Deep-tomography: iterative velocity model building with deep learning

TL;DR

Deep-Tomography introduces an iterative deep learning approach for seismic velocity model building, progressively refining models with each iteration to improve accuracy and handle complex unseen data like the Marmousi model.

Contribution

It presents a novel iterative deep learning framework inspired by traditional methods, enhancing the complexity and accuracy of velocity models in seismic imaging.

Findings

Successfully predicts complex velocity models like Marmousi

Iterative approach improves model accuracy over single-step predictions

Effective on unseen data, demonstrating robustness

Abstract

The accurate and fast estimation of velocity models is crucial in seismic imaging. Conventional methods, like Tomography and Full-Waveform Inversion (FWI), obtain appropriate velocity models; however, they require intense and specialized human supervision and consume much time and computational resources. In recent years, some works investigated deep learning(DL) algorithms to obtain the velocity model directly from shots or migrated angle panels, obtaining encouraging predictions of synthetic models. This paper proposes a new flow to increase the complexity of velocity models recovered with DL. Inspired by the conventional geophysical velocity model building methods, instead of predicting the entire model in one step, we predict the velocity model iteratively. We implement the iterative nature of the process when, for each iteration, we train the DL algorithm to determine the velocity model with a certain level of precision/resolution for the next iteration; we name this process as Deep-Tomography. Starting from an initial model that roughly approaches the true model, the Deep-Tomography is able to predict an appropriate final model, even in complete unseen data, like the Marmousi model.