Detection and Delimitation of Natural Gas in Seismic Images using MLP-Mixer and U-Net

Carolina Cipriano, Domingos Junior, Petterson Diniz, Luiz Marin, Anselmo Paiva, João Diniz, João Diniz, Aristófanes Silva

2022

Abstract

The seismic data acquired through the seismic reflection method is important for hydrocarbon prospecting. As an example of hydrocarbon, we have natural gas, one of the leading and most used energy sources in the current scenario. The techniques for analyzing these data are challenging for specialists. Due to the noisy nature of data acquisition, it is subject to errors and divergences between the specialists. The growth of deep learning has brought great highlights to tasks of segmentation, classification, and detection of objects in images from different areas. Consequently, the use of machine learning in seismic data has also grown. Therefore, this work proposes an automatic detection and delimitation of the natural gas region in seismic images (2D) using MLP-Mixer and U-Net. The proposed method obtained competitive results with an accuracy of 99.6% (inline) and 99.55% (crossline); specificity of 99.79% (inline) and 99.73% (crossline).

Paper Citation

in Harvard Style

Cipriano C., Junior D., Diniz P., Marin L., Paiva A., Diniz J. and Silva A. (2022). Detection and Delimitation of Natural Gas in Seismic Images using MLP-Mixer and U-Net. In Proceedings of the 24th International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 978-989-758-569-2, pages 578-585. DOI: 10.5220/0011075000003179

in Bibtex Style

@conference{iceis22,
author={Carolina Cipriano and Domingos Junior and Petterson Diniz and Luiz Marin and Anselmo Paiva and João Diniz and Aristófanes Silva},
title={Detection and Delimitation of Natural Gas in Seismic Images using MLP-Mixer and U-Net},
booktitle={Proceedings of the 24th International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2022},
pages={578-585},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011075000003179},
isbn={978-989-758-569-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 24th International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - Detection and Delimitation of Natural Gas in Seismic Images using MLP-Mixer and U-Net
SN - 978-989-758-569-2
AU - Cipriano C.
AU - Junior D.
AU - Diniz P.
AU - Marin L.
AU - Paiva A.
AU - Diniz J.
AU - Silva A.
PY - 2022
SP - 578
EP - 585
DO - 10.5220/0011075000003179