Bifidelity Karhunen-Lo`eve Expansion Surrogate with Active Learning for Random Fields
This method creates efficient models for complex field data by combining low-fidelity simulations with high-fidelity ones. It uses Karhunen–Loève expansions and polynomial chaos to build a bifidelity surrogate that learns from cheap simulations and strategically selects the most informative high-fidelity simulations using active learning to maximize accuracy efficiently.