275
Views
19
Downloads
2
Crossref
1
WoS
0
Scopus
N/A
CSCD
The manual picking of reservoir formation boundaries using limited available well-log data in multiple wells across gas and oil reservoirs tends to be subjective and unreliable. The reasons for this are typically caused by the combined effects of spatial boundary complexity and limited well-log data availability. Formation boundary characterization and classification can be improved when treated as a binary classification task based on two or three recorded well logs assisted by their calculated derivative and volatility attributes assessed by machine learning. Two example wellbores penetrating a complex reservoir boundary,one with gamma-ray,compressional-sonic,and bulk-density logs recorded,the other with just gamma-ray and bulk-density logs recorded,are used to illustrate a more rigorous proposed methodology. By combining attribute calculation,optimized feature selection,multi-k-fold cross validation,confusion matrices,feature-influence analysis,and machine learning models it is possible to improve the classification of the formation boundary. With just gamma-ray and bulk-density recorded well logs plus selected attributes. K-nearest neighbour,support vector classification,and extreme gradient boosting machine learning models are able to achieve high binary classification accuracy: greater than 0.97 for training/validation in one well; and greater than 0.94 for testing in another well. extreme gradient boosting feature-influence analysis reveals the attributes that are the most important in the formation boundary predictions but these are likely to vary from reservoir to reservoir. The results of the study suggest that well-log attribute analysis,combined with machine learning has the potential to provide a more systematic formation boundary definition than relying only on a few recorded well-log curves.
The manual picking of reservoir formation boundaries using limited available well-log data in multiple wells across gas and oil reservoirs tends to be subjective and unreliable. The reasons for this are typically caused by the combined effects of spatial boundary complexity and limited well-log data availability. Formation boundary characterization and classification can be improved when treated as a binary classification task based on two or three recorded well logs assisted by their calculated derivative and volatility attributes assessed by machine learning. Two example wellbores penetrating a complex reservoir boundary,one with gamma-ray,compressional-sonic,and bulk-density logs recorded,the other with just gamma-ray and bulk-density logs recorded,are used to illustrate a more rigorous proposed methodology. By combining attribute calculation,optimized feature selection,multi-k-fold cross validation,confusion matrices,feature-influence analysis,and machine learning models it is possible to improve the classification of the formation boundary. With just gamma-ray and bulk-density recorded well logs plus selected attributes. K-nearest neighbour,support vector classification,and extreme gradient boosting machine learning models are able to achieve high binary classification accuracy: greater than 0.97 for training/validation in one well; and greater than 0.94 for testing in another well. extreme gradient boosting feature-influence analysis reveals the attributes that are the most important in the formation boundary predictions but these are likely to vary from reservoir to reservoir. The results of the study suggest that well-log attribute analysis,combined with machine learning has the potential to provide a more systematic formation boundary definition than relying only on a few recorded well-log curves.
Abualigah, L., Diabat, A. Advances in Sine Cosine Algorithm: A comprehensive survey. Artificial Intelligence Review, 2021, 54(4): 2567-2608.
Atashnezhad, A., Wood, D. A., Fereidounpour, A., et al. Designing and optimizing deviated wellbore trajectories using novel particle swarm algorithms. Journal of Natural Gas Science and Engineering, 2014, 21: 1184-1204.
Chang, Y., Hsieh, C., Chang, K., et al. Training and testing low-degree polynomial data mappings via linear SVM. Journal of Machine Learning Research, 2010, 11(4): 1471-1490.
Cortes, C., Vapnik, V. Support-Vector Networks. Machine Learning, 1995, 20(3): 273-297.
Cox, D. R. The regression analysis of binary sequences. Journal of the Royal Statistical Society. Series B (Methodological). 1958, 20(2): 215-242.
Darling, T. Well Logging and Formation Evaluation. Huston, USA, Gulf Professional Publishing, 2005.
Liu, K., Ostadhassan, M. The impact of pore size distribution data presentation format on pore structure interpretation of shales. Advances in Geo-Energy Research, 2019, 3(2): 187-197.
Luthi, S. M. Geological Well Logs: Their Use in Reservoir Modeling. Berlin, Germany, Springer Science & Business Media, 2011.
Rafiei, Y., Motie, M. Improved reservoir characterization by employing hydraulic flow unit classification in one of Iranian carbonate reservoirs. Advances in Geo-Energy Research, 2019, 3(3): 277-286.
Rao, R. V. Jaya: A simple and new optimization algorithm for solving constrained and unconstrained optimization problems. International Journal of Industrial Engineering Computations, 2016, 7: 19-34.
Serra, O. Fundamentals of Well-Log Interpretation-2. The Interpretation of Logging Data, Developments in Petroleum Science. Amsterdam, Netherlands, Elsevier, 1986.
Shahid, R., Bertazzon, S., Knudtson. M. L., et al. Comparison of distance measures in spatial analytical modeling for health service planning. BMC Health Services Research, 2009, 9: 200.
Wood, D. A. Hybrid cuckoo search optimization algorithms applied to complex wellbore trajectories aided by dynamic, chaos-enhanced, fat-tailed distribution sampling and metaheuristic profiling. Journal of Natural Gas Science and Engineering, 2016, 34: 236-252.
Wood, D. A. Gamma-ray log derivative and volatility attributes assist facies characterization in clastic sedimentary sequences for formulaic and machine learning analysis. Advances in Geo-Energy Research, 2022a, 6(1): 69-85.
Wood, D. A. Enhancing lithofacies machine learning predictions with gamma-ray attributes for boreholes with limited diversity of recorded well logs. Artificial Intelligence in Geosciences, 2022b, 2: 148-164.
Wood, D. A. Carbonate/siliciclastic lithofacies classification aided by well-log derivative, volatility and sequence boundary attributes combined with machine learning. Earth Science Informatics, 2022c, 15(3): 1699-1721.
Wood, D. A. Optimized feature selection assists lithofacies machine learning with sparse well log data combined with calculated attributes in a gradational fluvial sequence. Artificial Intelligence in Geosciences, 2022d, 3: 132-147.
Zhang, Y., Li, Y., Guo, W., et al. Differential evolution and the influencing factors of low-maturity terrestrial shale with different types of kerogen: A case study of a Jurassic shale from the northern margin of Qaidam Basin, China. International Journal of Coal Geology, 2020, 230: 103591.
Zhang, F., Zhang, C. Evaluating the potential of carbonate sub-facies classification using NMR longitudinal over transverse relaxation time ratio. Advances in Geo-Energy Research, 2021, 5(1): 87-103.
Open Access This article is distributed under the terms and conditions of the Creative Commons Attribution (CC BY-NC-ND) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.