A method for enhancing well-log resolution of thin lithological heterogeneities using wavelet transform and automated machine learning
Abstract
Clastic reservoirs exhibit complex and diverse lithologies. Some lithological heterogeneities, occurring as thin but effectively low-permeability units, have pronounced impact on CO2 flooding schemes and oil recovery. Thin low-permeability units within permeable sandbodies typically exhibit weak well-log responses, and are therefore of difficult recognition using conventional well-log analysis methods. To address this challenge, a hierarchical method is proposed for interpreting thin lithological heterogeneities by integrating wavelet transform and machine learning. The discrete wavelet transform enhances well-log responses of thin heterogeneities. An automated machine-learning framework is designed, which integrates multiple algorithms and achieves automated parameter optimization. This machine-learning method is then applied to well logs to establish a nonlinear mapping model between lithology and well-log responses. Additionally, the hierarchical nature of the workflow highlights lithological contrasts, facilitating a more accurate lithological differentiation by dividing the recognition of thin heterogeneities into three levels. Benefiting from these three advantages, the proposed method offers potential to significantly enhance the accuracy of well-log interpretations. The results demonstrate that this method yields accurate identification of lithological units as thin as 0.2 m for muddy beds and 0.3 m for diagenetic units, achieving a recognition accuracy exceeding the conventional well-log interpretations. This method also shows significant potential for broader applications, including the identification of other types of geological entities of limited thickness, and determination of reservoir parameters at fine scales.
Document Type: Original article
Cited as: Li, W., Liu, L., Yue, D., Gao, J., Zhang, S., Colombera, L. A method for enhancing well-log resolution of thin lithological heterogeneities using wavelet transform and automated machine learning. Advances in Geo-Energy Research, 2025, 17(2): 149-161. https://doi.org/10.46690/ager.2025.08.06
Keywords:
Well-log interpretation, permeability barrier, clastic reservoir, thin lithology, flow baffle, wavelet transformReferences
Chandrasekhar, E., Rao, V. E. Wavelet analysis of geophysical well-log data of Bombay Offshore Basin, India. Mathematical Geosciences, 2012, 44(8): 901-928.
Chawla, N. V., Bowyer, K. W., Hall, L. O., et al. SMOTE: Synthetic minority over-sampling technique nitesh. Journal of Artificial Intelligence Research, 2002, 16: 321-357.
Chen, S., Liu, P., Tang, D., et al. Identification of thin-layer coal texture using geophysical logging data: Investigation by wavelet transform and linear discrimination analysis. International Journal of Coal Geology, 2021, 239: 103727.
Erickson, N., Mueller, J., Shirkov, A., et al. AutoGluonTabular: Robust and accurate AutoML for structured data. ArXiv Preprint ArXiv: 2003.06505, 2020.
Feng, R., Grana, D., Balling, N. Variational inference in Bayesian neural network for well-log prediction. Geophysics, 2021, 86(3): M91-M99.
Iraji, S., Soltanmohammadi, R., Matheus, G. F., et al. Application of unsupervised learning and deep learning for rock type prediction and petrophysical characterization using multi-scale data. Geoenergy Science and Engineering, 2023, 230: 212241.
Kuang, L., Liu, H., Ren, Y., et al. Application and development trend of artificial intelligence in petroleum exploration and development. Petroleum Exploration and Development, 2021, 48(1): 1-14.
Lai, J., Wang, G., Wang, S., et al. Review of diagenetic facies in tight sandstones: Diagenesis, diagenetic minerals, and prediction via well logs. Earth-Science Reviews, 2018, 185: 234-258.
Li, W., Mamora, D., Li, Y., et al. Numerical investigation of potential injection strategies to reduce shale barrier impacts on SAGD process. Journal of Canadian Petroleum Technology, 2011: 50(3): 57-64.
Li, W., Yue, D., Du, Y., et al. Controls of accommodation to sediment-supply ratio on sedimentary architecture of continental fluvial successions. Petroleum Science, 2023, 20(4): 1961-1977.
Liu, R., Yue, D., Li, W., et al. Characterization of tight sandstone and sedimentary facies using well logs and seismic inversion in lacustrine gravity-flow deposits. Journal of Asian Earth Sciences, 2024, 259: 105897.
Lynds, R., Hajek, E. Conceptual model for predicting mudstone dimensions in sandy braided-river reservoirs. AAPG Bulletin, 2006, 90(8): 1273-1288.
Mallat, S. G., Zhang, Z. Matching pursuits with timefrequency dictionaries. IEEE Transactions on Signal Processing, 1993, 41(12): 3397-3415.
Miall, A. D. Architectural-element analysis: A new method of facies analysis applied to fluvial deposits. Earth-Science Reviews, 1985, 22(4): 261-308.
Nyberg, B., Henstra, G., Gawthorpe, R. L. et al. Global scale analysis on the extent of river channel belts. Nature Communications, 2023, 14(1): 2163.
Olkkonen, J. O. Discrete Wavelet Transforms-Theory and Applications. Rijeka, Croatia, InTech, 2011.
