Machine Learning for Sparse Nonlinear Modeling and Control

Abstract

This work describes how machine learning may be used to develop accurate and efficient nonlinear dynamical systems models for complex natural and engineered systems.  We explore the sparse identification of nonlinear dynamics (SINDy) algorithm, which identifies a minimal dynamical system model that balances model complexity with accuracy, avoiding overfitting.  This approach tends to promote models that are interpretable and generalizable, capturing the essential “physics” of the system.  We also discuss the importance of learning effective coordinate systems in which the dynamics may be expected to be sparse.  This sparse modeling approach will be demonstrated on a range of challenging modeling problems, for example in fluid dynamics, and we will discuss how to incorporate these models into existing model-based control efforts.