InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion

TL;DR

InversionNet3D is a scalable deep learning model that efficiently reconstructs high-resolution 3D subsurface velocity maps from seismic data, reducing computational costs and memory usage.

Contribution

It introduces group convolution and invertible layers to enhance scalability and efficiency in 3D seismic full-waveform inversion deep learning models.

Findings

Achieves state-of-the-art 3D velocity map reconstruction.

Reduces computational cost compared to baseline methods.

Uses less memory while maintaining high accuracy.

Abstract

Seismic full-waveform inversion (FWI) techniques aim to find a high-resolution subsurface geophysical model provided with waveform data. Some recent effort in data-driven FWI has shown some encouraging results in obtaining 2D velocity maps. However, due to high computational complexity and large memory consumption, the reconstruction of 3D high-resolution velocity maps via deep networks is still a great challenge. In this paper, we present InversionNet3D, an efficient and scalable encoder-decoder network for 3D FWI. The proposed method employs group convolution in the encoder to establish an effective hierarchy for learning information from multiple sources while cutting down unnecessary parameters and operations at the same time. The introduction of invertible layers further reduces the memory consumption of intermediate features during training and thus enables the development of deeper networks with more layers and higher capacity as required by different application scenarios. Experiments on the 3D Kimberlina dataset demonstrate that InversionNet3D achieves state-of-the-art reconstruction performance with lower computational cost and lower memory footprint compared to the baseline.