Description

Symbolic regression is used to discover mathematical expressions of functions that can fit the given data based on the rules of accuracy, simplicity, and generalization. As distinct from linear or nonlinear regression that efficiently optimizes the parameters in the pre-specified model, SR tries to seek appropriate models and their parameters simultaneously for a purpose of getting better insights into the dataset. Without any prior knowledge of physics, kinematics, and geometry, some natural laws described by mathematical expressions, such as Hamiltonians, Lagrangians, and other laws of geometric and momentum conservation, can be inferred from experimental data by the Genetic Programming method on symbolic regression. The aim of this project is to investigate the use of available libraries for symbolic regression and assess their usefulness to identify and characterise missing components of dynamical equations. The project requires VERY GOOD programming skills (Matlab and/or Python) and very good data analytics skills.

Key Objectives

• identification of one or more suitable libraries already available for symbolic regression;

• identification or creation of a suitable database containing aerothermodynamic data;

• test of the identified libraries on the available database and critical assessment of the performance in terms of usability, accuracy, and compuytational costs.