Operator learning provides methods to approximate mappings between infinite-dimensional function spaces. Deep operator networks (DeepONets) are a notable architecture in this field. Recently, an extension of DeepONet based on model reduction and neural networks, proper orthogonal decomposition (POD)-DeepONet, has been able to outperform other architectures in terms of accuracy for several benchmark tests. We extend this idea towards nonlinear model order reduction by proposing an efficient framework that combines neural networks with kernel principal component analysis (KPCA) for operator learning. Our results demonstrate the superior performance of KPCA-DeepONet over POD-DeepONet.
TGPT-PINN: Nonlinear model reduction with transformed GPT-PINNs
University of Massachusetts Dartmouth(马萨诸塞大学达特茅斯分校);Shanghai Jiao Tong University(上海交通大学);University of Utah(犹他大学);Scientific Computing and Imaging Institute(科学计算与成像研究所)
Neural empirical interpolation method for nonlinear model reduction
Department of Mathematics, University of California Berkeley(加州大学伯克利分校数学系);mathLab, Mathematics Area, SISSA(SISSA数学区);MCSS, École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院MCSS)
Nonlinear Model Order Reduction of Dynamical Systems in Process Engineering: Review and Comparison
Process Systems Engineering (AVT.SVT), RWTH Aachen University(过程系统工程(AVT.SVT),亚琛工业大学);JARA-CSD;Energy Systems Engineering (ICE-1), Forschungszentrum Jülich(能源系统工程(ICE-1),卢比希研究中心)