A High Performance Framework for Seismic Facies Analysis

• Julio Cesar Faracco UNICAMP
• Otávio Napoli UNICAMP https://orcid.org/0000-0001-9606-4751
• Edson Borin UNICAMP http://orcid.org/0000-0003-1783-4231

DOI: https://doi.org/10.5753/eradsp.2022.222235

Abstract

Seismic facies analysis is an important geological study to obtain relevant structural information from seismic data. These data are usually obtained by mapping a region using various capture methods and can be relatively large if the analyzed area is on the order of kilometers. Furthermore, with the increasing use of machine learning or deep learning techniques in this type of analysis, handling large data can require a greater amount of computational resources. In the context of seismic facies analysis, there are few tools and libraries dedicated to broadly addressing this area of HPC. As a result, the need for tools that support the most varied processing infrastructures is increasingly necessary. Therefore, the objective of this work is to present a standardized framework that can be easily used for seismic facies analysis, offering the maximum possible of joint acceleration techniques. Finally, we will present some results obtained through the use of this developed tool and how it can benefit geologists or geophysicists.

Keywords: HPC Applications, Machine Learning, Data Science, Cloud, Grid, Cluster and P2P (Peer-to-Peer)

References

Alaudah, Y., Michalowicz, P., Alfarraj, M., and AlRegib, G. (2019). A machine-learning benchmark for facies classification. Interpretation, 7(3):SE175-SE187.

Forest, F., Lebbah, M., Azzag, H., and Lacaille, J. (2019). Deep architectures for joint clustering and visualization with self-organizing maps. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pages 105-116. Springer.

Napoli, O., Do Rosario, V., De Oliveira, J., Silva, P. E., and Borin, E. (2021). Accelerating multi-attribute unsupervised seismic facies analysis with rapids. volume 2021, pages 1-5. European Association of Geoscientists & Engineers.

Troccoli, E. B., Cerqueira, A. G., Lemos, J. B., and Holz, M. (2022). K-means clustering using principal component analysis to automate label organization in multi-attribute seismic facies analysis. Journal of Applied Geophysics, 198:104555.

Waldeland, A. U., Jensen, A. C., Gelius, L.-J., and Solberg, A. H. S. (2018). Convolutional neural networks for automated seismic interpretation. The Leading Edge, 37(7):529-537.

Wu, X., Liang, L., Shi, Y., and Fomel, S. (2019). Faultseg3d: Using synthetic data sets to train an end-to-end convolutional neural network for 3d seismic fault segmentation. Geophysics, 84(3):IM35-IM45.

Zhao, T. (2018). Seismic facies classification using different deep convolutional neural networks. In SEG Technical Program Expanded Abstracts 2018, pages 2046-2050. Society of Exploration Geophysicists.