Data-Driven Interfacial Tension Modeling of Quaternary Aqueous H2 Systems Using Sequential and Parallel Ensemble Learning Techniques and the Implications on H2 Geo-Storage DOI
Joshua Nsiah Turkson, Bennet Nii Tackie-Otoo, Victor Darkwah-Owusu

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

Multi-model environmental modelling of energy-exergy efficiency using GUI-based aided design tools integrated with dependency feature analysis DOI Creative Commons
Ismail A. Mahmoud,

Abubakar D. Maiwada,

Sagir Jibrin Kawu

и другие.

Hybrid Advances, Год журнала: 2025, Номер unknown, С. 100493 - 100493

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0

Optimized SVR with nature-inspired algorithms for environmental modelling of mycotoxins in food virtual-water samples DOI Creative Commons
A. G. Usman, Sagiru Mati, Hanita Daud

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 13, 2025

The accurate determination of mycotoxins in food samples is crucial to guarantee safety and minimize their toxic effects on human animal health. This study proposed the use a support vector regression (SVR) predictive model improved by two metaheuristic algorithms used for optimization namely, Harris Hawks Optimization (HHO) Particle Swarm (PSO) predict chromatographic retention time various mycotoxin groups. dataset was collected from secondary sources train validate SVR-HHO SVR-PSO models. performance models assessed via mean square error, correlation coefficient, Nash-Sutcliffe efficiency. outperformed existing methods 4-7% both learning (training testing) phases respectively. By using optimization, parameter adjustment became more effective, avoiding trapping local minima improving generalization. These results demonstrate how machine metaheuristics may be combined accurately forecast levels, providing useful tool regulatory compliance monitoring. framework perfect commercial quality assurance, testing, extensive programs because it provides exceptional accuracy resilience predicting times. In contrast conventional models, effectively manages intricate nonlinear interactions, guaranteeing identification while lowering hazards

Язык: Английский

Процитировано

0

A novel algorithm for modeling gas–oil dynamic interfacial tension (IFT) and component exchange mechanisms DOI Creative Commons
Ali Safaei,

Masoud Riazi

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 30, 2025

Interfacial tension (IFT) between two immiscible phases is a key parameter in various oil and gas industries, especially enhanced recovery Carbon dioxide capture storage. There are several laboratory methods for measuring IFT, of which the pendant drop method one most commonly used. This can be used both thermodynamic equilibrium dynamic approaches. For more complete study modeling to investigate process component exchange determine mechanism equilibrium. this purpose, novel computational algorithm presented that calculates IFT under (non-thermodynamic equilibrium) conditions at different time intervals, where each step separately considered Vapor-liquid calculations were performed using Peng-Robinson equation state (PR-EOS), was calculated Parachor model. The power proposed model also matching fit experimental data. Over time, increases, thereby reducing IFT. decreasing continues until it reaches constant (thermodynamic value. In step, exchangeable components calculated, their transfer directions determined. results show rate differed any time. However, intermediate intense beginning experiment, but gradually, as passed exchanged phases, decreased. ultimately reduces average molecular weight viscosity over goals injecting into reservoirs. Therefore, changes composition gas, well properties oil, reach two-phase paper, decreased by an approximately 31% compared first contact due exchange. mass about 39% 23%, respectively. These justify use rich injection because increase mobility during process. Thus, effectively studies reservoirs accurately identify mechanisms reservoir conditions.

Язык: Английский

Процитировано

0

Advanced generalized machine learning models for predicting hydrogen–brine interfacial tension in underground hydrogen storage systems DOI Creative Commons
Ahmed Farid Ibrahim

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 30, 2025

The global transition to clean energy has highlighted hydrogen (H2) as a sustainable fuel, with underground storage (UHS) in geological formations emerging key solution. Accurately predicting fluid interactions, particularly interfacial tension (IFT), is critical for ensuring reservoir integrity and security UHS. IFT behavior, influencing structural residual trapping capacities. However, measuring H2-brine systems challenging due H2's volatility the complexity of conditions. This study applies machine learning (ML) techniques predict between H2 brine across various salt types, concentrations, gas compositions. A dataset was used variables such temperature, pressure, salinity, composition (H2, CH4, CO2). Several ML models, including Random Forests (RF), Gradient Boosting Regressor (GBR), Extreme (XGBoost), Artificial Neural Networks (ANN), Decision Trees (DT), Linear Regression (LR), were trained evaluated. RF, GBR, XGBoost achieved R2 values over 0.99 training, 0.97 testing, all exceeded 0.975 validation. These top models RMSE below 1.3 mN/m MAPE under 1.5%, confirming their high predictive accuracy. Residual frequency analysis APRE results further confirmed these ensemble models' low bias reliability, error distributions centered near zero. DT performed slightly lower, 0.93, while LR struggled model non-linear behavior IFT. novel equivalency metric introduced, transforming multiple into single parameter improving generalization maintaining prediction accuracy (R2 = 0.98). Sensitivity SHAP (Shapley Additive Explanations) revealed temperature dominant factor IFT, followed by CO2 concentration divalent salts (CaCl2, MgCl2) exhibited stronger impact than monovalent (NaCl, KCl). optimizes offering generalized, high-accuracy that captures nonlinear interactions systems. Integrating real-world experimental data ML-driven insights enhances simulation accuracy, improves injection strategies, supports toward solutions.

Язык: Английский

Процитировано

0

Data-Driven Interfacial Tension Modeling of Quaternary Aqueous H2 Systems Using Sequential and Parallel Ensemble Learning Techniques and the Implications on H2 Geo-Storage DOI
Joshua Nsiah Turkson, Bennet Nii Tackie-Otoo, Victor Darkwah-Owusu

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

2