Modeling of Two-Phase Fluid Flow in a Well Using Machine Learning Algorithms

Summary Bottom hole pressure prediction is crucial issue in integrated field modeling. This article proposes a new approach to well modeling implementing machine learning algorithms. In this paper bottomhole pressure is analysed as dependent variable on four parameters such as level of wellhead pressure, flow rate, gas factor and water cut. The model is developed using the "Random forest" approach with gradient boosting. The model was tested on synthetic and real data from different wells and fields. The prediction accuracy satisfies company requirements and is more than 90 times faster than traditional empirical correlations.