Predicting oil and gas production from unconventional tight-rock reservoirs using machine learning
V.V. Vesselinov
XXIII International Conference on Computational Methods in Water Resources (CMWR)2020
Summary
Machine learning is applied to predict oil and gas production in unconventional tight-rock reservoirs by mapping complex, non-linear relationships between geological properties, completion designs, and historical production data. These data-driven models bypass the extreme computational bottlenecks of traditional physics-based simulations while outperforming conventional decline curve analysis. The presentation covers the development and application of these machine learning models, demonstrating their ability to provide accurate production forecasts and insights into key factors influencing reservoir performance.