Summary
Connor Robertson is a Postdoctoral Researcher at Sandia National Laboratories with nine years of experience applying scientific machine learning to surrogate modeling, Bayesian and variational inference, and data-driven model discovery for complex physical and biological systems. He bridges theory and practice by turning experimental video, agent-based models, and noisy spatiotemporal data into calibrated predictive models using tools from Gaussian processes and neural differential equations to Stein variational inference and MCMC. His PhD work extracted governing PDEs from active nematic experiments, and his projects have ranged from forecasting bacterial colony growth with recurrent networks to predicting urban water-main failures as a cofounder of a startup. Based in Bentonville, Arkansas, he combines strong numerical analysis and teaching experience with a track record of translating computational mathematics into deployable surrogate models for real-world decision-making.
9 years of coding experience
Doctor of Philosophy - PhD, Applied Mathematics, Doctor of Philosophy - PhD, Applied Mathematics at New Jersey Institute of Technology
Bachelor of Science - BS, Computational and Applied Mathematics, Bachelor of Science - BS, Computational and Applied Mathematics at Brigham Young University
English, Spanish