Scaled Conjugate Gradient Research Articles

Dijagnostika kvarova u ležajevima kotrljajućih elemenata poboljšana AI - sveobuhvatan pristup analizi vibracija

This research presents a comprehensive approach for bearing fault diagnosis using artificial intelligence (AI), particularly through the application of artificial neural networks (ANNs). By integrating these networks into vibration analysis, the approach aims to meet the critical need for prompt fault detection. The methodology comprises three key steps: vibration signal acquisition, feature extraction, and fault classification. Experiments were conducted to acquire vibration signals for the test bearings on a machinery fault simulator. Six time-domain features were extracted using MATLAB, creating a comprehensive dataset for training the ANN models with three algorithms: Levenberg-Marquardt backpropagation (LMBP), scaled conjugate gradient backpropagation (SCGBP), and Bayesian regularization backpropagation (BRBP). The BRBP algorithm achieved the highest correct classification rate (97.2%), followed by LMBP (90%) and SCGBP (83.6%). To evaluate their efficacy in bearing fault classification, these three networks were simulated, revealing that BRBP could predict all four classes of bearings with zero errors.

A descent scaled conjugate gradient method for unconstrained optimization with its applications in image restoration problems

Based on combining the conjugate gradient method proposed by Hager and Zhang with the scaled gradient idea, we presented a new scaled conjugate gradient method which satisfies the sufficient descent condition. In our method, the scaled parameter is determined so that the search direction becomes close to the three-term HS method suggested by Zhang, Zhou and Li. It is proved that the new method is globally convergent for general nonlinear functions, under some standard assumptions. Numerical comparisons on some test problems from the CUTEst library and image restoration problems illustrate the efficiency and robustness of our proposed method in practice.

Effectiveness and number of transfer units of plate heat exchanger with Fe3O4–SiO2/Water hybrid nanofluids: Experimental and artificial neural network predictions

This paper analyses the effectiveness and number of transfer units of water dispersed Fe3O4–SiO2 hybrid fluids passing via plate heat exchanger experimentally. The flow of Fe3O4–SiO2/water hybrid nanofluids in plate heat exchanger remains the laminar flow conditions. The experimental studies were carried out with particle loadings ranging from 0.2 % to 1.0 % and flow rates ranging from 0.05 kg/s to 0.1166 kg/s. The obtained results of effectiveness and number of transfer units from these experiments were predicted with artificial neural network based scaled conjugate gradient (SCG) method. Based on the chemical reaction and in-situ growth methods, the Fe3O4–SiO2 nanoparticles were prepared and then characterized using x-ray diffraction (XRD) and vibrating sample magnetometer (VSM) equipment. Water diluted hybrid nanofluids were developed and used for the experimental studies. Results from the XRD indicates that, the particle size of synthesized Fe3O4–SiO2 nanoparticles were found to be 47 nm and the results from VSM shows, the final Fe3O4–SiO2 sample contains 67.8 % of SiO2 and 32.2 % of Fe3O4. Results also indicates with an increase of volume loadings and Reynolds number, the effectiveness and number of transfer units were enhanced. The effectiveness and number of transfer units were increased by 13.23 % and 24.51 % at 1.0 % vol. of hybrid nanofluid and at a Reynolds number of 571.89, over water data. Through the SCG method, the correlation coefficient R2 for effectiveness is 0.99040, and the R2 for number of transfer units is 0.98771, respectively. New generalized equation was proposed for the evaluation of effectiveness and number of transfer units.

A scale conjugate neural network approach for the fractional schistosomiasis disease system

This study presents the numerical solutions of the fractional schistosomiasis disease model (SDM) using the supervised neural networks (SNNs) and the computational scaled conjugate gradient (SCG), i.e. SNNs-SCG. The fractional derivatives are used for the precise outcomes of the fractional SDM. The preliminary fractional SDM is categorized as: uninfected, infected with schistosomiasis, recovered through infection, expose and susceptible to this virus. The accurateness of the SNNs-SCG is performed to solve three different scenarios based on the fractional SDM with synthetic data obtained with fractional Adams scheme (FAS). The generated data of FAS is used to execute SNNs-SCG scheme with 81% for training samples, 12% for testing and 7% for validation or authorization. The correctness of SNNs-SCG approach is perceived by the comparison with reference FAS results. The performances based on the error histograms (EHs), absolute error, MSE, regression, state transitions (STs) and correlation accomplish the accuracy, competence, and finesse of the SNNs-SCG scheme.

