Operator inference with roll outs for learning reduced models from scarce and low-quality data

被引:9
|
作者
Uy, Wayne Isaac Tan [1 ]
Hartmann, Dirk [2 ]
Peherstorfer, Benjamin [1 ]
机构
[1] NYU, Courant Inst Math Sci, 251 Mercer St, New York, NY 10012 USA
[2] Siemens Ind Software GmbH, Munich, Germany
基金
美国国家科学基金会;
关键词
Data-driven modeling; Scientific machine learning; Model reduction; Scarce and noisy data; EIGENSYSTEM REALIZATION-ALGORITHM; ORDER REDUCTION; DYNAMICS; TIME; APPROXIMATION; INTERPOLATION; IDENTIFICATION; DECOMPOSITION; FRAMEWORK; SYSTEMS;
D O I
10.1016/j.camwa.2023.06.012
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
Data-driven modeling has become a key building block in computational science and engineering. However, data that are available in science and engineering are typically scarce, often polluted with noise and affected by measurement errors and other perturbations, which makes learning the dynamics of systems challenging. In this work, we propose to combine data-driven modeling via operator inference with the dynamic training via roll outs of neural ordinary differential equations. Operator inference with roll outs inherits interpretability, scalability, and structure preservation of traditional operator inference while leveraging the dynamic training via roll outs over multiple time steps to increase stability and robustness for learning from low-quality and noisy data. Numerical experiments with data describing shallow water waves and surface quasi-geostrophic dynamics demonstrate that operator inference with roll outs provides predictive models from training trajectories even if data are sampled sparsely in time and polluted with noise of up to 10%.
引用
收藏
页码:224 / 239
页数:16
相关论文
共 50 条
  • [31] Optimization and sensitivity analysis of existing deep learning models for pavement surface monitoring using low-quality images
    Roberts, Ronald
    Menant, Fabien
    Di Mino, Gaetano
    Baltazart, Vincent
    AUTOMATION IN CONSTRUCTION, 2022, 140
  • [32] Using Energy Landscapes to Determine Crystal Structures from Low-Quality Experimental Data.
    van de Streek, Jacco
    Neumann, Marcus A.
    ACTA CRYSTALLOGRAPHICA A-FOUNDATION AND ADVANCES, 2009, 65 : S106 - S106
  • [33] Learning From Data Semiparametric Models Versus Faith-based Inference
    Van der Laan, Mark
    Hubbard, Alan E.
    Jewell, Nicholas
    EPIDEMIOLOGY, 2010, 21 (04) : 479 - 481
  • [34] Data-driven reduced-order models via regularised Operator Inference for a single-injector combustion process
    McQuarrie, Shane A.
    Huang, Cheng
    Willcox, Karen E.
    JOURNAL OF THE ROYAL SOCIETY OF NEW ZEALAND, 2021, 51 (02) : 194 - 211
  • [35] A Learning-based Video Compression on Low-Quality Data by Unscented Kalman Filters with Gaussian Process Regression
    Xiong, Hongkai
    Yuan, Zhe
    Zheng, Yuan F.
    2011 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2011, : 1227 - 1230
  • [36] Comparison of deep learning systems and cornea specialists in detecting corneal diseases from low-quality images
    Li, Zhongwen
    Jiang, Jiewei
    Qiang, Wei
    Guo, Liufei
    Liu, Xiaotian
    Weng, Hongfei
    Wu, Shanjun
    Zheng, Qinxiang
    Chen, Wei
    ISCIENCE, 2021, 24 (11)
  • [37] Applying a deep learning pipeline to classify land cover from low-quality historical RGB imagery
    Eyster, Harold N.
    Beckage, Brian
    PEERJ COMPUTER SCIENCE, 2024, 10
  • [38] Maximizing Molecular Data From Low-Quality Fluid-Preserved Specimens in Natural History Collections
    Bernstein, Justin M.
    Ruane, Sara
    FRONTIERS IN ECOLOGY AND EVOLUTION, 2022, 10
  • [39] Data reconstruction from machine learning models via inverse estimation and Bayesian inference
    Agus Hartoyo
    Dominika Ciupek
    Maciej Malawski
    Alessandro Crimi
    Scientific Reports, 15 (1)
  • [40] Multi-objective learning of white box models with low quality data
    Villar, Jose R.
    Berzosa, Alba
    de la Cal, Enrique
    Sedano, Javier
    Garcia-Tamargo, Marco
    NEUROCOMPUTING, 2012, 75 (01) : 219 - 225