TY - JOUR
T1 - Towards more accurate and explainable supervised learning-based prediction of deliverability for underground natural gas storage
AU - Ali, Aliyuda
AU - Aliyuda, Kachalla
AU - Elmitwally, Nouh
AU - Muhammad Bello, Abdulwahab
N1 - Funding Information:
The authors acknowledge financial support from the Petroleum Technology Development Fund (PTDF) of the Federal Republic of Nigeria. Special thanks to the subject Editor and anonymous reviewers for their valuable time and insightful comments, which significantly improved the quality of this paper.
Funding Information:
The authors acknowledge financial support from the Petroleum Technology Development Fund (PTDF) of the Federal Republic of Nigeria. Special thanks to the subject Editor and anonymous reviewers for their valuable time and insightful comments, which significantly improved the quality of this paper. Datasets related to this article can be found at https://www.eia.gov/naturalgas/ngqs/#?report = RP8&year1 = 2016&year2 = 2021&company = Name, an official repository of the U.S. Energy Information Administration (EIA).
Publisher Copyright:
© 2022 The Author(s)
PY - 2022/12/1
Y1 - 2022/12/1
N2 - Numerous subsurface factors, including geology and fluid properties, can affect the connectivity of the storage spaces in depleted reservoirs; hence, fluid flow simulations become more complicated, and predicting their deliverability remains challenging. This paper applies Machine Learning (ML) techniques to predict the deliverability of underground natural gas storage (UNGS) in depleted reservoirs. First, three baseline models were developed based on Support Vector Regression (SVR), Artificial Neural Network (ANN), and Random Forest (RF) algorithms. To improve the accuracy of the RF model as the best-performing baseline model, a unified framework, referred to as SARF, was developed. SARF combines the capabilities of Sparse Autoencoder (SA) and that of Random Forest (RF). To achieve this, the internal representations of the SA, which constitute extracted features of the input variables, are used in RF to develop the proposed SARF framework. The predictive capabilities of the baseline models and the proposed SARF model were validated using 3744 real-world storage data samples of 52 active storage reservoirs in the United States. The experimental result of this study shows that the proposed SARF model achieved an average 5.7% increase in accuracy on four separate data partitions over the baseline RF model. Furthermore, a set of eXplainable Artificial Intelligence (XAI) methods were developed to provide an intuitive explanation of which factors influence the deliverability of reservoir storage. The visualizations developed using the XAI method provide an easy-to-understand interpretation of how the SARF model predicted the deliverability values for separate reservoirs.
AB - Numerous subsurface factors, including geology and fluid properties, can affect the connectivity of the storage spaces in depleted reservoirs; hence, fluid flow simulations become more complicated, and predicting their deliverability remains challenging. This paper applies Machine Learning (ML) techniques to predict the deliverability of underground natural gas storage (UNGS) in depleted reservoirs. First, three baseline models were developed based on Support Vector Regression (SVR), Artificial Neural Network (ANN), and Random Forest (RF) algorithms. To improve the accuracy of the RF model as the best-performing baseline model, a unified framework, referred to as SARF, was developed. SARF combines the capabilities of Sparse Autoencoder (SA) and that of Random Forest (RF). To achieve this, the internal representations of the SA, which constitute extracted features of the input variables, are used in RF to develop the proposed SARF framework. The predictive capabilities of the baseline models and the proposed SARF model were validated using 3744 real-world storage data samples of 52 active storage reservoirs in the United States. The experimental result of this study shows that the proposed SARF model achieved an average 5.7% increase in accuracy on four separate data partitions over the baseline RF model. Furthermore, a set of eXplainable Artificial Intelligence (XAI) methods were developed to provide an intuitive explanation of which factors influence the deliverability of reservoir storage. The visualizations developed using the XAI method provide an easy-to-understand interpretation of how the SARF model predicted the deliverability values for separate reservoirs.
KW - Artificial neural network
KW - Data-driven modeling
KW - Interpretable machine learning
KW - Natural gas industry
KW - Random forests
KW - Support vector regression
UR - http://www.scopus.com/inward/record.url?scp=85140272188&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85140272188&partnerID=8YFLogxK
U2 - https://doi.org/10.1016/j.apenergy.2022.120098
DO - https://doi.org/10.1016/j.apenergy.2022.120098
M3 - Article
AN - SCOPUS:85140272188
SN - 0306-2619
VL - 327
JO - Applied Energy
JF - Applied Energy
M1 - 120098
ER -