An artificial neural network approach for the language learning model

The current study provides the numerical solutions of the language-based model through the artificial intelligence (AI) procedure based on the scale conjugate gradient neural network (SCJGNN). The mathematical learning language differential model is characterized into three classes, named as unknown, familiar, and mastered. A dataset is generalized by using the performance of the Adam scheme, which is used to reduce to mean square error. The AI based SCJGNN procedure works by taking the data with the ratio of testing (12%), validation (13%), and training (75%). An activation log-sigmoid function, twelve numbers of neurons, SCJG optimization, hidden and output layers are presented in this stochastic computing work for solving the learning language model. The correctness of AI based SCJGNN is noted through the overlapping of the results along with the small calculated absolute error that are around 10–06 to 10–08 for each class of the model. Moreover, the regression performances for each case of the model is performed as one that shows the perfect model. Additionally, the dependability of AI based SCJGNN is approved using the histogram, and function fitness.

Estimating PM2.5 utilizing multiple linear regression and ANN techniques

The accurate prediction of air pollutants, particularly Particulate Matter (PM), is critical to support effective and persuasive air quality management. Numerous variables influence the prediction of PM, and it's crucial to combine the most relevant input variables to ensure the most dependable predictions. This study aims to address this issue by utilizing correlation coefficients to select the most pertinent input and output variables for an air pollution model. In this work, PM2.5 concentration is estimated by employing concentrations of sulfur dioxide, nitrogen dioxide, and PM10 found in the air through the application of Artificial Neural Networks (ANNs). The proposed approach involves the comparison of three ANN models: one trained with the Levenberg–Marquardt algorithm (LM-ANN), another with the Bayesian Regularization algorithm (BR-ANN), and a third with the Scaled Conjugate Gradient algorithm (SCG-ANN). The findings revealed that the LM-ANN model outperforms the other two models and even surpasses the Multiple Linear Regression method. The LM-ANN model yields a higher R2 value of 0.8164 and a lower RMSE value of 9.5223.

A Quadratic Model based Conjugate Gradient Optimization Method

In this paper, we introduce a nonlinear scaled conjugate gradient method, operating on the premise of a descent and conjugacy relationship. The proposed algorithm employs a conjugacy parameter that is determined to ensure that the method generates conjugate directions. It also utilizes a parameter that scales the gradient to enhance the convergence behavior of the method. The derived method not only exhibits the crucial feature of global convergence but also maintains the generation of descent directions. The efficiency of the method is established through numerical tests conducted on a variety of high-dimensional nonlinear test functions. The obtained results attest to the improved behavior of the derived algorithm and support the presented theory.

Investigating the effect of textural properties on CO2 adsorption in porous carbons via deep neural networks using various training algorithms

The adsorption of carbon dioxide (CO2) on porous carbon materials offers a promising avenue for cost-effective CO2 emissions mitigation. This study investigates the impact of textural properties, particularly micropores, on CO2 adsorption capacity. Multilayer perceptron (MLP) neural networks were employed and trained with various algorithms to simulate CO2 adsorption. Study findings reveal that the Levenberg–Marquardt (LM) algorithm excels with a remarkable mean squared error (MSE) of 2.6293E−5, indicating its superior accuracy. Efficiency analysis demonstrates that the scaled conjugate gradient (SCG) algorithm boasts the shortest runtime, while the Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm requires the longest. The LM algorithm also converges with the fewest epochs, highlighting its efficiency. Furthermore, optimization identifies an optimal radial basis function (RBF) network configuration with nine neurons in the hidden layer and an MSE of 9.840E−5. Evaluation with new data points shows that the MLP network using the LM and bayesian regularization (BR) algorithms achieves the highest accuracy. This research underscores the potential of MLP deep neural networks with the LM and BR training algorithms for process simulation and provides insights into the pressure-dependent behavior of CO2 adsorption. These findings contribute to our understanding of CO2 adsorption processes and offer valuable insights for predicting gas adsorption behavior, especially in scenarios where micropores dominate at lower pressures and mesopores at higher pressures.

