In the oil and gas exploration process, understanding the hydrocarbon distribution of a reservoir is important. Well-log and core sample data such as porosity and water saturation are widely used for this purpose. With porosity and water saturation, we can calculate hydrocarbon volume more accurately than using well-log solely.
However, as obtaining core sample data is expensive and time-consuming, predicting it with well-log can be a valuable solution for early-stage exploration since acquiring well-log is relatively economic and swift. Recently, numerous studies applied machine learning algorithms to predict core data from well-log. To the best of our knowledge, most works provide point estimation without probabilistic distribution modeling.
In this paper, we developed a probabilistic deep neural network to provide uncertainty via confidence interval. Besides, we employed normalizing flows and multi-task learning to improve prediction accuracy. With this approach, we present the model's uncertainty that can be reliable information for decision making. Furthermore, we demonstrate our model outperforms other supervised machine learning algorithms regards to prediction accuracy.