Abstract

This study presents an integrated workflow for reservoir characterization in the Laxmi Field, Western Offshore Basin, using seismic attributes and well log analysis. Structural mapping revealed features such as four-way closures, while attributes like RMS amplitude, average absolute amplitude (AAA), average energy sweetness, and spectral decomposition highlighted potential hydrocarbon zones. Well logs from multiple wells were analyzed using gamma ray, resistivity, density, and neutron data, supported by cross-plots and M-N diagrams for lithology and fluid interpretation. Artificial intelligence was employed specifically for electrofacies classification to streamline and enhance the interpretation of well log data. By leveraging unsupervised clustering and supervised neural networks, the approach enabled automated identification of facies patterns with greater speed, objectivity, and scalability—particularly effective in managing large and complex datasets where manual classification would be time-consuming and inconsistent.