ANPERC

Petrographic analysis is one of the most important and routinely used methods in a wide range of earth and environmental science applications. There has been a growing motivation for computer-aided automated analysis of thin sections due to an inherent subjectivity of interpretation by geologists and the ever-increasing need for analysis of new and legacy thin section petrography data. In this study, we propose a workflow for petrographic features prediction of carbonate reservoir including Dunham textures classification and depositional facies prediction based on thin sections using deep-learning. A pre-trained DenseNet model is applied for auto-classification of Dunham textures. An integrated scheme consists of two VGG models and one U-Net model is used for depositional facies prediction. First, one VGG model was used to classify thin sections into three groups, namely, grain-dominated, mud-dominated, and stromatoporoid facies. Then the U-Net model was used to identify oncoids to further classify oncoidal facies from grain-dominated facies. Finally, another VGG model was applied to classify the peloid-rich facies from the left grain-dominated facies. We used 1042 thin sections collected from the Upper Jurassic Hanifa reservoir analog formation, Saudi Arabia, to demonstrate our proposed workflow and the prediction results show that our proposed method performs well in automatically petrographic features prediction. The Dunham classification model resulted in a prediction accuracy of 89%, and the depositional facies prediction model achieved final accuracy of 86%.