Deep Recurrent Architectures for Seismic Tomography

TL;DR

This paper develops deep recurrent neural network architectures, including LSTM and GRU, for seismic velocity model building, demonstrating improved accuracy in predicting salt bodies and advancing towards faster, fully machine learning-based seismic tomography.

Contribution

It introduces novel deep recurrent neural network architectures for seismic tomography, extending beyond previous convolutional approaches and improving salt body prediction accuracy.

Findings

GRU and LSTM architectures outperform non-recurrent models in salt body prediction

Recurrent architectures reduce seismic tomography turnaround time

Advances towards fully machine learning-based seismic velocity modeling

Abstract

This paper introduces novel deep recurrent neural network architectures for Velocity Model Building (VMB), which is beyond what Araya-Polo et al 2018 pioneered with the Machine Learning-based seismic tomography built with convolutional non-recurrent neural network. Our investigation includes the utilization of basic recurrent neural network (RNN) cells, as well as Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) cells. Performance evaluation reveals that salt bodies are consistently predicted more accurately by GRU and LSTM-based architectures, as compared to non-recurrent architectures. The results take us a step closer to the final goal of a reliable fully Machine Learning-based tomography from pre-stack data, which when achieved will reduce the VMB turnaround from weeks to days.