intelligence are becoming a single, powerful ecosystem for understanding and shaping the world. From digital twins and reinforcement learning to large language models and synthetic data, this volume captures how AI and modeling and simulation together are redefining how we explore complexity, uncertainty, and decision-making.
Artificial Intelligence and Modeling and Simulation brings together leading researchers who show how AI can support every stage of a simulation study, from model specification and input modeling to execution, verification, and analysis. It also demonstrates how simulations provide critical data, training environments, and validation platforms for AI. Chapters are supplemented by exercises, including in-depth exploratory questions that provide a guided, hands-on experience. The volume offers a coherent roadmap for navigating an increasingly interconnected ecosystem of models, data, and learning algorithms.
Topics and features:
- Complete coverage of the AI-simulation pipeline, from conceptual modeling and input modeling to verification, validation, and result interpretation - State-of-the-art methods including surrogate modeling, reinforcement learning, and large language models applied directly to modeling and simulation problems - Rigorous treatment of verification, validation, and benchmarking, including risks, uncertainty, and the limits of black-box models - Interdisciplinary case studies spanning healthcare, energy, political history, wildlife education, and evacuation This book provides comprehensive research guidance on methods, applications, and open problems at the interface of artificial intelligence and modeling and simulation. This is written for researchers and graduate students who seek research methods in AI and simulation, as well as for industry professionals and practitioners in data science or digital twins.
The book is edited by Dr. Philippe Giabbanelli (full professor by research at Old Dominion University, USA) and Dr. Istvan David (assistant professor at McMaster University, Canada). Contributions to the chapters come from 28 authors across 20 institutions (reflecting perspectives from academia, industry, and national laboratories) in four countries.
About the Author :
Dr. Philippe Giabbanelli is a Full Professor at Old Dominion University. His work has combined Artificial Intelligence (AI) with Modeling & Simulation (M&S) for fifteen years, resulting in over 130 peer-reviewed articles and several books. Most recently, he was the lead editor for "Fuzzy Cognitive Maps" (Springer) and previously he was lead editor for "Advanced Data Analytics in Health" (Springer). By integrating AI with M&S, his research made significant advances in a broad portfolio of conditions including obesity, suicide prevention, COVID, or HIV. He has been recognized as a top 2% scientist worldwide by Scopus for several years. He is well established in the simulation community, as track/program/conference chair at several international events as well as prior editor for special issues of SIMULATION, a founding member of several journals (BMC Digital Health, Intelligence-Based Medicine), and an editorial member or guest editor for several journals.
Dr. Istvan David is actively engaged on several topics in modeling and simulation, including modeling and simulation of cyber-physical systems, automated simulator engineering, collaborative modeling, and model consistency in heterogeneous engineering settings. He is an organizer for multiple events in the M&S community, including multiple editions of the IEEE/ACM MODELS conference; and frequently serves on the PC of important conferences, including CAiSE, ICLR, and SLE. He founded the International Workshop on Collaborative and Participatory Modeling, the Hands-on Workshop on Collaborative Modeling, and the International Workshop on Sustainability and Modeling; and served as track chair and vice-general chair at international events. He served as a guest editor for journal issues for Springer, SAGE, and Elsevier. He has over 50 publications with a focus on highly recognized venues, including flagship conferences in modeling (such as IEEE/ACM MODELS, and CAiSE) and impactful journals in software and systems engineering (such as IEEE Transactions on Software Engineering, Elsevier's Journal of Systems and Software, and Springer's Software & Systems Modeling).