The Predictive Power of Macroeconomic Variables on the Indian Stock Market Utilizing an Ann Model Approach: An Empirical Investigation Based on BSE Sensex

Abstract Research background The paper focuses on the use of Artificial Neural Networks (ANNs) for forecasting time series data of the stock market since ANNs are dynamic and are more capable of handling complex data sets in comparison to conventional forecasting techniques such as regression, Logistic regression, and have massive potential for the prediction of stock market prices. Purpose Artificial neural networks are an effective method for forecasting time series. Therefore, this study aims to forecast the closing price of the BSE Sensex using artificial neural networks (ANNs). Research methodology The study uses nine input variables, including macroeconomic and global stock market factors, to estimate the BSE Sensex using scaled conjugate gradient algorithm artificial neural networks (SCGANNs) and Bayesian regularized artificial neural networks (BRANN). Results As per the empirical results of the study, the ANN model can forecast the closing values of the BSE Sensex with a Bayesian Regularization (BR) method with an accuracy of over 99 percent, thus leading to significant implications for domestic institutional investors (DIIs), foreign institutional investors (FIIs), investment houses, and so on. This study adds more value to the existing literature by proving that the BRANN models outperform SCGANN in stock market forecasting. Novelty This is the first study to employ macroeconomic variables as input variables for predicting the Indian stock market using ANN. The study highlights the ANN model’s forecasting potential, giving investors robust and accurate stock value prediction capabilities.

Biodiesel production from waste cat fish oil using heterogeneous catalyst from cat fish born: A viable waste management approach, and ANN modeling of biodiesel yield

Biodiesel from vegetable or animal feedstock can serve as a suitable source for renewable energy. This study utilized heterogeneous catalyst obtained from fish bone for biodiesel production from raw cat fish waste (CFW) oil. The CFW oil yield obtained using wet reduction extraction method was 96.85 %. The heterogeneous catalyst was prepared by calcination at 600 °C, for 4 h and characterized using SEM-EDX. Catalyst characterization showed suitable elements that can improve the catalytic activity. Physiochemical characterization results showed that viscosity of CFW oil (48.782 mm2/s), reduced to 9.391 mm2/s in the produced biodiesel. Similarly, after transesterification free fatty acid (3.593 mg/KOH/Kg) and acid value (7.186 mg/KOH/Kg) of CFW oil reduced to 1.48 mg/KOH/Kg and 2.96 mg/KOH/Kg, respectively, in the biodiesel. Finding from the Fourier Transform Infrared (FTIR) Spectrum of the raw CFW oil showed the presence of –OH and was assigned to the axial deformation of water molecule. However, the –OH group disappeared in the FTIR spectrum of biodiesel due to the transesterification process. This observation is consistent with the findings for moisture contents of raw CFW oil (0.073 %) and biodiesel (0.00 %), which showed disappearance of water after transesterification. The biodiesel yield was further modeled using three algorithms (Scaled conjugate gradient, Bayesian regularization and Levenberg maraquardt) of the artificial neural network (ANN). It was evident that the predictions from the Scaled conjugate gradient algorithm were comparable to the experimental responses. Finally, transesterification of raw CFW oil using heterogeneous catalyst from fish bone, was a cost-effective approach for biodiesel production.

Comparison of the first four weak and moderate geomagnetic storms of the 2022 using artificial neural networks

Solar wind parameters (SWP) and geomagnetic indices act as defining factors between the Earth's magnetosphere-ionosphere and the Sun. Models between SWP and indices should be examined seriously to better interpret the dynamics of geomagnetic storms (GSs). This work touches on the first two weak (25 January and 22 February) and moderate (14 January and 13 March) GSs of the 2022 year with an artificial neural network (ANN) model. The models are based on SWP (E, v, P, T, N, Bz) and geomagnetic indices (Dst, Kp, ap). The ANN employs SWP as inputs and indices as outputs, predicting the indices via SWP. The Scaled Conjugate Gradient (trainscg) algorithm is used for the back-propagation iteration. Four different geomagnetic storms, which are weak; Dst = -35 nT (25 January), Dst = –32 nT (22 February), and moderate storms; Dst = -91 (14 January) nT, Dst = -85 nT (13 March), are considered as case studies. The results of the estimations have acceptable accuracy. While the model is trained with mean square error (MSE) loss function, the accuracy of the model is evaluated by both mean square error (MSE) and mean error (ME).

