Detection of potential gas accumulations in 2D seismic images using spatio-temporal, PSO, and convolutional LSTM approaches

Seismic reflection is one of the most widely used geophysical methods in the oil and gas (O&G) industry for hydrocarbon prospecting. In particular, for some Brazilian onshore fields, this method has been used to estimate the location and volume of gas accumulations. However, the analysis and interpretation of seismic data are time-consuming due to the large amount of information and noisy nature of the acquisitions. To help geoscientists with these tasks, computational tools based on machine learning have been proposed considering direct hy-drocarbon indicators. In this study, we present a methodology for detecting gas accumulation based on the convolutional long short-term memory model and particle swarm optimization scheme. In the best scenario, the proposed method achieved an F1-score of 84.22%, sensitivity of 98.06%, specificity of 99.44%, and accuracy of 99.42%. We present tests performed on the Parnaiba Basin, indicating that the proposed method is promising for gas exploration.

Automated summary

Seismic reflection is widely used in the oil and gas industry to prospect hydrocarbon resources, and has been used in Brazilian onshore fields to estimate gas accumulations. However, the analysis and interpretation of seismic data are time-consuming due to the large amount of information and noise. To assist geoscientists, a methodology based on convolutional long short-term memory and particle swarm optimization is proposed for detecting gas accumulation. Testing in the Parnaiba Basin shows promising results with an F1-score of 84.22%, sensitivity of 98.06%, specificity of 99.44%, and accuracy of 99.42%.