Abstract
Accurate clustering of oil wells is important for lithological studies and hydrocarbon production processes. Traditional methods for solving this problem require large amount of expert work, including careful analysis of high-dimensional datasets. Modern approaches to automatizing clustering are mostly based on deep neural networks (DNN) with complex architecture, which require significant training time and lack interpretability. This paper analyses methods based on simple similarity heuristics, which stem from reasonable assumptions on data generating process and can be interpreted in terms of statistics and geometry. For dataset labeled by experts, clustering is performed by means of computed heuristics, and the quality of algorithm is measured by Adjusted Rand Index (ARI). Results thus obtained turn out to be comparable to those of modern DNN models (0.41 vs 0.37), but the computation time is reduced significantly. For some types of heuristics physical interpretation is suggested and approaches to obtaining geological insights are studied.
REFERENCES
M. Ali et al., ‘‘Machine learning—A novel approach of well logs similarity based on synchronization measures to predict shear sonic logs,’’ J. Pet. Sci. Eng. 203, 108602 (2021). https://doi.org/10.1016/j.petrol.2021.108602
J. Cresson and S. Sonner, ‘‘A note on a derivation method for SDE models: Applications in biology and viability criteria,’’ Stoch. Anal. Appl. 36, 1386571 (2018). https://doi.org/10.1080/07362994.2017.1386571
E. Gurina et al., ‘‘Application of machine learning to accidents detection at directional drilling,’’ J. Pet. Sci. Eng. 184, 106519 (2020). https://doi.org/10.1016/j.petrol.2019.106519
S. Hirano, ‘‘Source time functions of earthquakes based on a stochastic differential equation,’’ Sci. Rep. 12, 3936 (2022). https://doi.org/10.1038/s41598-022-07873-2
S. Hirano, ‘‘Source time functions of earthquakes based on a stochastic differential equation,’’ Earth Space Sci. Open Arch. (2021). https://doi.org/10.1002/essoar.10507482.1
T. Kleinow, ‘‘Testing continuous time models in financial markets,’’ Dissertation (Berlin, 2002).
J. Kutz, S. Brunton, B. Brunton, and J. Proctor, Dynamic Mode Decomposition (Soc. Ind. Appl. Math., Philadelphia, 2016).
B. **e et al., ‘‘High-efficient low-cost characterization of composite material properties using domain-knowledge-guided self-supervised learning,’’ Comput. Mater. Sci. 216, 111834 (2023). https://doi.org/10.1016/j.commatsci.2022.111834
J. Steinier, Y. Termonia, and J. Deltour, ‘‘Smoothing and differentiation of data by simplified least square procedure,’’ Anal. Chem. 44, 1906 (1972).
N. Touzi, Optimal Stochastic Control, Stochastic Target Problems, and Backward SDE (Springer, New York, 2012).
A. Sekine and Tanaka ‘‘Notes on backward stochastic differential equations for computing XVA,’’ in Proceedings of the Forum Math-for-Industry (2018). https://doi.org/10.1016/j.commatsci.2022.111834
N. Vinh et al., ‘‘Information theoretic measures for clusterings comparison: Variants, properties, normalization and correction for chance,’’ J. Mach. Learn. Res. 11 (2010).
A. Verma et al., ‘‘Assessment of similarity between well logs using synchronization measures,’’ IEEE Geosci. Remote Sens. Lett. 11, 2317498 (2014). https://doi.org/10.1109/LGRS.2014.2317498
E. Romanenkova et al., ‘‘Similarity learning for wells based on logging data,’’ J. Pet. Sci. Eng. 215, 110690 (2022). https://doi.org/10.1016/j.petrol.2022.110690
R. Akkurt et al., ‘‘Accelerating and enhancing petrophysical analysis with machine learning: A case study of an automated system for well log outlier detection and reconstruction,’’ in Proceedings of the SPWLA Annual Logging Symposium (2018).
N. Stuov et al., ‘‘Out of distribution detection of well logs for ai-assisted formation evaluation,’’ in Proceedings of the IPTC International Petroleum Technology Conference (2022). https://doi.org/10.2523/IPTC-22097-MS
IBM Research, Taranaki Basin Curated Well Logs. https://developer.ibm.com/technologies/artificial-intelligence/data/taranaki-basin-curated-well-logs/. Accessed 2020.
A. Rogulina et al., ‘‘Similarity learning for well logs prediction using machine learning algorithms,’’ in Proceedings of the IPTC International Petroleum Technology Conference (2022). https://doi.org/10.2523/IPTC-22067-MS
Author information
Authors and Affiliations
Corresponding authors
Additional information
(Submitted by E. K. Lipachev)
Rights and permissions
About this article
Cite this article
Khliustov, D.K., Kovalev, D.Y. & Safonov, S.S. Similarity Heuristics for Clustering Wells Based on Logging-Data. Lobachevskii J Math 44, 157–169 (2023). https://doi.org/10.1134/S1995080223010195
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1995080223010195