Derivative-enhanced Deep Operator Network

arXiv:2402.19242v1 Announce Type: new
Abstract: Deep operator networks (DeepONets), a class of neural operators that learn mappings between function spaces, have recently been developed as surrogate models for parametric partial differential equations (PDEs). In this work we propose a derivative-enhanced deep operator network (DE-DeepONet), which leverages the derivative information to enhance the prediction accuracy, and provide a more accurate approximation of the derivatives, especially when the training data are limited. DE-DeepONet incorporates dimension reduction of input into DeepONet and includes …

abstract accuracy arxiv class cs.ce cs.lg cs.na deeponet differential function information learn math.na network networks operators parametric prediction spaces type work