Machine Learning Application of Two-Dimensional Fracture Properties Estimation

Abstract

Fractures are substantial contributors to solute transport sedimentary systems that form pathways. The pathway formed in a fracture has two physical parameters, there are mean aperture and surface roughness. Mean aperture is the thickness of the pathway that the fluid will pass through, and surface roughness is the roughness of the fracture pathway. The two physical parameters of the fracture are important to determine since they affect the permeability value in petroleum reservoir analysis. We developed a machine learning algorithm based on the Convolutional Neural Network (CNN) to predict those two parameters. Furthermore, image processing analysis is performed to generate the datasets. The results show that the CNN algorithm shows good agreement with the reference results. In addition, the algorithms showed efficient performance in terms of computational time. CNN is a type of deep neural designed to perform analysis on multi-channel images that can classify fracture geometry. The best model was determined using a benchmark dataset with a CNN model provided by Keras. The results of experiments conducted on fracture geometry images show that the machine learning model created is able to predict the mean aperture and surface roughness values.