Efficiency of machine learning to predict gas accumulations

Abstract

A growing number of research geophysicists are drawn to machine learning in geophysical applications. At the moment, direct applications of machine learning cover an expansive range of tasks related to the interpretation of seismic data. Beginning with computer-assisted seismic well tying, faults and horizons are automatically interpreted, velocity models are optimized, geobodies are extracted, and seismic facies are classified. Our goal is to demonstrate how artificial neural networks may be used to teach a computer to categorize seismic data and anticipate possible gas accumulations, starting from selecting training data, through filtering the best discriminating attributes, monitoring the learning process, and ending with running the predictions. This workflow was applied on a Dana Gas Messininan gas field in the Nile Delta province of Egypt. The network was trained on a few seismic points in the vicinity of one successful well as positive training examples. The network not only accurately predicted the gas accumulation near the training points but also the other nearby stratigraphically compartmentalized gas accumulations, aligning with production and pressure data of the hidden wells. Similar findings were obtained when the results were compared to classical amplitude variation with offset elastic inversion; however, the machine learning methodology is far faster and easier than the inversion in terms of procedural steps and required work.