Artificial intelligence-based framework for precise prediction of asphaltene particle aggregation kinetics in petroleum recovery

The precipitation and deposition of asphaltene on solid surfaces present a significant challenge throughout all stages of petroleum recovery, from hydrocarbon reservoirs in porous media to wellbore and transfer pipelines. A comprehensive understanding of asphaltene aggregation phenomena is crucial for controlling deposition issues. In addition to experimental studies, accurate prediction of asphaltene aggregation kinetics, which has received less attention in previous research, is essential. This study proposes an artificial intelligence-based framework for precisely predicting asphaltene particle aggregation kinetics. Different techniques were utilized to predict the asphaltene aggregate diameter as a function of pressure, temperature, oil specific gravity, and oil asphaltene content. These methods included the adaptive neuro-fuzzy interference system (ANFIS), radial basis function (RBF) neural network optimized with the Grey Wolf Optimizer (GWO) algorithm, extreme learning machine (ELM), and multi-layer perceptron (MLP) coupled with Bayesian Regularization (BR), Levenberg–Marquardt (LM), and Scaled Conjugate Gradient (SCG) algorithms. The models were constructed using a series of published data. The results indicate the excellent correlation between predicted and experimental values using various models. However, the GWO-RBF modeling strategy demonstrated the highest accuracy among the developed models, with a determination coefficient, average absolute relative deviation percent, and root mean square error (RMSE) of 0.9993, 1.1326%, and 0.0537, respectively, for the total data.

Optimizing buckling load of sandwich plates with cutouts using artificial neural networks and genetic algorithms

In this research, the optimization of the geometric parameters of a 3-layer composite plate with an elliptical cutout in the center was investigated utilizing an artificial neural network and genetic algorithm for the first time to obtain the minimum ratio of linear buckling load to weight and the ratio of the diameters of the ellipse. After completing 294 simulations in Abaqus finite element software and forming an artificial neural network with two hidden layers, the function obtained in the artificial neural network was used as the objective function in the genetic algorithm, and the optimal values for the angle of the ellipse with the horizon axis, the diameter ratio of ellipses as well as the fiber angle of the middle layer of the composite were obtained. using artificial neural networks, three algorithms, Levenberg-Marquardt, Bayesian regularization; and scaled conjugate gradient backpropagation, were compared and the number of neurons in each algorithm was compared. The results showed that Levenberg-Marquardt’s algorithm is more accurate compared to other algorithms. In the end, the optimal values for the angle of the ellipse with the horizontal axis; as the fiber angle of the middle layer of the composite and, the ratio of the oval diameters as α = 12.3001 degree , θ = 5.9481 degree and D = 1.5690 .

An Artificial Neural Network for Predicting Groundnut Yield Using Climatic Data

Groundnut, being a widely consumed oily seed with significant health benefits and appealing sensory profiles, is extensively cultivated in tropical regions worldwide. However, the yield is substantially impacted by the changing climate. Therefore, predicting stressed groundnut yield based on climatic factors is desirable. This research focuses on predicting groundnut yield based on several combinations of climatic factors using artificial neural networks and three training algorithms. The Levenberg–Marquardt, Bayesian Regularization, and Scaled Conjugate Gradient algorithms were evaluated for their performance using climatic factors such as minimum temperature, maximum temperature, and rainfall in different regions of Sri Lanka, considering the seasonal variations in groundnut yield. A three-layer neural network was employed, comprising a hidden layer. The hidden layer consisted of 10 neurons, and the log sigmoid functions were used as the activation function. The performance of these configurations was evaluated based on the mean squared error and Pearson correlation. Notable improvements were observed when using the Levenberg–Marquardt algorithm as the training algorithm and applying the natural logarithm transformation to the yield values. These improvements were evident through the higher Pearson correlation values for training (0.84), validation (1.00) and testing (1.00), and a lower mean squared error (2.2859 × 10−21) value. Due to the limited data, K-Fold cross-validation was utilized for optimization, with a K value of 5 utilized for the process. The application of the natural logarithm transformation to the yield values resulted in a lower mean squared error (0.3724) value. The results revealed that the Levenberg–Marquardt training algorithm performs better in capturing the relationships between the climatic factors and groundnut yield. This research provides valuable insights into the utilization of climatic factors for predicting groundnut yield, highlighting the effectiveness of the training algorithms and emphasizing the importance of carefully selecting and expanding the climatic factors in the modeling equation.

