SiameseLSRTM: Enhancing least-squares reverse time migration with a Siamese network

TL;DR

SiameseLSRTM integrates a Siamese neural network with least-squares reverse time migration to improve seismic imaging accuracy and resolution, especially when simulated data simplifications limit traditional methods.

Contribution

It introduces a self-supervised Siamese network framework into LSRTM, enhancing data matching and imaging quality without extensive labeled data or training.

Findings

Higher-resolution seismic images achieved

Improved imaging accuracy over traditional LSRTM

Effective on synthetic and field datasets

Abstract

Least-squares reverse time migration (LSRTM) is an inversion-based imaging method rooted in optimization theory, which iteratively updates the reflectivity model to minimize the difference between observed and simulated data. However, in real data applications, the Born-based simulated data, based on simplified physics, like the acoustic assumption, often under represent the complexity within observed data. Thus, we develop SiameseLSRTM, a novel approach that employs a Siamese network consisting of two identical convolutional neural networks (CNNs) with shared weights to measure the difference between simulated and observed data. Specifically, the shared-weight CNNs in the Siamese network enable the extraction of comparable features from both observed and simulated data, facilitating more effective data matching and ultimately improving imaging accuracy. SiameseLSRTM is a self-supervised framework in which the network parameters are updated during the iterative LSRTM process, without requiring extensive labeled data and prolonged training. We evaluate SiameseLSRTM using two synthetic datasets and one field dataset from a land seismic survey, showing that it produces higher-resolution and more accurate imaging results compared to traditional LSRTM.