Papík, M., Papíková, L. The possibilities of using AutoML in bankruptcy prediction: Case of Slovakia. Technological Forecasting and Social Change, 2025, 215: 124098.
Pham, N., Wu, X., Naeini, E. Z. Missing well log prediction using convolutional long short-term memory network. Geophysics, 2020, 85(4): WA159-WA171.
Qi, W., Xu, C., Xu, X. AutoGluon: A revolutionary framework for landslide hazard analysis. Natural Hazards Research, 2021, 1(3): 103-108.
Rafieepour, S., Zheng, D., Miska, S., et al. Combined experimental and well log evaluation of anisotropic mechanical properties of shales: An application to wellbore stability in bakken formation. Paper SPE 201334 Presented at the SPE Annual Technical Conference and Exhibition, Virtual, 26-29 October, 2020.
Saneifar, M., Heidari, Z., Hill, A. D. Application of conventional well logs to characterize spatial heterogeneity in carbonate formations required for prediction of acidfracture conductivity. SPE Production and Operations, 2015, 30(3): 243-256.
Shan, L., Liu, Y., Tang, M., et al. CNN-BiLSTM hybrid neural networks with attention mechanism for well log prediction. Journal of Petroleum Science and Engineering, 2021, 205: 108838.
Stanistreet, I. G., Stollhofen, H. Hoanib River flood deposits of Namib Desert interdunes as analoques for thin permeability barrier mudstone layers in aeolianite reservoirs. Sedimentology, 2002, 49(4): 719-736.
Strick, R. J. P., Ashworth, P. J., Sambrook Smith, G. H., et al. Quantification of bedform dynamics and bedload sediment flux in sandy braided rivers from airborne and satellite imagery. Earth Surface Processes and Landforms, 2019, 44(4): 953-972.
Sun, B., Cui, W., Liu, G., et al. A hybrid strategy of AutoML and SHAP for automated and explainable concrete strength prediction. Case Studies in Construction Materials, 2023, 19: e02405.
Wang, R., Lv, C., Lun, Z., et al. Study on gas channeling characteristics and suppression methods in CO2 flooding for low permeability reservoirs. Paper SPE 142306 Presented at the SPE Asia Pacific Oil and Gas Conference and Exhibition, Jakarta, Indonesia, 20-22 September, 2011.
Wang, W., Lyu, Q., Fan, T., et al. Characteristics of the tuffaceous shale oil reservoir and its sweet spots: A case study of the Tiaohu depression in the Santanghu Basin. Unconventional Resources, 2022, 2: 192-199.
Wei, T., Xu, J., Song, L., et al. Reservoir porosity interpretation method and application based on intelligent algorithms. Geoenergy Science and Engineering, 2025, 247: 213650.
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. Extracting useful information from sparsely logged wellbores for improved rock typing of heterogeneous reservoir characterization using well-log attributes, feature influence and optimization. Petroleum Science, 2022b, 22: 2307-2311.
Wood, D. A. Well-log attributes assist in the determination of reservoir formation tops in wells with sparse well-log data. Advances in Geo-Energy Research, 2023, 8(1): 45-60.
Yang, L., Wang, S., Chen, X., et al. Deep-learning missing well-log prediction via long short-term memory network with attention-period mechanism. Geophysics, 2023, 88(1): D31-D48.
Yang, X., Wang, R., Li, K., et al. Meta-Black-Box optimization for evolutionary algorithms: Review and perspective. Swarm and Evolutionary Computation, 2025, 93: 101838.
Yue, D., Wu, S., Xu, Z., et al. Reservoir quality, natural fractures, and gas productivity of upper Triassic Xujiahe tight gas sandstones in western Sichuan Basin, China. Marine and Petroleum Geology, 2018, 89: 370-386.
Zecchin, M, Catuneanu, O. High-resolution sequence stratigraphy of clastic shelves VI: Mixed siliciclastic-carbonate systems. Marine and Petroleum Geology, 2017, 88: 712-723.
Zhang, X., Li, Q., Li, L., et al. Combination of sonic wave velocity, density and electrical resistivity for joint estimation of gas-hydrate reservoir parameters and their uncertainties. Advances in Geo-Energy Research, 2023, 10(2): 133-140.
Zhang, S., Liu, C., Liang, H., et al. Mineralogical composition and organic matter characteristics of lacustrine fine-grained volcanic-hydrothermal sedimentary rocks: A data-driven analytics for the second member of Permian Lucaogou Formation, Santanghu Basin, NW China. Marine and Petroleum Geology, 2021, 126: 104920.
Zhang, X., Liu, M., Liu, Y. Battery state of health estimation using an AutoGluon-tabular model incorporating uncertainty quantification. Journal of Energy Storage, 2024, 101: 113920.
Zhang, Q., Zhang, F., Liu, J., et al. A method for identifying the thin layer using the wavelet transform of density logging data. Journal of Petroleum Science and Engineering, 2018, 160: 433-441.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.