A novel method to determine the thief zones in heavy oil reservoirs based on convolutional neural network

Abstract

The tracer breakthrough curve tends to be unimodal in heavy oil reservoir due to high oil-water viscosity ratio, which makes it difficult to classify thief zone (TZ) in these reservoirs using tracer breakthrough curve. To solve the problem, the paper applies the convolutional neural network (CNN) to achieve fast and accurate classification of TZ in heavy oil reservoir. The tracer flow analytical model is established by equating TZ with the flow tubes that satisfy the Hagen-Poiseuille equation. Then, 3000 tracer breakthrough curves are generated by the model as sample. Additionally, one-hot encoding method is applied to deal with these sample curves. Through the orthogonal design, the optimal combination of hyperparameters are determined to establish an OD-CNN model. According to the results, the number of convolutional layers is the most significant influencing factor in the accuracy of OD-CNN. Besides, the optimal hyperparameter combination for OD-CNN is detailed as follows. The number of convolutional layers is 4, the dropout rate is 0.6, the initialization method is Xavier normal, the optimizer is Adam, and the activation function is ReLU. Compared with random forest (RF) and K-means, the accuracy of OD-CNN on the training set is 94.67%, which is higher than 82.30% of RF and 75.63% of k-means. Moreover, OD-CNN can correctly classify 89 of the 100 curves from the oilfield indicating the reliability of OD-CNN. Thus, applying orthogonal design to OD-CNN can avoid the blindness of hyperparameter combination optimization and significantly reduce computing time.