Introduction of Applied Aerodynamics Surrogate Modeling Benchmark Cases

Abstract

From aircraft design to certification, a significant volume of aerodynamic data is required to ensure optimal performance, meet regulatory standards, and maintain structural integrity. These data must span the entire flight envelope, encompassing pressure and shear stress distributions, global coefficients, and derivatives. Traditionally sourced from flight tests, wind tunnel experiments, or numerical simulations, the data are often of varying fidelity, ranging from handbook methods to high-resolution simulations. In recent years, the demand for efficient use of these data has grown, driven by advancements in artificial intelligence and machine learning, enabling the development of fast-running surrogate models. Unlike traditional high-fidelity simulations or experimental setups, which can be resource-intensive, surrogate models trained on these data sets deliver rapid predictions comparable to database queries. The AIAA Applied Aerodynamics Surrogate Modeling (AASM) group was formed to bring focus to data-driven and AI modeling in aerospace sciences, uniting experts from academia, industry, and government agencies worldwide. The AASM group prioritizes the development, accuracy, and applicability of surrogate modeling for aerospace applications, including design optimization, uncertainty quantification, systems engineering, and mission analysis—all critical to a digital engineering ecosystem. To support evaluation and comparison of methodologies, this paper introduces four benchmark cases: an aerodynamic database of integrated airfoil performance coefficients, a missile case for 6DOF generation, and two data sets focusing on surface pressure distributions. These benchmarks highlight associated surrogate modeling challenges and will be made publicly available through AIAA, offering valuable resources for the aerospace community.