A Comprehensive Machine Learning Framework for Digital Twins: Data Collection, Surrogate Modeling, and Calibration
Thu, Apr 30, 2026 9:00 AM - 10:00 AM CDT
This webinar will discuss the role of machine learning (ML) in digital twins. In particular, three key topics essential to digital twins will be covered: Data collection, via modern design of experiments (DOEs) and ML data sampling techniques, predictive ML models (aka surrogate models), and statistical calibration.
Digital Twins require data, speed, and predictive accuracy. SmartUQ delivers in all these areas with:
• A large variety of modern, unique, and more efficient DOEs and data sampling tools.
• ML models with best-in-class speed and predictive accuracy.
• Unique statistical calibration approaches for better aligning models including digital twin models with physical data.
Join us for this webinar in which SmartUQ Principal Application Engineer, Gavin Jones, will introduce the use of SmartUQ for Digital Twins. The framework that will be presented applies to all manner of digital twins including design twins, manufacturing twins, and operational twins. The presentation will also include examples from customer use cases and a software demonstration.

Presented by Gavin Jones, Principal Application Engineer
Gavin Jones serves as a Principal Application Engineer at SmartUQ, where he is responsible for performing simulation and AI work for clients in the automotive, aerospace, defense, semiconductor, and other industries. He is a member of the SAE Chassis Committee as well as the AIAA Digital Engineering Integration Committee. Gavin is also a key contributor in SmartUQ’s Digital Twin/Digital Thread initiative.