Webinars

Engineering simulations play a critical role in design and analysis, but their high computational cost can make their use for optimization impractical or impossible. Surrogate modeling is a powerful alternative, enabling rapid, data-efficient optimization by replacing the expensive simulation with a fast-running predictive machine learning model. With a surrogate modeling approach to optimization, first a machine learning (aka surrogate) model is trained to predict the simulation results. The optimization is then performed on the surrogate, rather than the original, more computationally expensive simulation. SmartUQ supports this approach with surrogate modeling options having best-in-class accuracy, speed, and flexibility. Join us for this webinar in which SmartUQ principal application engineer, Gavin Jones, will introduce surrogate modeling and its benefits to optimization workflows. The session will cover how surrogate models are trained, validated, and used to efficiently explore design spaces and identify optimal solutions with fewer simulation runs.