Seismic Waveform Classification of Reservoir Properties Using Geological Facies Through Neural Network

Abstract

Seismic waveform classification is a very powerful tool to explore hydrocarbon especially in area with sparse well data. However, dependency on seismic data remains small without any geological or physical evidence such as well logs that are able to support the interpretation. Hence, numerous efforts have been made to establish strong relationship between geology and geophysics using different methods and techniques throughout the years. This paper focuses on seismic waveform classification to different classes using neural network and to link them to geological facies derived from well log data. The interpretation of seismic facies or waveform classification map provides a better understanding toward depositional environment and helps to identify significant reservoir rock. The produced facies model can also be used to reduce uncertainty in exploration and production, especially for reservoir productivity enhancement and stratigraphic identification.