Gaussian processes are a powerful and versatile tool, particularly well suited for the emulation of complex numerical models arising in computer experiments, including those used to simulate engineering systems. Such experiments are often computationally expensive, making it impractical to run them at the scale needed to fully characterise continuous input–output relationships. In this talk, I will present my work on using Gaussian process models to emulate the deterioration of infrastructure earthworks, demonstrating how these methods can provide efficient and informative surrogates for costly simulations.
Alex Svalova - Lecturer in Statistics at Newcastle University. Research focuses on Gaussian processes, with applications spanning areas such as environmental pollution and engineering. I am particularly motivated by opportunities to collaborate with engineers in both academia and industry to address real-world challenges. I am also interested in recent developments in Gaussian process emulation and their potential to advance practical applications.
Book now