Abstract
Accurate prediction of oil–nitrogen interfacial tension (IFT) is critical for designing efficient enhanced oil recovery (EOR) strategies. Traditional empirical correlations often lack generalizability and demand detailed compositional data, motivating the need for robust machine learning frameworks. In this study, Gradient Boosting Machine (GBM) models were developed and optimized using four metaheuristic algorithms including Artificial Bee Colony (ABC), Particle Swarm Optimization (PSO), Coupled Simulated Annealing (CSA), and Whale Optimization Algorithm (WOA) to predict equilibrium IFT under varying pressures, temperatures, and API gravities. A curated dataset of 148 experimental measurements was validated through outlier detection and evaluated using five-fold cross-validation to ensure generalization. Model performance was assessed using R2, mean squared error (MSE), and average absolute relative error percentage (AARE%). Comparative results demonstrate that the ABC-optimized GBM achieved the highest test R2 and competitive error metrics, outperforming other optimization strategies in predictive reliability. SHAP analysis further confirmed pressure and temperature as the dominant factors influencing IFT, with API gravity exerting a secondary effect. The findings not only establish the ABC-GBM framework as a powerful predictive tool but also reinforce the physical plausibility of the results, offering practical guidance for process optimization in nitrogen-based EOR applications.
Data availability
Data will be available on request from the corresponding author.
References
Mohammadi, M. H., Kulakhmetovna, Y. A. & Joia, R. An overview of oil recovery techniques: from primary to enhanced oil recovery methods. J. Res. Appl. Sci. Biotechnol. 3 (1), 291–301 (2024).
Ozowe, W., Daramola, G. O. & Ekemezie, I. O. Innovative approaches in enhanced oil recovery: A focus on gas injection synergies with other EOR methods. Magna Scientia Adv. Res. Reviews. 11 (1), 311–324 (2024).
Abdulsada, J. A. et al. A mini-review of water-alternating-CO2 injection process and derivations for enhanced oil recovery and CO2 storage in subsurface reservoirs. Petroleum, (2025).
Asare, K., Ejike, C. & Okere, C. J. Numerical evaluation of multi-well cyclic gas injection technique for enhanced oil recovery in composite tight oil reservoirs. Arab. J. Sci. Eng. 50 (7), 5037–5054 (2025).
da Silva Medeiros, D. C. C. et al. Biochar-enhanced removal of naphthenic acids from oil sands process water: Influence of feedstock and chemical activation. Energy Environ. Sustain. 1 (2), 100028 (2025).
Cao, C. et al. A review of CO2 storage in view of safety and cost-effectiveness. Energies 13 (3), 600 (2020).
Jia, Y. et al. Evaluating Nitrogen Gas Injection Performance for Enhanced Oil Recovery in Fractured Basement Complex Reservoirs: Experiments and Modeling Approaches. Processes 13 (2), 326 (2025).
Tileuberdi, N. et al. Optimizing oil recovery by low-pressure nitrogen injection: an experiment case study 25, 1189 (ES Materials & Manufacturing, 2024).
Luo, J. Y. et al. Optimized Nitrogen Foam Flooding System for Enhanced Oil Recovery: Development and Field Test in Mu146 Block Medium-High Permeability Reservoir, China. Energies 18 (5), 1183 (2025).
Gholamzadeh, Y., Hemmati-Sarapardeh, A. & Sharifi, M. Interfacial tension reduction using nitrogen graphene quantum dots with various precursors, molar ratios, and synthesis durations for enhanced oil recovery. Sci. Rep. 14 (1), 31863 (2024).
Zhang, C. et al. Characterization and optimization of oil–gas interfacial tension during CO2/N2 injection in heavy oil reservoirs: Experimental study and regression model. Pet. Sci., (2025).
Gajbhiye, R. Impact of gas composition, pressure, and temperature on interfacial Tension dynamics in CO₂-Enhanced oil recovery. Sci. Rep. 15 (1), 3821 (2025).
Li, X. et al. A thermo-stable polymeric surfactant for enhanced heavy oil recovery via hot water chemical flooding. Langmuir 41 (43), 29180–29195 (2025).
Dai, Q. et al. Carbon-pricing optimization framework for oilfield carbon dioxide-water alternation with economic and environmental gains. Energy. Conv. Manag. 348, 120613 (2026).
Berger Bioucas, F. E., Koller, T. M. & Fröba, A. P. Effective thermal conductivity of nanofluids containing silicon dioxide, titanium dioxide, copper oxide, polystyrene, or polymethylmethacrylate nanoparticles dispersed in water, ethylene glycol, or glycerol. Int. J. Thermophys. 46 (2), 27 (2025).
Koreh, P. et al. Interfacial performance of cationic, anionic and non-ionic surfactants; effect of different characteristics of crude oil. J. Petrol. Sci. Eng. 218, 110960 (2022).
Ramezani, M., Lashkarbolooki, M. & Abedini, R. Experimental investigation of different characteristics of crude oil on the interfacial activity of anionic, cationic and nonionic surfactants mixtures. J. Petrol. Sci. Eng. 214, 110485 (2022).
Jia, H. et al. Mechanism studies on the application of the mixed cationic/anionic surfactant systems to enhance oil recovery. Fuel 258, 116156 (2019).
Shen, J. et al. Estimation of nitrogen-crude oil interfacial tension: Application of hybrid machine learning algorithms, 104056 (Physics and Chemistry of the Earth, 2025).
