Automated Facies Identification Using Unsupervised Clustering
- Youngjun Hong (Enerzai) | Shinjo Wang (Enerzai) | Jeehoon Bae (Colorado school of mines) | Jaeyoon Yoo (Seoul National University) | Sungroh Yoon (Seoul National University)
- Document ID
- Offshore Technology Conference
- Offshore Technology Conference, 4-7 May, Houston, Texas, USA
- Publication Date
- Document Type
- Conference Paper
- 2020. Offshore Technology Conference
- deep neural networks, clustering, ensemble, Automated facies identification
- 3 in the last 30 days
- 104 since 2007
- Show more detail
- View rights & permissions
The interpretation of well logs is crucial for understanding subsurface geological formations and reservoir characterization. Categorizing subsurface into several geological facies types assists in identifying potential locations of hydrocarbon resources. Geologists interpret each well log feature such as gamma ray, sonic velocity, neutron porosity and resistivity, based on logging characteristics and their petrophysical domain knowledge. By integrating with core analysis result, well logs interpretation result becomes accurate, and geologists finally determine rock types of subsurface for the target well.
Recently, various studies propose to leverage the power of machine learning algorithms for facies classification to reduce laborious interpretation work. Most works utilize supervised learning algorithms that require input/label paired data for training. In case of facies classification, however, the accurate core analysis for determining facies is an expensive process, and the other methods require hard work and often result in noisy data.
In this paper, we develop an unsupervised facies identification model based on deep neural networks. Our model is purely unsupervised, which do not require facies label for input well logs. Because well logs response from the same rock type would have high similarity, we apply an unsupervised clustering algorithm, where data points with similar traits are assigned to the same group, while dissimilar data points are assigned to the different groups.
We demonstrate that our unsupervised facies identification model outperforms other unsupervised clustering algorithms for facies identification. Particularly, our clustered result shows highly similar distribution to the true facies distribution, which suggests future development of automated facies identification.
|File Size||711 KB||Number of Pages||9|
Vasileios-Marios Gkortsas,Lin Liang. 2019. Automatic electrofacies classification from well logs. SEG Technical Program Expanded Abstracts (2019): 2629–2633. https://doi.org/10.1190/segam2019-3215864.1.
Brendon Hall. 2016. Facies classification using machine learning. The Leading Edge 35, no. 10 (2016): 906–906. https://doi.org/10.1190/tle35100906.1
Weihua Hu,et al. 2017. Learning Discrete Representation via Information Maximizing Self-Augmented Training. Presented at the International Conference on Machine Learning, 7-9 August 2017, Sydney, Australia. https://proceedings.mlr.press/v70.hu17b.html.
Elie Aljalbout,et al. 2018. Clustering with deep learning: Taxonomy and new methods. https://arxiv.org/abs/1801.07648.
Takeru Miyato,et al. 2018. Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE transactions on pattern analysis and machine intelligence 41.8 (2018): 1979–1993. https://doi.org/10.1109/TPAMI.2018.2858821.
Licheng Zhang,Cheng Zhan. 2017. Machine learning in rock facies classification: an application of XGBoost. Presented at the International Geophysical Conference, April 2017, Qingdao, China. https://doi.org/10.1190/IGC2017-351.
Chayawan Jaikla,et al. 2019. FaciesNet: Machine Learning Applications for Facies Classification in Well Logs. Presented at the Second Workshop on Machine Learning and the Physical Sciences at the 33rd Conference on Neural Information Processing Systems (NeurIPS), 10-12 December 2019, Vancouver, Canada. https://ml4physicalsciences.github.io/files/NeurIPS_ML4PS_2019_140.pdf.