Machine learning for seismic exploration: Where are we and how far are we from the holy grail?

Abstract

Machine Learning (ML) applications in seismic exploration are growing faster than applications in other industry fields, mainly due to the large amount of acquired data for the exploration industry. The ML algorithms are constantly being implemented to almost all the steps involved in seismic processing and interpretation workflow, mainly for automation, processing time reduction, efficiency and in some cases for improving the results. We carried out a literature-based analysis of existing ML-based seismic processing and interpretation published in SEG and EAGE literature repositories and derived a detailed overview of the main ML thrusts in different seismic applications. For each publication, we extracted various metadata about ML implementations and performances. The data indicate that current ML implementations in seismic exploration are focused on individual tasks rather than a disruptive change in processing and interpretation workflows. The metadata shows that the main targets of ML applications for seismic processing are denoising, velocity model building and first break picking, whereas for seismic interpretation, they are fault detection, lithofacies classification and geo-body identification. Through the metadata available in publications, we obtained indices related to computational power efficiency, data preparation simplicity, real data test rate of the ML model, diversity of ML methods, etc. and we used them to approximate the level of efficiency, effectivity and applicability of the current ML-based seismic processing and interpretation tasks. The indices of ML-based processing tasks show that current ML-based denoising and frequency extrapolation have higher efficiency, whereas ML-based QC is more effective and applicable compared to other processing tasks. Among the interpretation tasks, ML-based impedance inversion shows high efficiency, whereas high effectivity is depicted for fault detection. ML-based Lithofacies classification, stratigraphic sequence identification and petro/rock properties inversion exhibit high applicability among other interpretation tasks.