Towards an Adaptive Dynamic Mode Decomposition
This work addresses the problem of improving dynamic mode decomposition for researchers and practitioners working with time-series data, representing an incremental improvement to an existing method.
This paper introduces Adaptive Dynamic Mode Decomposition (ADMD), a new version of DMD that incorporates time delay coordinates, projection methods, and filters to model time-series data. The method was tested on various datasets, showing promising performance.
Dynamic Mode Decomposition (DMD) is a data based modeling tool that identifies a matrix to map a quantity at some time instant to the same quantity in future. We design a new version which we call Adaptive Dynamic Mode Decomposition (ADMD) that utilizes time delay coordinates, projection methods and filters as per the nature of the data to create a model for the available problem. Filters are very effective in reducing the rank of high-dimensional dataset. We have incorporated 'discrete Fourier transform' and 'augmented lagrangian multiplier' as filters in our method. The proposed ADMD is tested on several datasets of varying complexities and its performance appears to be promising.