Efficient Classification of Seismic Textures

One of the most critical activities for the oil and gas industry is the discovery of new possibles reserves. Geoscientists must rely on indirect measures of the subsurface to scrutinize huge areas looking for leads of hydrocarbon reservoirs. Usually, to study the Earth's crust, geoscientists examine seismic images. Although deep learning has become popular in the last decade, only a few published results have demonstrated the application of such techniques to seismic images. In this paper, we present deep neural models specifically for the task of seismic facies analysis, using state-of-the-art concepts and tools to train and classify seismic facies efficiently. Our results show that we can train a neural network in 4 minutes using less than 5% of the dataset, and yet obtain 88% of accuracy. Moreover, we can reach up to 97% of accuracy in 30 minutes using 60% of the dataset.