The integration of data and scientific computation is driving a paradigm shift across the engineering, natural, and physical sciences. Indeed, there exists an unprecedented availability of high-fidelity measurements from time-series recordings, numerical simulations, and experimental data. When coupled with readily available algorithms and innovations in machine (statistical) learning, it is possible to extract meaningful spatio-temporal patterns that dominate dynamic activity. The focus of this book is on the emerging method of dynamic mode decomposition (DMD). DMD is a matrix decomposition technique that is highly versatile and builds upon the power of the singular value decomposition (SVD). The low-rank structures extracted from DMD are associated with temporal features as well as correlated spatial activity, thus providing a powerful diagnostic for state estimation, model building, control and prediction.