{"article_number":"141","year":"2024","scopus_import":"1","title":"Data-driven modeling of interrelated dynamical systems","date_updated":"2024-10-09T10:12:11Z","_id":"18204","article_processing_charge":"Yes","abstract":[{"text":"Non-linear dynamical systems describe numerous real-world phenomena, ranging from the weather, to financial markets and disease progression. Individual systems may share substantial common information, for example patients’ anatomy. Lately, deep-learning has emerged as a leading method for data-driven modeling of non-linear dynamical systems. Yet, despite recent breakthroughs, prior works largely ignored the existence of shared information between different systems. However, such cases are quite common, for example, in medicine: we may wish to have a patient-specific model for some disease, but the data collected from a single patient is usually too small to train a deep-learning model. Hence, we must properly utilize data gathered from other patients. Here, we explicitly consider such cases by jointly modeling multiple systems. We show that the current single-system models consistently fail when trying to learn simultaneously from multiple systems. We suggest a framework for jointly approximating the Koopman operators of multiple systems, while intrinsically exploiting common information. We demonstrate how we can adapt to a new system using order-of-magnitude less new data and show the superiority of our model over competing methods, in terms of both forecasting ability and statistical fidelity, across chaotic, cardiac, and climate systems.","lang":"eng"}],"language":[{"iso":"eng"}],"author":[{"last_name":"Elul","first_name":"Yonatan","full_name":"Elul, Yonatan"},{"first_name":"Eyal","last_name":"Rozenberg","full_name":"Rozenberg, Eyal"},{"full_name":"Boyarski, Amit","first_name":"Amit","last_name":"Boyarski"},{"full_name":"Yaniv, Yael","last_name":"Yaniv","first_name":"Yael"},{"full_name":"Schuster, Assaf","first_name":"Assaf","last_name":"Schuster"},{"id":"58f3726e-7cba-11ef-ad8b-e6e8cb3904e6","full_name":"Bronstein, Alexander","orcid":"0000-0001-9699-8730","last_name":"Bronstein","first_name":"Alexander"}],"article_type":"original","month":"05","citation":{"ista":"Elul Y, Rozenberg E, Boyarski A, Yaniv Y, Schuster A, Bronstein AM. 2024. Data-driven modeling of interrelated dynamical systems. Communications Physics. 7, 141.","ieee":"Y. Elul, E. Rozenberg, A. Boyarski, Y. Yaniv, A. Schuster, and A. M. Bronstein, “Data-driven modeling of interrelated dynamical systems,” <i>Communications Physics</i>, vol. 7. Springer Nature, 2024.","apa":"Elul, Y., Rozenberg, E., Boyarski, A., Yaniv, Y., Schuster, A., &#38; Bronstein, A. M. (2024). Data-driven modeling of interrelated dynamical systems. <i>Communications Physics</i>. Springer Nature. <a href=\"https://doi.org/10.1038/s42005-024-01626-5\">https://doi.org/10.1038/s42005-024-01626-5</a>","mla":"Elul, Yonatan, et al. “Data-Driven Modeling of Interrelated Dynamical Systems.” <i>Communications Physics</i>, vol. 7, 141, Springer Nature, 2024, doi:<a href=\"https://doi.org/10.1038/s42005-024-01626-5\">10.1038/s42005-024-01626-5</a>.","ama":"Elul Y, Rozenberg E, Boyarski A, Yaniv Y, Schuster A, Bronstein AM. Data-driven modeling of interrelated dynamical systems. <i>Communications Physics</i>. 2024;7. doi:<a href=\"https://doi.org/10.1038/s42005-024-01626-5\">10.1038/s42005-024-01626-5</a>","short":"Y. Elul, E. Rozenberg, A. Boyarski, Y. Yaniv, A. Schuster, A.M. Bronstein, Communications Physics 7 (2024).","chicago":"Elul, Yonatan, Eyal Rozenberg, Amit Boyarski, Yael Yaniv, Assaf Schuster, and Alex M. Bronstein. “Data-Driven Modeling of Interrelated Dynamical Systems.” <i>Communications Physics</i>. Springer Nature, 2024. <a href=\"https://doi.org/10.1038/s42005-024-01626-5\">https://doi.org/10.1038/s42005-024-01626-5</a>."},"date_published":"2024-05-01T00:00:00Z","status":"public","publication_status":"published","volume":7,"oa":1,"quality_controlled":"1","publication_identifier":{"issn":["2399-3650"]},"intvolume":"         7","date_created":"2024-10-08T12:45:35Z","extern":"1","type":"journal_article","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publisher":"Springer Nature","day":"01","publication":"Communications Physics","main_file_link":[{"url":"https://doi.org/10.1038/s42005-024-01626-5","open_access":"1"}],"doi":"10.1038/s42005-024-01626-5","oa_version":"Published Version"}