Facies classification with different machine learning algorithm – An efficient artificial intelligence technique for improved classification
MetadataShow full item record
Accurate and precise identification of lithological facies is vital to understand geological variation in a proven reservoir. Four specific different machine learning (ML) classification algorithms are implemented to predict facies on an open dataset in the Panoma gas field in southwest Kansas, USA. The objective is improvement of facies classification accuracy with robust application of ML technique compared to previous published work on the same dataset. A total of 4,149 data samples are available for analysis with known facies from the core data where each sample point contains four or five measured properties (wire-line logs), and two derived geological properties (geological constraining variables). Facies classification is addressed with four well-known classification algorithm which are artificial neural network (ANN), support vector machine (SVM), decision trees and gaussian process classifier (GPC). High dimensionality, non-linear correlation and overlapping feature space of facies classes make the non-parametric method more suitable to handle complex datasets. Among the presented classifiers, ANN perform better relative to others on validation dataset. It is observed that our present approach of adding more input features, increasing number of training dataset and efficient implementation of algorithm have improved facies prediction accuracy significantly on a blind well.
Showing items related by title, author, creator and subject.
Wright, Graeme L. (2000)The objective of this study was to investigate the application of multiscale satellite remote sensing data for assessment of land cover change in the rural-urban fringe. Inherent in this assessment process was the ...
Goh, Kwang Leng (2013)Web spamming has tremendously subverted the ranking mechanism of information retrieval in Web search engines. It manipulates data source maliciously either by contents or links with the intention of contributing negative ...
Accelerating Species Recognition and Labelling of Fish From Underwater Video With Machine-Assisted Deep LearningMarrable, Daniel ; Barker, Kathryn; Tippaya, Sawitchaya; Wyatt, M.; Bainbridge, S.; Stowar, M.; Larke, Jason (2022)Machine-assisted object detection and classification of fish species from Baited Remote Underwater Video Station (BRUVS) surveys using deep learning algorithms presents an opportunity for optimising analysis time and rapid ...