Imperialist Competitive Algorithm Research Articles

Co-Optimization of Operational and Intelligent Completion Parameters of CO2 Water-Alternating-Gas Injection Processes in Carbonate Reservoirs

Recently, maximum reservoir contacting (MRC) wells have attracted more and more attention and have been gradually applied to CO2 WAG injections. During the use of MRC wells for CO2 WAG injections, intelligent completions are commonly considered to control CO2 breakthroughs. However, the design of the operational and intelligent completion parameters is a complicated process and there are no studies on the co-optimization of the operational and intelligent completion parameters for CO2 WAG processes. This study outlines an approach to enhance the oil recovery from CO2 WAG injection processes through the co-optimization of the operational and intelligent completion parameters of MRC wells in a carbonate reservoir. First, a simulation method is developed by using Petrel and Intersect. Then, a series of simulations are performed to prove the viability of intelligent completions and to investigate the effects of the timing and duration of the CO2 WAG injection, as well as the type, number, and placement of intelligent completion devices on the performance of a CO2 WAG injection by MRC wells. Finally, the imperialist competitive algorithm is used to co-optimize the operational and intelligent completion parameters for MRC wells. The results show that compared with the spiral inflow control device (SICD), autonomous inflow control device (AICD), labyrinth inflow control device (LICD), and annular interval control valve (AICV), the nozzle inflow control device (NICD) is the best type of intelligent completion device for MRC wells. There is an optimal installation timing, inflow area, and number of NICDs for a CO2 WAG injection by MRC wells. The NICDs need to be placed based on the permeability distribution. The oil recovery for the optimal case with the NICDs reached 46.43%, which is an increase of 3.8% over that of the base case with a conventional completion. In addition, compared with the non-uniformity coefficient of the base case (11.7), the non-uniformity coefficient of the optimal case with the NICDs decreased to 4.21. This is the first time that the co-optimization of the operational and intelligent completion parameters of a CO2 WAG injection has been reported, which adds more information about the practical applications of MRC wells in CO2 WAG injections for enhancing oil recovery in carbonate reservoirs.

Optimization method of time of use electricity price considering losses in distributed photovoltaic access distribution network

Currently, the time-of-use pricing model for electricity focuses on a single objective, often overlooking various factors that influence electricity costs. This oversight can lead to significant disparities in peak and off-peak electricity usage within the distribution network following optimization. Therefore, a new time of using electricity price optimization method is proposed that takes into account the losses of distributed photovoltaic access to the distribution network. Considering the topology structure of the distribution network after the integration of distributed photovoltaic, this paper calculates the comprehensive losses generated by the operation of the distribution network. Also, this paper constructs a time of use electricity price optimization mathematical model with the objectives of minimizing network loss, minimizing load variance, minimizing peak valley difference of equivalent load, and maximizing user satisfaction. And refer to the basic requirements for electricity pricing in the distribution network, set a series of constraints for optimizing electricity prices. Applying an improved imperialist competition algorithm this paper integrates Tent chaotic reverse learning to solve a multi-objective optimization model and obtain an optimized time of use electricity pricing plan. The experimental results show that after the implementation of this optimization method, the peak valley difference of the daily power load curve of the distribution network is only 350 MW, demonstrating superior peak shaving and valley filling effects.

Design of Dual-Channel Supply Chain Network Based on the Internet of Things Under Uncertainty

In this paper, a mathematical model of a dual-channel supply chain network (DCSCN) based on the Internet of Things (IoT) under uncertainty is presented, and its solution using algorithms based on artificial intelligence such as genetic algorithm (GA), particle swarm optimization (PSO), imperialist competitive algorithm (ICA), and gray wolf optimizer (GWO). The main goal of this model is to maximize the total DCSCN profit to determine the amount of demand accurately, price in direct and indirect channels, locate distribution centers, and equip/not equip these centers with IoT devices. The results show that with the increase in the uncertainty rate, the amount of demand and corresponding transportation costs have increased. This issue has led to a decrease in the total DCSCN profit. By analyzing the mathematical model, it was also observed that deploying IoT equipment in distribution centers has increased fixed costs. Examining this issue shows that by increasing the savings factor by 0.2, the total DCSCN profit has increased by 6.5%. By ranking the algorithms with the TOPSIS method, the GA was ranked as the most efficient algorithm, followed by PSO, ICA, and GWO. This IoT-enhanced dual-channel supply chain model not only aims to optimize traditional supply chain metrics but also introduces advanced, data-driven strategies for improving demand management, pricing, and infrastructure allocation, ultimately driving profitability in uncertain environments.

