Virtual and Physical Prototyping

Physics-based and Data-driven Models for Additive Manufacturing

Additive manufacturing (AM) has matured from rapid prototyping to the production of certified, high-value components. Yet, broader industrial adoption is still constrained by variability in part quality, rooted in the complexity of AM process physics: strongly coupled heat transfer, fluid flow, phase change, powder dynamics, and thermo-mechanical effects evolving across length and time scales. Physics-based modeling has become indispensable for revealing these mechanisms, enabling parameter development, and understanding defect formation and microstructure evolution. At the same time, AM is increasingly data-rich, driven by advances in imaging, in situ sensing, and monitoring technologies, which create new opportunities for data-driven and AI-based modeling. This Article Collection focuses on the growing convergence of physics-based simulation and data-driven approaches, aiming to accelerate predictive capability, reduce experimental burden, and support model-informed process optimization and qualification across AM technologies.

Fast, reliable predictive models are essential for strengthening confidence in AM and improving process consistency. The ability to anticipate melt pool behavior, porosity, residual stresses, and distortion directly affects build quality, cost, and part performance. Physics-based simulations provide mechanistic insights but are often computationally expensive and difficult to scale across geometries, materials, and machines. Conversely, purely data-driven models can deliver speed and adaptability but often suffer from limited generalizability and weak physical interpretability. Bridging these paradigms via hybrid modeling, multi-fidelity learning, and uncertainty-aware reduced-order frameworks enables credible digital twins for closed-loop process control and, ultimately, faster qualification workflows. This Collection addresses this need in AM by bringing together advances in scalable modeling that combine physical credibility with computational efficiency and actionable decision support.

This Article Collection welcomes contributions that advance computational modeling, simulation, and data analytics for AM across the material-process-structure chain. Topics of interest include, but are not limited to:

• High-fidelity multi-physics simulations (DEM, CFD, SPH, coupled thermo-mechanics) for process understanding
• Reduced-order and surrogate models for rapid exploration, optimization, and design
• Scientific machine learning (SciML) and physics-embedded AI for AM
• Multi-scale and multi-fidelity frameworks linking powder/melt pool dynamics to microstructure and part-scale performance
• Uncertainty quantification (UQ), sensitivity analysis, and robust optimization
• Digital twins, in situ monitoring integration, and model-based control

Preferred article types include both Original Research Articles and Review Papers, consistent with formats commonly published in Virtual & Physical Prototyping.

Keywords: Additive manufacturing (AM); Physics-based simulation; Scientific machine learning (SciML); Multi-scale / multi-fidelity modeling; Digital twins and process control

­­All manuscripts submitted to this Article Collection will undergo a full peer-review; the Guest Advisor for this Collection will not be handling the manuscripts (unless they are an Editorial Board member).

Please review the journal scope and author submission instructions prior to submitting a manuscript.

The deadline for submitting manuscripts is [31 October 2026].

Please contact Zhan Yu at [email protected] with any queries and discount codes regarding this Article Collection.

Please be sure to select "Physics-based and Data-driven Models for Additive Manufacturing" from the drop-down menu in the submission system.

Mohamadreza (Mamzi) Afrasiabi is Head of the Computational Manufacturing Group at the Advanced Manufacturing Lab (am|z) and a Senior Scientist and Lecturer at ETH Zurich. He earned his Ph.D. in Mechanical and Process Engineering from ETH Zurich in 2020, specializing in computational mechanics and manufacturing science. His research focuses on physics-based and data-driven modeling of manufacturing processes, multi-scale multi-physics simulation, and high-performance scientific computing. Dr. Afrasiabi has published over 60 peer-reviewed papers and has received multiple awards, including most recently a Best Paper Award at the International Conference on Electro-Physical and Chemical Machining in 2025.

Zhilang Zhang is currently an Assistant Professor (Principal Investigator) and Doctoral Supervisor at the School of Advanced Manufacturing and Robotics, Peking University. He previously held research positions at ETH Zurich and the National University of Singapore after earning his Ph.D. from Peking University in 2020. His research focuses on advanced computational methods for multi-scale, multi-physics problems and the full-chain "observation-simulation-optimization" research in additive manufacturing. Dr. Zhang has published over 50 papers in top-tier journals, including three ESI highly cited papers. He has won several prestigious awards, including the Best Paper Award at the International Conference on Computational Methods.