A novel multiclass SVM based framework to classify lithology from well logs: A real-world application

Abstract

Abstract-Support vector machines (SVMs) have been recognized as a potential tool for supervised classification analyses in different domains of research. In essence, SVM is a binary classifier. Therefore, in case of a multiclass problem, the problem is divided into a series of binary problems which are solved by binary classifiers, and finally the classification results are combined following either the one-against-one or one-againstall strategies. In this paper, an attempt has been made to classify lithology using a multiclass SVM based framework using well logs as predictor variables. Here, the lithology is classified into four classes such as sand, shaly sand, sandy shale and shale based on the relative values of sand and shale fractions as suggested by an expert geologist. The available dataset consisting well logs (gamma ray, neutron porosity, density, and P-sonic) and class information from four closely spaced wells from an onshore hydrocarbon field is divided into training and testing sets. We have used one-against-all strategy to combine the results of multiple binary classifiers. The reported results established the superiority of multiclass SVM compared to other classifiers in terms of classification accuracy. The selection of kernel function and associated parameters has also been investigated here. It can be envisaged from the results achieved in this study that the proposed framework based on multiclass SVM can further be used to solve classification problems. In future research endeavor, seismic attributes can be introduced in the framework to classify the lithology throughout a study area from seismic inputs.

Application of Artificial Neural Networks for Identification of Lithofacies by Processing of Core Drilling Data

“…To mitigate the risk of overfitting and not properly testing, we applied L2 regularization and incorporated dropout procedures for both the input and hidden layers during the training process. Furthermore, when tested on different segments of the same drilling data, we consistently achieved an accuracy rate of over 92% for this binary classification problem, compared to a prediction accuracy rate of 31.86% for SVM methods [27], 82.43% for multiclass SVM methods [23], 84.5% in multi-agent collaborative learning architecture methods [28], and 88.32% in HEMs [3]. We note from the table that the trained model required only 2.85 ms to classify all eight samples in the testing dataset, which is negligible compared to the 49 s required to collect the 4900 data points for a single sample at the applied sampling frequency.…”

“…The work of de Lima et al [22] conducted lithofacies identification based on core image data processed using a deep convolutional neural network (CNN) trained with millions of core images. Chaki et al [23], using a multiclass SVM framework based on well logs as predictor variables, demonstrating the superiority of multiclass SVMs over other conventional SVMs in terms of classification accuracy, improved the prediction accuracy to 84.5%. Tewari [3] proposed a heterogeneous ensemble method (HEM) approach for lithofacies identification, which has the capability to handle complex, nonlinear, multidimensional, and imbalanced drilling data, achieved an accuracy of 88.32% on the testing set.…”

A comparative study of heterogeneous ensemble methods for the identification of geological lithofacies

“…Extraction of valuable lithofacies information from well logs data is quite a challenging task even for intelligent HoEMs. Spatial distribution and heterogeneous behavior of the hydrocarbon reservoir properties contribute to complexity, nonlinearly and uncertainty in all types of sensor-based measurements (Chaki et al 2015;Bhattacharya et al 2016). Also, no standard tools or techniques are available in the present scenario that can measure the reservoir heterogeneity and its influence on other reservoir properties, well logs and drilling data, etc.…”

“…Recognition of subsurface lithofacies is much researched topic and still a thought-provoking problem due to the uncertainty associated with reservoir measurements (Chaki et al 2015;Bhattacharya et al 2016). Quantitative modeling of lithofacies is essential to assess the potential of unconventional hydrocarbon reservoirs lying in mudstone formations.…”

“…Several logging techniques such as wireline, logging-while-drilling, measurement-while-logging, etc., are utilized to generate wide varieties of well logs for measuring petrophysical properties of reservoir rock (Anifowose et al 2015(Anifowose et al , 2017. Various researchers have reported that logging data are found to be nonlinear, high dimensional, complex and noisy in nature due to the heterogeneity and spatial distribution of reservoir properties (Kocberber and Collins 1990;Chaki et al 2015;Bhattacharya et al 2016;Tewari and Dwivedi 2018a). Therefore, manual identification of geological lithofacies from sensory well logs is an impractical and tedious job even for expert field engineers.…”