CNN-O-ELMNet: Optimized Lightweight and Generalized Model for Lung Disease Classification and Severity Assessment.

The high burden of lung diseases on healthcare necessitates effective detection methods. Current Computer-aided design (CAD) systems are limited by their focus on specific diseases and computationally demanding deep learning models. To overcome these challenges, we introduce CNN-O-ELMNet, a lightweight classification model designed to efficiently detect various lung diseases, surpassing the limitations of disease-specific CAD systems and the complexity of deep learning models. This model combines a convolutional neural network for deep feature extraction with an optimized extreme learning machine, utilizing the imperialistic competitive algorithm for enhanced predictions. We then evaluated the effectiveness of CNN-O-ELMNet using benchmark datasets for lung diseases: distinguishing pneumothorax vs. non-pneumothorax, tuberculosis vs. normal, and lung cancer vs. healthy cases. Our findings demonstrate that CNN-O-ELMNet significantly outperformed (p < 0.05) state-of-the-art methods in binary classifications for tuberculosis and cancer, achieving accuracies of 97.85% and 97.70%, respectively, while maintaining low computational complexity with only 2481 trainable parameters. We also extended the model to categorize lung disease severity based on Brixia scores. Achieving a 96.20% accuracy in multi-class assessment for mild, moderate, and severe cases, makes it suitable for deployment in lightweight healthcare devices.

EXPLOITING REMOTE SENSING IMAGERY FOR VEHICLE DETECTION AND CLASSIFICATION USING ROBUST COMPETITIVE ALGORITHM WITH DEEP CONVOLUTIONAL NEURAL NETWORK

Fast and robust vehicle recognition from remote sensing images (RSIs) has excellent economic analysis, emergency management, and traffic surveillance applications. Additionally, vehicle density and location data are vital for intelligent transportation systems. However, correct and robust vehicle recognition in RSIs has been complex. Conventional vehicle recognition approaches depend on handcrafted extracted features in sliding windows with distinct scales. Recently, the convolutional neural network can be executed for aerial image object recognition, and it has accomplished promising outcomes. This research projects an automatic vehicle detection and classification utilizing an imperialist competitive algorithm with a deep convolutional neural network (VDC-ICADCNN) technique. The primary purpose of the VDC-ICADCNN technique is to develop the RSI and apply deep learning (DL) models for the recognition and identification of vehicles. Three main procedures were involved in the presented VDC-ICADCNN technique. At the primary stage, the VDC-ICADCNN technique employs the EfficientNetB7 approach for the feature extractor. Then, the hyperparameter fine-tuning of the EfficientNet approach takes place utilizing ICA, which aids in attaining improved performance in the classification process. The VDC-ICADCNN technique utilizes a variational autoencoder (VAE) model for the vehicle recognition method. Extensive experiments can be implemented to establish the superior solution of the VDC-ICADCNN technique. The obtained outcomes of the VDC-ICADCNN technique highlighted a superior accuracy value of 96.77% and 98.59% with other DL approaches under Vehicle Detection in Aerial Imagery (VEDAI) and Potsdam datasets.