Obaidur Rab, S. et al. Machine learning-based estimation of crude oil-nitrogen interfacial tension. Sci. Rep. 15 (1), 1037 (2025).
Xie, M., Zhang, M. & Jin, Z. Machine learning-based interfacial tension equations for (H2 + CO2)-water/brine systems over a wide range of temperature and pressure. Langmuir 40 (10), 5369–5377 (2024).
Nsiah Turkson, J. et al. Harnessing Ensemble Learning Techniques for Accurate Interfacial Tension Estimation in Aqueous CO2 Systems. SPE. (2024).
Fan, J. et al. Enhanced Prediction of CO2–Brine Interfacial Tension at Varying Temperature Using a Multibranch-Structure-Based Neural Network Approach. Langmuir 41 (3), 1587–1600 (2025).
Rezaei, F. et al. On the evaluation of interfacial tension (IFT) of CO2–paraffin system for enhanced oil recovery process: comparison of empirical correlations, soft computing approaches, and parachor model. Energies 14 (11), 3045 (2021).
Karami, M., Behnamnia, M. & Monfared, A. D. From Empirical to Intelligent: ML-Enhanced Parachor Modeling of Gas (H2, CO2, CH4, and N2)–Water Interfacial Tension for Applications in Energy Storage and Carbon Sequestration. Results in Engineering, 107554 (2025).
Alatefi, S. et al. Explainable advanced modelling of interfacial tension in H2–CO2–CH4–brine systems for sustainable subsurface storage in saline aquifer. J. Contam. Hydrol. 104827, p (2025).
Ren, D. et al. Harmonizing physical and deep learning modeling: A computationally efficient and interpretable approach for property prediction. Scripta Mater. 255, 116350 (2025).
Wang, C. et al. Sequential construction of stable nitrogen–oxygen compounds using high-throughput quantum mechanical calculations and customized machine learning model. J. Mater. Chem. A, (2025).
Alatefi, S. et al. Accurate prediction of water activity in ionic liquid-based aqueous ternary solutions using advanced explainable artificial intelligence frameworks. Chem. Eng. Sci. 318, 122218 (2025).
Zheng, M. et al. Optimization of microcrack control and performance in deepwater well cementing with microencapsulated phase change materials. Geoenergy Sci. Eng. 214220 (2025).
Zheng, W. et al. GEP-DNN4Mol: automatic chemical molecular design based on deep neural networks and gene expression programming. Health Inform. Sci. Syst. 13 (1), 31 (2025).
Bakary, K., Mouhamadou, D. & Seydou, T. Contribution Based on Neurons Networks for the Prediction of Greenhouse Gas Emissions in a Handling Port. Asian J. Water Environ. Pollut. 21 (6), 261–269 (2024).
Alatefi, S. et al. Advancing hydrogen storage: Explainable machine learning models for predicting hydrogen uptake in metal-organic frameworks. Results Eng. 107304 (2025).
Wang, Y. et al. A Data Augmentation Method for Establishing a Relationship Model Between Composition and Viscoelastic Properties of Asphalt Binder (IEEE Transactions on Intelligent Transportation Systems, 2025).
Qian, Y. et al. Enhanced Protein Secondary Structure Prediction Through Multi-View Multi-Feature Evolutionary Deep Fusion Method (IEEE Transactions on Emerging Topics in Computational Intelligence, 2025).
Hemmati-Sarapardeh, A. et al. Experimental determination of equilibrium interfacial tension for nitrogen-crude oil during the gas injection process: the role of temperature, pressure, and composition. J. Chem. Eng. Data. 59 (11), 3461–3469 (2014).
Bayat, M. et al. Investigation of gas injection flooding performance as enhanced oil recovery method. J. Nat. Gas Sci. Eng. 29, 37–45 (2016).
Awari-Yusuf, I. O. Measurement of crude oil interfacial tension to determine minimum miscibility in carbon dioxide and nitrogen [MS thesis]. Dalhousie University, Halifax, Canada. (2013).
Heidary, S., Dehghan, A. A. & Zamanzadeh, S. M. A comparative study of the carbon dioxide and nitrogen minimum miscibility pressure determinations for an Iranian light oil sample. Energy Sour. Part A Recover. Utilization Environ. Eff. 38 (15), 2217–2224 (2016).
Bahralolom, I. M. & Orr, F. M. Solubility and extraction in multiple-contact miscible displacements: comparison of N2 and CO2 flow visualization experiments. SPE. Reserv. Eng. 3 (01), 213–219 (1988).
Lu, T. et al. Flow behavior of N2 huff and puff process for enhanced oil recovery in tight oil reservoirs. Sci. Rep. 7 (1), 15695 (2017).
Rofatto, V. F. et al. A Monte Carlo-based outlier diagnosis method for sensitivity analysis. Remote Sens. 12 (5), 860 (2020).
Tama, B. A. & Rhee, K. H. An in-depth experimental study of anomaly detection using gradient boosted machine. Neural Comput. Appl. 31 (4), 955–965 (2019).
Yang, F. Clustering by Gaussian Mixture Model and Light Gradient Boosting Machine. (2024).
Author information
Authors and Affiliations
Contributions
All authors contributed to this paper.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Abushuhel, M., Mohammad, H., Rao P S, R. et al. Pioneering oil and nitrogen interfacial tension using evolutionarily optimized gradient boosting machine. Sci Rep (2026). https://doi.org/10.1038/s41598-026-43758-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-43758-4
