Well Tops Guided Prediction of Reservoir Properties using Modular Neural Network Concept A Case Study from Western Onshore, India

TL;DR

This study introduces a modular neural network framework for predicting reservoir sand fraction from seismic attributes, utilizing well tops to segment data and improve prediction accuracy in an Indian hydrocarbon field.

Contribution

The paper presents a novel modular neural network approach that segments data by well tops and trains separate networks for each zone, enhancing prediction accuracy over traditional single-network methods.

Findings

Modular neural networks outperform single networks in prediction accuracy.

Segmentation by well tops improves model performance.

The approach reduces computation time and increases correlation coefficients.

Abstract

This paper proposes a complete framework consisting pre-processing, modeling, and post-processing stages to carry out well tops guided prediction of a reservoir property (sand fraction) from three seismic attributes (seismic impedance, instantaneous amplitude, and instantaneous frequency) using the concept of modular artificial neural network (MANN). The data set used in this study comprising three seismic attributes and well log data from eight wells, is acquired from a western onshore hydrocarbon field of India. Firstly, the acquired data set is integrated and normalized. Then, well log analysis and segmentation of the total depth range into three different units (zones) separated by well tops are carried out. Secondly, three different networks are trained corresponding to three different zones using combined data set of seven wells and then trained networks are validated using the remaining test well. The target property of the test well is predicted using three different tuned networks corresponding to three zones; and then the estimated values obtained from three different networks are concatenated to represent the predicted log along the complete depth range of the testing well. The application of multiple simpler networks instead of a single one improves the prediction accuracy in terms of performance metrics such as correlation coefficient, root mean square error, absolute error mean and program execution time.