Multifidelity Deep Operator Networks

04/19/2022
by   Amanda A. Howard, et al.
15

Operator learning for complex nonlinear operators is increasingly common in modeling physical systems. However, training machine learning methods to learn such operators requires a large amount of expensive, high-fidelity data. In this work, we present a composite Deep Operator Network (DeepONet) for learning using two datasets with different levels of fidelity, to accurately learn complex operators when sufficient high-fidelity data is not available. Additionally, we demonstrate that the presence of low-fidelity data can improve the predictions of physics-informed learning with DeepONets.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset