{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-convolutional-recurrent-autoencoders-for","title":"Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systems","arxiv_id":"1808.01346","date":"2018-08-03","proceeding":null,"authors":["Francisco J. Gonzalez","Maciej Balajewicz"],"abstract":"Model reduction of high-dimensional dynamical systems alleviates\ncomputational burdens faced in various tasks from design optimization to model\npredictive control. One popular model reduction approach is based on projecting\nthe governing equations onto a subspace spanned by basis functions obtained\nfrom the compression of a dataset of solution snapshots. However, this method\nis intrusive since the projection requires access to the system operators.\nFurther, some systems may require special treatment of nonlinearities to ensure\ncomputational efficiency or additional modeling to preserve stability. In this\nwork we propose a deep learning-based strategy for nonlinear model reduction\nthat is inspired by projection-based model reduction where the idea is to\nidentify some optimal low-dimensional representation and evolve it in time. Our\napproach constructs a modular model consisting of a deep convolutional\nautoencoder and a modified LSTM network. The deep convolutional autoencoder\nreturns a low-dimensional representation in terms of coordinates on some\nexpressive nonlinear data-supporting manifold. The dynamics on this manifold\nare then modeled by the modified LSTM network in a computationally efficient\nmanner. An offline unsupervised training strategy that exploits the model\nmodularity is also developed. We demonstrate our model on three illustrative\nexamples each highlighting the model's performance in prediction tasks for\nfluid systems with large parameter-variations and its stability in long-term\nprediction.","url_abs":"http://arxiv.org/abs/1808.01346v2","url_pdf":"http://arxiv.org/pdf/1808.01346v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-convolutional-recurrent-autoencoders-for","repo_url":"https://github.com/panchgonzalez/nmor","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-convolutional-recurrent-autoencoders-for","repo_url":"https://github.com/jeroaranda/thesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"model-predictive-control","task_name":"Model Predictive Control"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.01346","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}