seismic facies analysis, modeling and geobody extraction by machine learning in an oilfield in iran

In this paper, we have used the supervised learning analysis, which is one of the machine learning methods, so that it is possible to determine the facies and build their model more accurately, and then proceed to the extraction of different geobodies. the goal of supervised learning algorithms is learning a function that maps feature vectors (inputs) to labels (output), based on example input-output pairs. in geology, facies are a body of rock with specified characteristics which can be any observable attribute of rocks (such as their overall appearance, composition, or condition of formation), and the changes that may occur in those attributes over a geographic area. facies encompasses all of the characteristics of a rock including its chemical, physical, and biological features that distinguish it from adjacent rock. seismic facies analysis based on the bayesian classification has been implemented for this oilfield. in this regard, different lithofacies (with distinct characteristics) have been proposed based on the rock physics concepts and petrophysical evaluations. moreover, these lithofacies were suitable for differentiating by elastic properties. in this paper, firstly the importance of machine learning is discussed, then the entire process is explained with relevant figures, and finally, the results of the work are presented.