Inversion-DeepONet: A Novel DeepONet-Based Network with Encoder-Decoder for Full Waveform Inversion
This work addresses the challenge of insufficient data representation in geophysical imaging, offering incremental improvements for more realistic subsurface modeling.
The paper tackled the problem of limited dataset diversity in deep learning-based full waveform inversion (FWI) for geophysics by developing enhanced datasets with varying source locations and frequencies and proposing a novel DeepONet architecture called Inversion-DeepONet, which achieved superior accuracy and generalization compared to existing methods.
Full waveform inversion (FWI) plays a crucial role in the field of geophysics. There has been lots of research about applying deep learning (DL) methods to FWI. The success of DL-FWI relies significantly on the quantity and diversity of the datasets. Nevertheless, existing FWI datasets, like OpenFWI, where sources have fixed locations or identical frequencies, provide limited information and do not represent the complex real-world scene. For instance, low frequencies help in resolving larger-scale structures. High frequencies allow for a more detailed subsurface features. %A single source frequency is insufficient to describe subsurface structural properties. We consider that simultaneously using sources with different frequencies, instead of performing inversion using low frequencies data and then gradually introducing higher frequencies data, has rationale and potential advantages. Hence, we develop three enhanced datasets based on OpenFWI where each source have varying locations, frequencies or both. Moreover, we propose a novel deep operator network (DeepONet) architecture Inversion-DeepONet for FWI. We utilize convolutional neural network (CNN) to extract the features from seismic data in branch net. Source parameters, such as locations and frequencies, are fed to trunk net. Then another CNN is employed as the decoder of DeepONet to reconstruct the velocity models more effectively. Through experiments, we confirm the superior performance on accuracy and generalization ability of our network, compared with existing data-driven FWI methods.