Predictive modeling of oil rate for wells under gas lift using machine learning

Abstract Optimizing oil production in wells employing gas lift systems is a critical challenge due to the complex interplay of operational and reservoir parameters. This study aimed to develop robust predictive models for estimating oil production rates using a comprehensive dataset from oil fields...

Full description

Saved in:
Bibliographic Details
Main Authors: Famin Ma, Farag M. A. Altalbawy, Pinank Patel, R. Manjunatha, Rishiv Kalia, Shoira Formanova, P. Raja Naveen, Kamal Kant Joshi, Aashna Sinha, Abdolali Yarahmadi Kandahari, Taqi Mohammed Khattab Al-Rubaye, Mohammad Mahtab Alam
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-12129-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333076113489920
author Famin Ma
Farag M. A. Altalbawy
Pinank Patel
R. Manjunatha
Rishiv Kalia
Shoira Formanova
P. Raja Naveen
Kamal Kant Joshi
Aashna Sinha
Abdolali Yarahmadi Kandahari
Taqi Mohammed Khattab Al-Rubaye
Mohammad Mahtab Alam
author_facet Famin Ma
Farag M. A. Altalbawy
Pinank Patel
R. Manjunatha
Rishiv Kalia
Shoira Formanova
P. Raja Naveen
Kamal Kant Joshi
Aashna Sinha
Abdolali Yarahmadi Kandahari
Taqi Mohammed Khattab Al-Rubaye
Mohammad Mahtab Alam
author_sort Famin Ma
collection DOAJ
description Abstract Optimizing oil production in wells employing gas lift systems is a critical challenge due to the complex interplay of operational and reservoir parameters. This study aimed to develop robust predictive models for estimating oil production rates using a comprehensive dataset from oil fields in south-eastern Iraq, leveraging advanced machine learning techniques. The dataset, comprised of 169 rigorously validated samples, includes key features such as basic sediment and water content, choke size, pressures, gas injection characteristics, gas lift valve depth, oil density, and temperature. Input and output variables were normalized and split into training and test sets to ensure fairness and reliability. Multiple machine learning models (Decision Tree, AdaBoost, Random Forest, Ensemble Learning, CNN, SVR, MLP-ANN, and Lasso Regression) were trained and evaluated using 5-fold cross-validation and key statistical metrics (R², MSE, AARE%). The Random Forest model demonstrated superior performance, achieving a test R² of 0.867 and the lowest prediction errors (MSE: 18502 and AARE: 8.76%) for the testing phase, while other models were prone to overfitting or underfitting. Sensitivity analysis and SHAP interpretability methods revealed that basic sediment and water content, choke size, and upstream pressure had the greatest influence on oil output. These findings underscore the importance of both statistical rigor and model interpretability in oil production forecasting and provide actionable insights for optimizing gas lift operations in oil wells.
format Article
id doaj-art-83dc1c25ef3b4b2eae5ad7b9a57cff5b
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-83dc1c25ef3b4b2eae5ad7b9a57cff5b2025-08-20T03:46:00ZengNature PortfolioScientific Reports2045-23222025-07-0115112610.1038/s41598-025-12129-wPredictive modeling of oil rate for wells under gas lift using machine learningFamin Ma0Farag M. A. Altalbawy1Pinank Patel2R. Manjunatha3Rishiv Kalia4Shoira Formanova5P. Raja Naveen6Kamal Kant Joshi7Aashna Sinha8Abdolali Yarahmadi Kandahari9Taqi Mohammed Khattab Al-Rubaye10Mohammad Mahtab Alam11Shangluo UniversityDepartment of Chemistry, University College of Duba, University of TabukDepartment of Mechanical Engineering, Faculty of Engineering & Technology, Marwadi Universitly Research Center,, Marwadi UniversityDepartment of Data analytics and Mathematical Sciences, School of Sciences, JAIN (Deemed to be University)Centre for Research Impact & Outcome, Chitkara University Institute of Engineering and Technology, Chitkara UniversityDepartment of Chemistry and Its Teaching Methods, Tashkent State Pedagogical UniversityDepartment of Mechanical Engineering, Raghu Engineering CollegeDepartment of Allied Science, Graphic Era Hill UniversitySchool of Applied and Life Sciences, Division of