conference paper · SPE Nigeria Annual International Conference and Exhibition
This study addresses the subjectivity and time-intensive nature of conventional history-matching methods, which lead to uncertainty in production forecasting for the Rio Del Rey Basin. A machine learning-enhanced framework was developed using Python to improve forecast accuracy. Production data from two wells were preprocessed, and various machine learning models were trained and evaluated against decline curve analysis. For Well-101S5D, a Random Forest Regressor significantly outperformed traditional methods. For Well-102, while a hyperbolic decline curve analysis showed strong results, machine learning provided a more consistent and automated workflow. The integration of machine learning improves forecast accuracy, objectivity, repeatability, and efficiency, offering a practical and scalable approach for complex basins.
Accurate prediction of oil and gas production is vital for managing reservoirs and making sound economic decisions. This research offers a more reliable and efficient way to forecast production, reducing uncertainties associated with traditional methods. This can lead to better resource allocation and financial planning for energy companies operating in complex basins.
This research presents an applied, tested framework for improving oil and gas production forecasting. It could be used by reservoir engineers and energy companies to enhance decision-making in reservoir management and economic evaluation. The workflow is described as practical and scalable, suggesting it is near-market for integration into existing industry software or proprietary systems for complex basins.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Accurate production forecasting is critical for reservoir management and economic evaluation, yet conventional history-matching methods are subjective and time intensive, which can increase uncertainty in the Rio Del Rey (RDR) Basin. This study develops an ML-enhanced history-matching framework to improve production forecast accuracy for wells in the basin. Using Python in a Jupyter Notebook, production data from Well-101S5D and Well-102 were preprocessed, including the imputation of 39 missing values for Well-101S5D. Data were split into 80% training and 20% testing sets. The following ML models were trained and evaluated—Linear Regression (LR), Random Forest Regressor (RFR), XGBoost, Prophet, and LSTM—and their forecasts were compared with decline curve analysis (DCA) models. The selected models were RFR for Well-101S5D and LR for Well-102. ML predictions produced EUR estimates of 0.3269 MMbbl (Well-101S5D) and 0.1274 MMbbl (Well-102). For Well-101S5D, RFR outperformed DCA models (RFR: MSE = 3766.65, MAE = 36.83, R2 = 0.6901; DCA: MSE = 750740.32, MAE = 630.74, R2 = 0.3948). For Well-102, the hyperbolic DCA achieved a strong R2 (0.8055), while ML provided a more consistent and automated workflow. Overall, integrating ML into history matching improves forecast accuracy while increasing objectivity, repeatability, and efficiency. The proposed workflow provides a practical and scalable approach for other complex basins where data-driven history matching is not widely documented.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.2118/235151-ms
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
