Identifying Salt Bodies using an Ensemble of Convolutional Neural Network

17 Views · 9 Downloads · ★★★★★ 5.0

NOT PEER REVIEWED

Authors

Areola Joshua¹

Poster summary: In deep-water hydrocarbon exploration, locating salt-related structures is vital for finding hydrocarbon zones and drilling spots. Salt structures can trap and channel hydrocarbons and influence sediment deposition. Traditional salt mapping methods are time-consuming. This study used a semi-supervised approach and an ensemble of Convolutional Neural Networks to improve salt body segmentation. It employed 17,600 seismic image patches for training, standardized to 256x256 pixels. The ensemble's output came from averaging two U-Net models

Keywords: Hydrocarbon Exploration, Salt Structure, Sediment Deposition, Supervised Approach, Segmentation, Convolutional Neural Network

References

Kim W., Kanezaki A., Tanaka M. Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering. In: Ieee Transactions on Image Processing. Available here: https://arxiv.org/pdf/2007.09990.pdf (2020).
Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical I mage computing and computer-assisted intervention. pp. 234{241. Springer (2015).
Arthur E. Barnes, Kenneth J. Laughlin. “Investigation of methods for unsupervised classification of seismic data”. In SEG Technical Program Expanded Abstracts (January, 2002).

Additional information

Data availability statement: The datasets generated during and / or analyzed during the current study are available from the corresponding author on reasonable request.

Creative Commons license: Copyright © 2024 Joshua. This is an open access work distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.