Description As the design of complex engineering systems evolves, so is the demand for higher accuracy in the numerical simulations and design tools. AI techniques, such as machine learning algorithms, can be used to build computationally fast surrogate models. This can then be used in a systems-wide design optimisation. One popular implementation is in the models for the aerodynamics of a launch vehicle, that covers a wide range of flight regimes and flight conditions.   Key Objectives This project will: 1- develop models for a test suite of launch vehicles within Matlab, 2- develop an aerodynamic database, 3- implement and compare different surrogate modelling methods, using Statistics and Machine Learning Toolbox) for the aerodynamic database.  A background in programming, preferrably in Matlab or Python, is essential.