{"title":"深度学习用于理想化大气动力学中的库普曼算子估计","authors":"David Millard, Arielle Carr, Stéphane Gaudreault","doi":"arxiv-2409.06522","DOIUrl":null,"url":null,"abstract":"Deep learning is revolutionizing weather forecasting, with new data-driven\nmodels achieving accuracy on par with operational physical models for\nmedium-term predictions. However, these models often lack interpretability,\nmaking their underlying dynamics difficult to understand and explain. This\npaper proposes methodologies to estimate the Koopman operator, providing a\nlinear representation of complex nonlinear dynamics to enhance the transparency\nof data-driven models. Despite its potential, applying the Koopman operator to\nlarge-scale problems, such as atmospheric modeling, remains challenging. This\nstudy aims to identify the limitations of existing methods, refine these models\nto overcome various bottlenecks, and introduce novel convolutional neural\nnetwork architectures that capture simplified dynamics.","PeriodicalId":501035,"journal":{"name":"arXiv - MATH - Dynamical Systems","volume":"12 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep Learning for Koopman Operator Estimation in Idealized Atmospheric Dynamics\",\"authors\":\"David Millard, Arielle Carr, Stéphane Gaudreault\",\"doi\":\"arxiv-2409.06522\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Deep learning is revolutionizing weather forecasting, with new data-driven\\nmodels achieving accuracy on par with operational physical models for\\nmedium-term predictions. However, these models often lack interpretability,\\nmaking their underlying dynamics difficult to understand and explain. This\\npaper proposes methodologies to estimate the Koopman operator, providing a\\nlinear representation of complex nonlinear dynamics to enhance the transparency\\nof data-driven models. Despite its potential, applying the Koopman operator to\\nlarge-scale problems, such as atmospheric modeling, remains challenging. This\\nstudy aims to identify the limitations of existing methods, refine these models\\nto overcome various bottlenecks, and introduce novel convolutional neural\\nnetwork architectures that capture simplified dynamics.\",\"PeriodicalId\":501035,\"journal\":{\"name\":\"arXiv - MATH - Dynamical Systems\",\"volume\":\"12 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - MATH - Dynamical Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.06522\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - MATH - Dynamical Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.06522","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Deep Learning for Koopman Operator Estimation in Idealized Atmospheric Dynamics
Deep learning is revolutionizing weather forecasting, with new data-driven
models achieving accuracy on par with operational physical models for
medium-term predictions. However, these models often lack interpretability,
making their underlying dynamics difficult to understand and explain. This
paper proposes methodologies to estimate the Koopman operator, providing a
linear representation of complex nonlinear dynamics to enhance the transparency
of data-driven models. Despite its potential, applying the Koopman operator to
large-scale problems, such as atmospheric modeling, remains challenging. This
study aims to identify the limitations of existing methods, refine these models
to overcome various bottlenecks, and introduce novel convolutional neural
network architectures that capture simplified dynamics.