Classification of seismic facies using seismic multi-attribute

Resumo

Seismic interpretation is a fundamental process for hydrocarbon exploration. This activity consists
of identifying geological information through the processing and analysis of seismic data. With seismic data’s
rapid growth and complexity, manual seismic facies analysis has become a significant challenge. Mapping seismic
facies is a time-consuming process that requires specialized professionals. The objective of this work aims to
apply multiattribute classification using a deconvolution neural network to map the seismic facies and assist in
the interpretation process. We calculate a set of seismic attributes using Opendtect version 6.6 software from the
amplitude data contained in the Facies-Mark Dataset. They are: Energy, Pseudo Relief, Instantaneous Phase, and
Texture, all selected by an interpreter. The results showed that the attributes obtained a satisfactory result, reaching
85.15%, and the attributes together with the amplitude obtained 85.73%, while the amplitude, which is the most
commonly used data in seismic classification, obtained 81.23%, based on the FWIU metric. In a direct comparison
between the model with data augmentation and with attributes, the second performed better.