Research and Innovation, Uttaranchal UniversityFaculty of Engineering, Kandahar UniversityDepartment of computers Techniques engineering, College of technical engineering, The Islamic UniversityDepartment of Basic Medical Sciences, College of Applied Medical Science, King Khalid UniversityAbstract Optimizing oil production in wells employing gas lift systems is a critical challenge due to the complex interplay of operational and reservoir parameters. This study aimed to develop robust predictive models for estimating oil production rates using a comprehensive dataset from oil fields in south-eastern Iraq, leveraging advanced machine learning techniques. The dataset, comprised of 169 rigorously validated samples, includes key features such as basic sediment and water content, choke size, pressures, gas injection characteristics, gas lift valve depth, oil density, and temperature. Input and output variables were normalized and split into training and test sets to ensure fairness and reliability. Multiple machine learning models (Decision Tree, AdaBoost, Random Forest, Ensemble Learning, CNN, SVR, MLP-ANN, and Lasso Regression) were trained and evaluated using 5-fold cross-validation and key statistical metrics (R², MSE, AARE%). The Random Forest model demonstrated superior performance, achieving a test R² of 0.867 and the lowest prediction errors (MSE: 18502 and AARE: 8.76%) for the testing phase, while other models were prone to overfitting or underfitting. Sensitivity analysis and SHAP interpretability methods revealed that basic sediment and water content, choke size, and upstream pressure had the greatest influence on oil output. These findings underscore the importance of both statistical rigor and model interpretability in oil production forecasting and provide actionable insights for optimizing gas lift operations in oil wells.https://doi.org/10.1038/s41598-025-12129-wGas liftMachine learningOil production predictionRandom forestSHAP analysis
spellingShingle Famin Ma
Farag M. A. Altalbawy
Pinank Patel
R. Manjunatha
Rishiv Kalia
Shoira Formanova
P. Raja Naveen
Kamal Kant Joshi
Aashna Sinha
Abdolali Yarahmadi Kandahari
Taqi Mohammed Khattab Al-Rubaye
Mohammad Mahtab Alam
Predictive modeling of oil rate for wells under gas lift using machine learning
Scientific Reports
Gas lift
Machine learning
Oil production prediction
Random forest
SHAP analysis
title Predictive modeling of oil rate for wells under gas lift using machine learning
title_full Predictive modeling of oil rate for wells under gas lift using machine learning
title_fullStr Predictive modeling of oil rate for wells under gas lift using machine learning
title_full_unstemmed Predictive modeling of oil rate for wells under gas lift using machine learning
title_short Predictive modeling of oil rate for wells under gas lift using machine learning
title_sort predictive modeling of oil rate for wells under gas lift using machine learning
topic Gas lift
Machine learning
Oil production prediction
Random forest
SHAP analysis
url https://doi.org/10.1038/s41598-025-12129-w
work_keys_str_mv AT faminma predictivemodelingofoilrateforwellsundergasliftusingmachinelearning
AT faragmaaltalbawy predictivemodelingofoilrateforwellsundergasliftusingmachinelearning
AT pinankpatel predictivemodelingofoilrateforwellsundergasliftusingmachinelearning
AT rmanjunatha predictivemodelingofoilrateforwellsundergasliftusingmachinelearning
AT rishivkalia predictivemodelingofoilrateforwellsundergasliftusingmachinelearning
AT shoiraformanova predictivemodelingofoilrateforwellsundergasliftusingmachinelearning
AT prajanaveen predictivemodelingofoilrateforwellsundergasliftusingmachinelearning
AT kamalkantjoshi predictivemodelingofoilrateforwellsundergasliftusingmachinelearning
AT aashnasinha predictivemodelingofoilrateforwellsundergasliftusingmachinelearning
AT abdolaliyarahmadikandahari predictivemodelingofoilrateforwellsundergasliftusingmachinelearning
AT taqimohammedkhattabalrubaye predictivemodelingofoilrateforwellsundergasliftusingmachinelearning
AT mohammadmahtabalam predictivemodelingofoilrateforwellsundergasliftusingmachinelearning