College of Petroleum Engineering and Geosciences, King Fahd University of Petroleum and Minerals, Dhahran, 31261, Saudi Arabia.
Sci Rep. 2021 Dec 6;11(1):23445. doi: 10.1038/s41598-021-02959-9.
Determination of in-situ stresses is essential for subsurface planning and modeling, such as horizontal well planning and hydraulic fracture design. In-situ stresses consist of overburden stress (σ), minimum (σ), and maximum (σ) horizontal stresses. The σ and σ are difficult to determine, whereas the overburden stress can be determined directly from the density logs. The σ and σ can be estimated either from borehole injection tests or theoretical finite elements methods. However, these methods are complex, expensive, or need unavailable tectonic stress data. This study aims to apply different machine learning (ML) techniques, specifically, random forest (RF), functional network (FN), and adaptive neuro-fuzzy inference system (ANFIS), to predict the σ and σ using well-log data. The logging data includes gamma-ray (GR) log, formation bulk density (RHOB) log, compressional (DTC), and shear (DTS) wave transit-time log. A dataset of 2307 points from two wells (Well-1 and Well-2) was used to build the different ML models. The Well-1 data was used in training and testing the models, and the Well-2 data was used to validate the developed models. The obtained results show the capability of the three ML models to predict accurately the σh and σH using the well-log data. Comparing the results of RF, ANFIS, and FN models for minimum horizontal stress prediction showed that ANFIS outperforms the other two models with a correlation coefficient (R) for the validation dataset of 0.96 compared to 0.91 and 0.88 for RF, and FN, respectively. The three models showed similar results for predicting maximum horizontal stress with R values higher than 0.98 and an average absolute percentage error (AAPE) less than 0.3%. a index for the actual versus the predicted data showed that the three ML techniques were able to predict the horizontal stresses with a deviation less than 20% from the actual data. For the validation dataset, the RF, ANFIS, and FN models were able to capture all changes in the σ and σ trends with depth and accurately predict the σ and σ values. The outcomes of this study confirm the robust capability of ML to predict σ and σ from readily available logging data with no need for additional costs or site investigation.
原地应力的确定对于地下规划和建模至关重要，例如水平井规划和水力压裂设计。原地应力由上覆应力（σ）、最小水平应力（σ）和最大水平应力（σ）组成。σ和σ难以确定，而上覆应力可以直接从密度测井中确定。σ和σ可以通过钻孔注入测试或理论有限元方法来估算。然而，这些方法复杂、昂贵，或者需要不可用的构造应力数据。本研究旨在应用不同的机器学习（ML）技术，特别是随机森林（RF）、函数网络（FN）和自适应神经模糊推理系统（ANFIS），使用测井数据预测 σ 和 σ。测井数据包括伽马射线（GR）测井、地层体积密度（RHOB）测井、纵波（DTC）和横波（DTS）渡越时间测井。使用来自两口井（井 1 和井 2）的 2307 个点数据集来构建不同的 ML 模型。井 1 数据用于训练和测试模型，井 2 数据用于验证开发的模型。结果表明，这三种 ML 模型能够使用测井数据准确地预测 σ h 和 σ H。比较 RF、ANFIS 和 FN 模型对最小水平应力预测的结果表明，与 RF 和 FN 相比，ANFIS 的相关系数（R）对于验证数据集分别为 0.96、0.91 和 0.88，表现出更好的预测能力。对于最大水平应力的预测，三个模型的结果相似，R 值均高于 0.98，平均绝对百分比误差（AAPE）均小于 0.3%。a 指数用于表示实际数据与预测数据之间的偏差，表明三种 ML 技术能够以小于实际数据 20%的偏差来预测水平应力。对于验证数据集，RF、ANFIS 和 FN 模型能够捕捉到 σ 和 σ 随深度的变化趋势，并准确预测 σ 和 σ 值。本研究的结果证实了 ML 从现成的测井数据中预测 σ 和 σ 的强大能力，无需额外的成本或现场调查。
