Al-Mudhafar Watheq J, Hasan Alqassim A, Abbas Mohammed A, Wood David A
Basrah Oil Company, Basra, Iraq.
Basrah University of Oil and Gas, Basra, Iraq.
Sci Rep. 2025 Apr 15;15(1):12939. doi: 10.1038/s41598-025-95490-0.
Most carbonate reservoirs exhibit heterogeneous pore distribution, whereby the matrix displays low permeability, thus impeding the flow of oil. On the other hand, highly permeable fractures function as the main flow conduits within such reservoirs. Permeability measurements are obtained from core and well test analysis, which are too expensive and not available for many wells. Therefore, accurate permeability prediction is a vital step in developing an efficient field development plan, as it plays a pivotal role in the accurate distribution of 3D petrophysical properties throughout a reservoir. Machine learning (ML) algorithms are now widely applied to predict core permeability using conventional well logs to build a model for permeability prediction in uncored wells. This review considers the performance of six ML algorithms (LightGBM, CATBoost, XGBoost, Adaboost, random forest and gradient boosting) for permeability prediction from a high-quality dataset. The dataset incorporates multiple well-log inputs (gamma ray, caliper, density, neutron porosity, shallow and deep resistivity, total porosity, spontaneous potential, water saturation, depth, and facies) in addition to direct core permeability and porosity measurements. Data pre-processing techniques applied include missing data imputation, scale correction, normalization with three different transformations (log, Box-Cox, and NST) and outlier detection. To enhance the ML performance, two search algorithms (random search and Bayesian optimization) are compared in their ability to tune the ML hyperparameters. There is a need to identify a suitable parameter space, especially when the target variable range is changing. ML performance was evaluated with four evaluation metrics (RMSE, MAE, R, and Adjusted R). Results showed that the XGBoost algorithm with configuration of (RS as search algorithm, Box Cox as the normalization method, Z-score for outlier detection, without scale correction, old parameter space) delivered the best prediction performance for permeability with RMSE values of 6.9 md and 9.78 md for training and testing, respectively.
大多数碳酸盐岩储层呈现出孔隙分布不均的情况，其中基质渗透率较低，从而阻碍了油的流动。另一方面，高渗透率的裂缝是此类储层中的主要流动通道。渗透率测量是通过岩心和试井分析获得的，这些方法成本过高，而且许多井无法进行。因此，准确的渗透率预测是制定高效油田开发计划的关键一步，因为它在整个储层三维岩石物理性质的精确分布中起着关键作用。机器学习（ML）算法现在被广泛应用于利用常规测井数据预测岩心渗透率，以建立未取心井的渗透率预测模型。本综述从一个高质量数据集中考虑了六种ML算法（LightGBM、CATBoost、XGBoost、Adaboost、随机森林和梯度提升）在渗透率预测方面的性能。该数据集除了直接的岩心渗透率和孔隙度测量值外，还纳入了多个测井输入数据（伽马射线、井径、密度、中子孔隙度、浅电阻率和深电阻率、总孔隙度、自然电位、含水饱和度、深度和岩相）。应用的数据预处理技术包括缺失数据插补、尺度校正、采用三种不同变换（对数、Box-Cox和NST）的归一化以及异常值检测。为了提高ML性能，比较了两种搜索算法（随机搜索和贝叶斯优化）调整ML超参数的能力。需要确定合适的参数空间，尤其是当目标变量范围发生变化时。使用四个评估指标（RMSE、MAE、R和调整后的R）评估ML性能。结果表明，配置为（随机搜索作为搜索算法、Box Cox作为归一化方法、Z分数用于异常值检测、不进行尺度校正、旧参数空间）的XGBoost算法在渗透率预测方面表现出最佳性能，训练和测试的RMSE值分别为6.9 md和9.78 md。
