Digital Twin
Digital twins are virtual representations of physical systems, aiming to mirror their behavior and enable predictive modeling, optimization, and analysis. Current research emphasizes developing digital twins across diverse domains, from supercomputers and transportation systems to healthcare and manufacturing, often employing machine learning models (like transformers and neural ODEs), graph-based methods, and large language models for data integration, prediction, and control. This technology's significance lies in its ability to improve efficiency, safety, and decision-making in various sectors by providing a virtual testing ground for complex systems and facilitating data-driven insights.
Papers
Learning Physics between Digital Twins with Low-Fidelity Models and Physics-Informed Gaussian Processes
Michail Spitieris, Ingelin Steinsland
A Machine Learning-based Digital Twin for Electric Vehicle Battery Modeling
Khaled Sidahmed Sidahmed Alamin, Yukai Chen, Enrico Macii, Massimo Poncino, Sara Vinco
HDL: Hybrid Deep Learning for the Synthesis of Myocardial Velocity Maps in Digital Twins for Cardiac Analysis
Xiaodan Xing, Javier Del Ser, Yinzhe Wu, Yang Li, Jun Xia, Lei Xu, David Firmin, Peter Gatehouse, Guang Yang
Transfer Learning as an Essential Tool for Digital Twins in Renewable Energy Systems
Chandana Priya Nivarthi