Smart predictions of petrophysical formation pore pressure via robust data-driven intelligent models
Publikationen: Beitrag in Fachzeitschrift › Artikel › Forschung › (peer-reviewed)
Standard
in: Multiscale and multidisciplinary modeling, experiments and design, Jahrgang 7.2024, Nr. 6, 24.07.2024, S. 5611-5630.
Publikationen: Beitrag in Fachzeitschrift › Artikel › Forschung › (peer-reviewed)
Harvard
APA
Vancouver
Author
Bibtex - Download
}
RIS (suitable for import to EndNote) - Download
TY - JOUR
T1 - Smart predictions of petrophysical formation pore pressure via robust data-driven intelligent models
AU - Krishna, Shwetank
AU - Irfan, Sayed Ameenuddin
AU - Keshavarz, Sahar
AU - Thonhauser, Gerhard
AU - Umer Ilyas, Suhaib
N1 - Publisher Copyright: © The Author(s) 2024.
PY - 2024/7/24
Y1 - 2024/7/24
N2 - Predicting pore pressure in the formation is crucial for assessing reservoir geomechanical characteristics, designing drilling schemes/mud programs, and strategies to enhance oil recovery. Accurate predictions are vital for safe and cost-effective exploration and development. Recent research has seen the emergence of intelligent models utilizing machine learning (ML) and deep learning (DL) algorithms, offering promising outcomes. However, there remains a need to identify the most accurate and dependable model among these. This study aims to address this gap by comparing the performance of various ML and DL models, as reported in existing literature, to determine the optimal approach for pore pressure prediction. The sorted machine learning (ML) and deep learning (DL) regression algorithms used for the comparative analysis are decision tree (DT), extreme gradient boosting (XGBoost), random forest (RF), recurrent neural network (RNN), and convolutional neural network (CNN). A total dataset of 22,539 is gathered from five wells (15/9-F-1 A, 15/9-F-1 B, 15/9-F-11 A, 15/9-F-11 T2, and 15/9-F-14) drilled at North-sea Volve oil field, Norway. The first four wells are used to train and test the ML and DL algorithm, and the remaining well (15/9-F-14) is used to evaluate the best-performing algorithm’s universality in predicting pore pressure at the field of study. Seven different petrophysical parameters are used as input parameters to develop the predictive models. Statistical performance metrics are carried out to analyze the applied ML and DL performance. Based on performance indicators, the RF algorithm showed superior results compared to other predictive models with R 2 and RMSE values of 0.97 and 2.70 MPa, respectively. Furthermore, the best-performing predictive model with low prediction error RMSE value is applied to the other well dataset from the field of study to access the universality of the RF algorithm to predict pore pressure in the field of study. The results of the universality analysis show a satisfactory prediction accuracy with R 2 and RMSE values of 0.905 and 6.48 MPa, respectively.
AB - Predicting pore pressure in the formation is crucial for assessing reservoir geomechanical characteristics, designing drilling schemes/mud programs, and strategies to enhance oil recovery. Accurate predictions are vital for safe and cost-effective exploration and development. Recent research has seen the emergence of intelligent models utilizing machine learning (ML) and deep learning (DL) algorithms, offering promising outcomes. However, there remains a need to identify the most accurate and dependable model among these. This study aims to address this gap by comparing the performance of various ML and DL models, as reported in existing literature, to determine the optimal approach for pore pressure prediction. The sorted machine learning (ML) and deep learning (DL) regression algorithms used for the comparative analysis are decision tree (DT), extreme gradient boosting (XGBoost), random forest (RF), recurrent neural network (RNN), and convolutional neural network (CNN). A total dataset of 22,539 is gathered from five wells (15/9-F-1 A, 15/9-F-1 B, 15/9-F-11 A, 15/9-F-11 T2, and 15/9-F-14) drilled at North-sea Volve oil field, Norway. The first four wells are used to train and test the ML and DL algorithm, and the remaining well (15/9-F-14) is used to evaluate the best-performing algorithm’s universality in predicting pore pressure at the field of study. Seven different petrophysical parameters are used as input parameters to develop the predictive models. Statistical performance metrics are carried out to analyze the applied ML and DL performance. Based on performance indicators, the RF algorithm showed superior results compared to other predictive models with R 2 and RMSE values of 0.97 and 2.70 MPa, respectively. Furthermore, the best-performing predictive model with low prediction error RMSE value is applied to the other well dataset from the field of study to access the universality of the RF algorithm to predict pore pressure in the field of study. The results of the universality analysis show a satisfactory prediction accuracy with R 2 and RMSE values of 0.905 and 6.48 MPa, respectively.
KW - Deep learning
KW - Machine learning
KW - Petrophysical properties
KW - Pore pressure
KW - Prediction
UR - http://www.scopus.com/inward/record.url?scp=85199358804&partnerID=8YFLogxK
U2 - 10.1007/s41939-024-00542-z
DO - 10.1007/s41939-024-00542-z
M3 - Article
VL - 7.2024
SP - 5611
EP - 5630
JO - Multiscale and multidisciplinary modeling, experiments and design
JF - Multiscale and multidisciplinary modeling, experiments and design
SN - 2520-8179
IS - 6
ER -