Using Supervised Machine Learning Algorithms for Automated Lithology Prediction from Wireline Log Data

This paper presents advancements in machine learning and cloud deployment that enable rapid and accurate automated lithology interpretation. A supervised machine learning technique is described that enables rapid, consistent, and accurate lithology prediction alongside quantitative uncertainty from large wireline or logging-while-drilling (LWD) datasets. To leverage supervised machine learning, a team of geoscientists and petrophysicists made detailed lithology interpretations of wells to generate a comprehensive training dataset. Lithology interpretations were based on applying determinist cross-plotting by utilizing and combining various raw logs. This training dataset was used to develop a model and test a machine learning pipeline. The pipeline was applied to a dataset previously unseen by the algorithm, to predict lithology. A quality checking process was performed by a petrophysicist to validate new predictions delivered by the pipeline against human interpretations. Confidence in the interpretations was assessed in two ways. The prior probability was calculated, a measure of confidence in the input data being recognized by the model. Posterior probability was calculated, which quantifies the likelihood that a specified depth interval comprises a given lithology. The supervised machine learning algorithm ensured that the wells were interpreted consistently by removing interpreter biases and inconsistencies. The scalability of cloud computing enabled a large log dataset to be interpreted rapidly; >100 wells were interpreted consistently in five minutes, yielding >70% lithological match to the human petrophysical interpretation. Supervised machine learning methods have strong potential for classifying lithology from log data because: 1) they can automatically define complex, non-parametric, multi-variate relationships across several input logs; and 2) they allow classifications to be quantified confidently. Furthermore, this approach captured the knowledge and nuances of an interpreter's decisions by training the algorithm using human-interpreted labels. In the hydrocarbon industry, the quantity of generated data is predicted to increase by >300% between 2018 and 2023 (IDC, Worldwide Global DataSphere Forecast, 2019–2023). Additionally, the industry holds vast legacy data. This supervised machine learning approach can unlock the potential of some of these datasets by providing consistent lithology interpretations rapidly, allowing resources to be used more effectively.

Application of Sh S-Wave Data in Lithologic Trap Identification

The biogas lithologic reservoirs in Sanhu Area of the Qaidam Basin has a broad exploration prospect, however, the demands of structural implementation and reservoir prediction can hardly be met with the existing P-wave seismic data due to the thin thickness of single sandstone layers, the rapid lateral changes and the low prediction accuracy of lithologic reservoirs. The SH-wave data has a higher resolution ability in lithology prediction. I can better reflect the lateral change features of formations. Because few SH-wave logging data are available and they are in accurate in the current study area, the SH-wave velocity is estimated through petrophysical modeling and the calibration and horizon interpretation of the SH-wave data are realized combined with the P- and SH-wave matching technology. Through the inversion of S-wave data,the lithological distribution of formations are predicted in combination with the comrehensive analysis of P-wave data, which provides a favorable basis for the survey of lithologic gas reservoir in the research area and achieves a good good result. In this way,a set of reservoir prediction methods and processes suitable for the shallow biogas lithological exploration in the Sanhu Area have formed initially.