Prediction of Surface Roughness of Monel k 500 Super Alloy by Using Artificial Neural Network

The surface roughness is a feature that is of tremendous relevance in the assessment of cutting performance, and it plays an essential part in the manufacturing process as well. In this research, an effort was made to construct a model based on artificial neural networks to replicate the hard turning of Monel K 500 in dry conditions. The results of this endeavor are presented. This model is anticipated to accurately estimate the surface roughness for various cutting settings. Networks that use Scaled Conjugate Gradient (SCG) were trained using a set of training data for several cycles. Then they were tested with a collection of input/output data that was specifically reserved for this purpose. For each of the designs that were considered, the root mean square error was calculated. As compared with other models, the RMSE that the SCG Produces better value-. Analysis was done on the ability of the ANN model to predict surface roughness (Ra). It was discovered that the predictions produced by the ANN model had a high degree of congruence with the experiment’s findings.

Integrated process for simulation of gasification and chemical looping hydrogen production using Artificial Neural Network and machine learning validation

A significant driver of global warming is fast growth in greenhouse gas (GHG) generated by energy-producing areas. Converting biomass into useful products, chemical looping gasification is an appropriate route. Using integrated steam gasification technology that utilizes a chemical looping method to produce hydrogen. Mn-, Ni-, and Ca-based materials are the three types of oxygen carriers (OC), and they are utilized. This process offers the syngas, in the greatest quality and quantity, which is a key factor. We consider that the optimum gasifier temperature is 1100 °C. The steam-to-biomass ratio is 0.95, if the steam is further increased then the char gasification reaction starts moving in the reverse direction. In this process, 736.629 MW of power is produced when only natural gas and air are used in the combustion chamber and if we add hydrogen, power is increased up to 16 MW. To predict syngas composition and the S/B ratio, machine learning modeling using Artificial Neural Networks (ANN) algorithms are applied and compared, Bayesian Regularization and Scaled Conjugate gradient proves to be the best ANN model for validating and comparing with process model, demonstrating its accuracy and potential for optimizing biomass gasification processes as high as up-to 0.99 R2 value.

A computational stochastic procedure for solving the epidemic breathing transmission system

This work provides numerical simulations of the nonlinear breathing transmission epidemic system using the proposed stochastic scale conjugate gradient neural networks (SCGGNNs) procedure. The mathematical model categorizes the breathing transmission epidemic model into four dynamics based on a nonlinear stiff ordinary differential system: susceptible, exposed, infected, and recovered. Three different cases of the model are taken and numerically presented by applying the stochastic SCGGNNs. An activation function ‘log-sigmoid’ uses twenty neurons in the hidden layers. The precision of SCGGNNs is obtained by comparing the proposed and database solutions. While the negligible absolute error is performed around 10–06 to 10–07, it enhances the accuracy of the scheme. The obtained results of the breathing transmission epidemic system have been provided using the training, verification, and testing procedures to reduce the mean square error. Moreover, the exactness and capability of the stochastic SCGGNNs are approved through error histograms, regression values, correlation tests, and state transitions.

Multi-Objective Optimization Design of Permanent Magnet Eddy Current Coupler Based on SCG-BP Neural Network Modeling and the ONDX-NSGA-II Algorithm

There is a complex coupling relationship between the structural parameters and various performance indicators of a permanent magnet eddy current coupler. In order to obtain the optimal combination of structural parameters that can improve the overall performance of the coupler, it is necessary to reasonably balance the contradiction and competition among performance indicators of the permanent magnet eddy current coupler. A multi-objective optimization method for permanent magnet eddy current couplers based on scaled conjugate gradient back propagation neural network modeling, improved opposition-based learning, and normal distribution crossover operator non-dominated sorting genetic algorithm-II is proposed. The optimization results are compared with those of the traditional non-dominated sorting genetic algorithm-II and the Pareto envelope-based selection algorithm-II, and it is verified that the proposed multi-objective optimization algorithm is accurate, reliable, and has better convergence and versatility. Compared with the original model, the output torque of the optimized coupler increased by 8.54%, and the eddy current loss and cost decreased by 3.71% and 8.74%, respectively. Finally, the correctness of the theoretical analysis was verified through 3D finite element simulation and an experimental simulation platform.

