This talk presents two physics-informed methods to search high-dimensional continuous spaces in a sample efficient way, with a focus on transportation problems. The first method uses a physics model to design a sampling distribution that enhances the exploration step of general-purpose simulation-based optimization algorithms. The second presents various ways in which physics models can be combined with Gaussian processes and Bayesian optimization to tackle high-dimensional problems. The methods are illustrated with challenging New York City traffic signal control case studies.