On May 22 Novi’s chief geophysicist Kiran Sathaye gave a technical presentation at AAPG ACE 2019 in San Antonio on leveraging AI to predict hydrocarbon recovery. Read the abstract and be sure to view the presentation slides here. Thank you to everyone who attended the talk!
Authors
K. Sathaye, J. Ramey, J. Wan
Abstract
We combine production and completion data from 9,000 unconventional wells in the Williston Basin with 42,000 geophysical log files representing 10,000 unique wells to build a predictive model for hydrocarbon production. We predict hydrocarbon recovery at 30-day intervals up to 2 years after the start of production. This model contains dozens of input features and incorporates their nonlinear, multivariate effects on hydrocarbon production. The subsurface modeling and recovery predictions are implemented using the open source machine learning tools Scikit-learn and Tensorflow.
In developing the subsurface model for this machine learning approach, we also create predictions for important subsurface features that are not commonly logged due to cost and complexity, such as measurements of hydrocarbon chain length in productive formations of the basin. These measurements show nonlinear relationships both in space and with commonly logged properties, boosting the impact of a relatively sparse dataset. Additionally, we use this public subsurface dataset to identify subdivisions in the Bakken (lower, middle, upper), and train the model with subsurface features informed by previous geologic studies which identified these sections in core studies and well log interpretation.
With only production and completion data included, we see less than 15-25% aggregate error for various areas of the basin. We show successive improvements in this machine learning model by training it with a sequence of datasets: Production and completion data with limited well counts and full dataset, and a model with subsurface features added with both limited well count and full dataset. For all models, we use an 80%-20% training-test split to avoid overfitting the model.
View Our AAPG Presentation Now!