Abstract
The aim of this work is to demonstrate how geologically interpretative features can improve machine learning facies classification with uncertainty assessment.Manual interpretation of lithofacies from wireline log data is traditionally performed by an expert, can be subject to biases, and is substantially laborious and time consuming for very large datasets. Characterizing the interpretational uncertainty in facies classification is quite difficult, but it can be very important for reservoir development decisions. Thus, automation of the facies classification process using machine learning is a potentially intuitive and efficient way to facilitate facies interpretation based on large-volume data. It can also enable more adequate quantification of the uncertainty in facies classification by ensuring that possible alternative lithological scenarios are not overlooked. An improvement of the performance of purely data-driven classifiers by integrating geological features and expert knowledge as additional inputs is proposed herein, with the aim of equipping the classifier with more geological insight and gaining interpretability by making it more explanatory. Support vector machine and random forest classifiers are compared to demonstrate the superiority of the latter. This study contrasts facies classification using only conventional wireline log inputs and using additional geological features. In the first experiment, geological rule-based constraints were implemented as an additional derived and constructed input. These account for key geological features that a petrophysics or geological expert would attribute to typical and identifiable wireline log responses. In the second experiment, geological interpretative features (i.e., grain size, pore size, and argillaceous content) were used as additional independent inputs to enhance the prediction accuracy and geological consistency of the classification outcomes. Input and output noise injection experiments demonstrated the robustness of the results towards systematic and random noise in the data. The aspiration of this study is to establish geological characteristics and knowledge to be considered as decisive data when used in machine learning facies classification.
Highlights
Manual interpretation of lithofacies from wireline log data is traditionally performed by an expert, can be subject to biases, and is substantially laborious and time consuming for very large datasets
Lithofacies classification based on wireline logs is often subject to interpretation bias as it is traditionally performed by an expert, who assigns a lithology to a particular set of wireline log responses cross-references the interpretation to the lithology observed in cores
The depth shuffling of the grain size input reduced its weighted importance to almost null (Fig. 8c), while the average test prediction accuracy remained at 99%
Summary
Lithofacies classification based on wireline logs is often subject to interpretation bias as it is traditionally performed by an expert, who assigns a lithology to a particular set of wireline log responses cross-references the interpretation to the lithology observed in cores (when available). Compiling a series of well logs from heavily explored basins or giant oil/gas fields is an intensively time-consuming and strenuous task to perform. The uncertainty associated with well log interpretation must be accounted for, as it may have a significant impact on development decisions. This interpretational uncertainty is usually difficult to determine using a traditional, deterministic approach
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
