Hybrid analysis and modeling, eclecticism, and multifidelity computing toward digital twin revolution
arXiv:2103.14629
Abstract
Most modeling approaches lie in either of the two categories: physics-based or data-driven. Recently, a third approach which is a combination of these deterministic and statistical models is emerging for scientific applications. To leverage these developments, our aim in this perspective paper is centered around exploring numerous principle concepts to address the challenges of (i) trustworthiness and generalizability in developing data-driven models to shed light on understanding the fundamental trade-offs in their accuracy and efficiency, and (ii) seamless integration of interface learning and multifidelity coupling approaches that transfer and represent information between different entities, particularly when different scales are governed by different physics, each operating on a different level of abstraction. Addressing these challenges could enable the revolution of digital twin technologies for scientific and engineering applications.
References in corpus (9)
- Discovering Symbolic Models from Deep Learning with Inductive Biases
- Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control
- Universal Differential Equations for Scientific Machine Learning
- Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems
- Automating Turbulence Modeling by Multi-Agent Reinforcement Learning
- Dissecting Deep Neural Networks
- Generation of High-Resolution Handwritten Digits with an Ion-Trap Quantum Computer
- A Probabilistic Graphical Model Foundation for Enabling Predictive Digital Twins at Scale
- COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning