A novel data generation scheme for surrogate modelling with deep operator networks

arXiv:2402.16903v1 Announce Type: new
Abstract: Operator-based neural network architectures such as DeepONets have emerged as a promising tool for the surrogate modeling of physical systems. In general, towards operator surrogate modeling, the training data is generated by solving the PDEs using techniques such as Finite Element Method (FEM). The computationally intensive nature of data generation is one of the biggest bottleneck in deploying these surrogate models for practical applications. In this study, we propose a novel methodology to alleviate the …

abstract architectures arxiv cs.lg cs.na data element general generated math.na modeling modelling network networks neural network novel systems tool training training data type