Predictive Modeling of Signal Degradation in Urban VANETs Using Artificial Neural Networks

In urban Vehicular Ad Hoc Network (VANET) environments, buildings play a crucial role as they can act as obstacles that attenuate the transmission signal between vehicles. Such obstacles lead to multipath effects, which could substantially impact data transmission due to fading. Therefore, quantifying the impact of buildings on transmission quality is a key parameter of the propagation model, especially in critical scenarios involving emergency vehicles where reliable communication is of utmost importance. In this research, we propose a supervised learning approach based on Artificial Neural Networks (ANNs) to develop a predictive model capable of estimating the level of signal degradation, represented by the Bit Error Rate (BER), based on the obstacles perceived by moving emergency vehicles. By establishing a relationship between the level of signal degradation and the encountered obstacles, our proposed mechanism enables efficient routing decisions being made prior to the transmission process. Consequently, data packets are routed through paths that exhibit the lowest BER. To collect the training data, we employed Network Simulator 3 (NS-3) in conjunction with the Simulation of Urban MObility (SUMO) simulator, leveraging real-world data sourced from the OpenStreetMap (OSM) geographic database. OSM enabled us to gather geospatial data related to the Two-Dimensional (2D) geometric structure of buildings, which served as input for our Artificial Neural Network (ANN). To determine the most suitable algorithm for our ANN, we assessed the accuracy of ten learning algorithms in MATLAB, utilizing five key metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Correlation Coefficient (R), and Maximum Prediction Error (MaxPE). For each algorithm, we conducted fifteen iterations based on ten hidden neurons and gauged its accuracy against the aforementioned metrics. Our analysis highlighted that the ANN underpinned by the Conjugate Gradient With Powell/Beale Restarts (CGB) learning algorithm exhibited superior performance in terms of MSE, RMSE, MAE, R, and MaxPE compared to other algorithms such as Levenberg–Marquardt (LM), Bayesian Regularization (BR), BFGS Quasi-Newton (BFG), Resilient Backpropagation (RP), Scaled Conjugate Gradient (SCG), Fletcher–Powell Conjugate Gradient (CGF), Polak–Ribiére Conjugate Gradient (CGP), One-Step Secant (OSS), and Variable Learning Rate Backpropagation (GDX). The BER prediction by our ANN incorporates the TWO-RAY Ground (TRG) propagation model, an adjustable parameter within NS-3. When subjected to 300 new samples, the trained ANN’s simulation outcomes illustrated its capability to learn, generalize, and successfully predict the BER for a new data instance. Overall, our research contributes to enhancing the performance and reliability of communication in urban VANET environments, especially in critical scenarios involving emergency vehicles, by leveraging supervised learning and artificial neural networks to predict signal degradation levels and optimize routing decisions accordingly.

Rigorous hybrid machine learning approaches for interfacial tension modeling in brine-hydrogen/cushion gas systems: Implication for hydrogen geo-storage in the presence of cushion gas

In light of the environmental consequences linked to the burning of fossil fuels, there is a mounting push to devise cleaner means of energy generation. The production of hydrogen is gaining momentum as a favored avenue for enabling the shift toward sustainable energy. Effective hydrogen storage is crucial for sustainable energy solutions, and the inclusion of cushion gas in geological storage could aid in maintaining formation pressure during hydrogen reproduction while expanding pore volumes for gas by preventing water presence in pores. Accurately controlling hydrogen behavior and interactions in porous media is crucial for successful storage, with interfacial tension between gas and water playing a significant role in the trapping and mobilizing the phases. Thus, developing a predictive tool to simulate interfacial tension measurements is essential. This study employs various intelligent modeling techniques, including Adaptive Neuro-Fuzzy Inference System, Multilayer Perceptron optimized with Bayesian Regularization, Levenberg-Marquardt, and Scaled Conjugate Gradient algorithm, Grey Wolf Optimizer-based Least Squares Boosting (GWO-LSBOOST), GWO-based Radial Basis Function, GWO-based Least Squares Support Vector Machine, and Extreme Learning Machine (ELM), to develop interfacial tension models for brine-hydrogen/cushion gas systems. Applying these models developed based on diverse theories, structures, and performance characteristics helps identify the optimal predictor for the target parameter. The evaluation of the models was carried out using 2868 experimental data points. The achieved results demonstrated the satisfactory performance of different modeling techniques (with R2 falling within the range of 0.8979 to 0.9960), however, GWO-LSBOOST outperformed others (improving R2 from 0.8979 to 0.9960 and AARE% from 5.5714 % to 0.8060 %, compared to ELM). Leverage outlier identification and trend estimation analysis confirmed the statistical reliability of the dataset and the GWO-LSBOOST model. The formulated strategies offer a promising framework applicable for incorporating the gas-water interfacial tension in simulating various stages of gas injection/ reproduction in underground hydrogen storage.