Seismic horizon detection with neural networks

TL;DR

This paper explores the use of neural networks for seismic horizon detection, emphasizing real-world data and model generalization across different seismic datasets, addressing limitations of synthetic training data.

Contribution

It presents an open-source study applying binary segmentation to seismic horizon detection on multiple real datasets, focusing on model generalization across different seismic cubes.

Findings

Effective horizon detection on real seismic data

Improved model generalization across datasets

Open-source implementation for reproducibility

Abstract

Over the last few years, Convolutional Neural Networks (CNNs) were successfully adopted in numerous domains to solve various image-related tasks, ranging from simple classification to fine borders annotation. Tracking seismic horizons is no different, and there are a lot of papers proposing the usage of such models to avoid time-consuming hand-picking. Unfortunately, most of them are (i) either trained on synthetic data, which can't fully represent the complexity of subterranean structures, (ii) trained and tested on the same cube, or (iii) lack reproducibility and precise descriptions of the model-building process. With all that in mind, the main contribution of this paper is an open-sourced research of applying binary segmentation approach to the task of horizon detection on multiple real seismic cubes with a focus on inter-cube generalization of the predictive model.