DLKoopman: A deep learning software package for Koopman theory

Sourya Dey, Eric William Davis
Proceedings of The 5th Annual Learning for Dynamics and Control Conference, PMLR 211:1467-1479, 2023.

Abstract

We present DLKoopman – a software package for Koopman theory that uses deep learning to learn an encoding of a nonlinear dynamical system into a linear space, while simultaneously learning the linear dynamics. While several previous efforts have either restricted the ability to learn encodings, or been bespoke efforts designed for specific systems, DLKoopman is a generalized tool that can be applied to data-driven learning and analysis of any dynamical system. It can either be trained on data from individual states (snapshots) of a system and used to predict its unknown states, or trained on data from trajectories of a system and used to predict unknown trajectories for new initial states. DLKoopman is available on the Python Package Index (PyPI) as ’dlkoopman’, and includes extensive documentation and tutorials. Additional contributions of the package include a novel metric called Average Normalized Absolute Error for evaluating performance, and a ready-to-use hyperparameter search module for improving performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v211-dey23a, title = {DLKoopman: A deep learning software package for Koopman theory}, author = {Dey, Sourya and Davis, Eric William}, booktitle = {Proceedings of The 5th Annual Learning for Dynamics and Control Conference}, pages = {1467--1479}, year = {2023}, editor = {Matni, Nikolai and Morari, Manfred and Pappas, George J.}, volume = {211}, series = {Proceedings of Machine Learning Research}, month = {15--16 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v211/dey23a/dey23a.pdf}, url = {https://proceedings.mlr.press/v211/dey23a.html}, abstract = {We present DLKoopman – a software package for Koopman theory that uses deep learning to learn an encoding of a nonlinear dynamical system into a linear space, while simultaneously learning the linear dynamics. While several previous efforts have either restricted the ability to learn encodings, or been bespoke efforts designed for specific systems, DLKoopman is a generalized tool that can be applied to data-driven learning and analysis of any dynamical system. It can either be trained on data from individual states (snapshots) of a system and used to predict its unknown states, or trained on data from trajectories of a system and used to predict unknown trajectories for new initial states. DLKoopman is available on the Python Package Index (PyPI) as ’dlkoopman’, and includes extensive documentation and tutorials. Additional contributions of the package include a novel metric called Average Normalized Absolute Error for evaluating performance, and a ready-to-use hyperparameter search module for improving performance.} }
Endnote
%0 Conference Paper %T DLKoopman: A deep learning software package for Koopman theory %A Sourya Dey %A Eric William Davis %B Proceedings of The 5th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2023 %E Nikolai Matni %E Manfred Morari %E George J. Pappas %F pmlr-v211-dey23a %I PMLR %P 1467--1479 %U https://proceedings.mlr.press/v211/dey23a.html %V 211 %X We present DLKoopman – a software package for Koopman theory that uses deep learning to learn an encoding of a nonlinear dynamical system into a linear space, while simultaneously learning the linear dynamics. While several previous efforts have either restricted the ability to learn encodings, or been bespoke efforts designed for specific systems, DLKoopman is a generalized tool that can be applied to data-driven learning and analysis of any dynamical system. It can either be trained on data from individual states (snapshots) of a system and used to predict its unknown states, or trained on data from trajectories of a system and used to predict unknown trajectories for new initial states. DLKoopman is available on the Python Package Index (PyPI) as ’dlkoopman’, and includes extensive documentation and tutorials. Additional contributions of the package include a novel metric called Average Normalized Absolute Error for evaluating performance, and a ready-to-use hyperparameter search module for improving performance.
APA
Dey, S. & Davis, E.W.. (2023). DLKoopman: A deep learning software package for Koopman theory. Proceedings of The 5th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 211:1467-1479 Available from https://proceedings.mlr.press/v211/dey23a.html.

Related Material