Machine learning-assisted production data analysis in liquid-rich Duvernay Formation

Abstract

Abstract The production of gas and oil from the unconventional tight and shale reservoirs is the outcome through a series of cooperative efforts of drilling, completion, and production operations. This study aims to optimize these operations to enhance the well productivity and oil recovery, and ultimately to reduce the development footprint on the level of individual wells. More specifically, a comprehensive data set is collected and analyzed for the Duvernay reservoir, including geology, drilling, completion, production operations, and production data. A customized stacked model is created to train production models with an extreme gradient boosting regressor as the base model and linear regressor as the meta model. The models achieve robust predictive ability with a determination coefficient of up to 0.80. The Shapley values reveal that the producing time, condensate/gas ratio, and the completion section length are the most important features to the early time production. The Bayesian optimization method is adopted to optimize the production using the trained models. This study shows the potential of the machine learning approach to model oil and gas production and provides insights for optimizing production in the tight and shale reservoirs.