Optimal Coordination of Directional Overcurrent Relays in Microgrids Considering European and North American Curves

Protecting AC microgrids (MGs) is a challenging task due to their dual operating modes—grid-connected and islanded—which cause sudden variations in fault currents. Traditional protection methods may no longer ensure network security. This paper presents a novel approach to protection coordination in AC MGs using non-standard features of directional over-current relays (DOCRs). Three key optimization variables are considered: Time Multiplier Setting (TMS), the plug setting multiplier’s (PSM) maximum limit, and the standard characteristic curve (SCC). The proposed model is formulated as a mixed-integer nonlinear programming problem and solved using four metaheuristic techniques: the genetic algorithm (GA), Imperialist Competitive Algorithm (ICA), Harmonic Search (HS), and Firefly Algorithm (FA). Tests on a benchmark IEC MG with distributed generation and various operating modes demonstrate that this approach reduces coordination times compared to existing methods. This paper’s main contributions are threefold: (1) introducing a methodology for assessing the optimal performance of different standard curves in MG protection; (2) utilizing non-standard characteristics for optimal coordination of DOCRs; and (3) enabling the selection of curves from both North American and European standards. This approach improves trip time performance across multiple operating modes and topologies, enhancing the reliability and efficiency of MG protection systems.

VIS/NIR Spectroscopy as a Non-Destructive Method for Evaluation of Quality Parameters of Three Bell Pepper Varieties Based on Soft Computing Methods

Spectroscopic analysis was employed to evaluate the quality of three bell pepper varieties within the 350–1150 nm wavelength range. Quality parameters such as firmness, pH, soluble solids content, titratable acids, vitamin C, total phenols, and anthocyanins were measured. To enhance data reliability, principal component analysis (PCA) was used to identify and remove outliers. Raw spectral data were initially modeled using partial least squares regression (PLSR). To optimize wavelength selection, support vector machines (SVMs) were combined with genetic algorithms (GAs), particle swarm optimization (PSO), ant colony optimization (ACO), and imperial competitive algorithm (ICA). The most effective wavelength selection method was subsequently used for further analysis. Three modeling techniques—PLSR, multiple linear regression (MLR), and artificial neural networks (ANNs)—were applied to the selected wavelengths. PLSR analysis of raw data yielded a maximum R2 value of 0.98 for red pepper pH, while the lowest R2 (0.58) was observed for total phenols in yellow peppers. SVM-PSO was determined to be the optimal wavelength selection algorithm based on ratio of performance to deviation (RPD), root mean square error (RMSE), and correlation values. An average of 15 effective wavelengths were identified using this combined approach. Model performance was evaluated using root mean square error of cross-validation and coefficient of determination (R2). ANN consistently outperformed MLR and PLSR in predicting firmness, pH, soluble solids content, titratable acids, vitamin C, total phenols, and anthocyanins for all three varieties. R2 values for the ANN model ranged from 0.94 to 1.00, demonstrating its superior predictive capability. Based on these results, ANN is recommended as the most suitable method for evaluating the quality parameters of bell peppers using spectroscopic data.

Voltage Deviation Improvement in Microgrid Operation through Demand Response Using Imperialist Competitive and Genetic Algorithms

In recent decades, with the expansion of distributed energy generation technologies and the increasing need for more flexibility and efficiency in energy distribution systems, microgrids have been considered a promising innovative solution for local energy supply and enhancing resilience against network fluctuations. One of the basic challenges in the operation of microgrids is the optimal management of voltage and frequency in the network, which has been the subject of extensive research in the field of microgrid operational optimization. The energy demand is considered a crucial element for energy management due to its fluctuating nature over the day. The use of demand response strategies for energy management is one of the most important factors in dealing with renewables. These strategies enable better energy management in microgrids, thereby improving system efficiency and stability. Given the complexity of optimization problems related to microgrid management, evolutionary optimization algorithms such as the Imperialist Competitive Algorithm (ICA) and Genetic Algorithm (GA) have gained great attention. These algorithms enable solving high-complexity optimization problems by considering various constraints and multiple objectives. In this paper, both ICA and GA, as well as their hybrid application, are used to significantly enhance the voltage regulation in microgrids. The integration of optimization techniques with demand response strategies improves the overall system efficiency and stability. The results proved that the hybrid method provides valuable insights for optimizing energy management systems.

Hybrid of imperialist competitive algorithm and particle swarm optimization for parameter extraction of photovoltaic cells

To improve the efficiency of photovoltaic systems, it is essential to obtain the parameters of photovoltaic cells through an identification process. However, due to the nonlinear and multimodal characteristics, accurately and reliably identifying the parameters of photovoltaic cells still remains a challenging task. In this paper, a hybrid of the imperialist competitive algorithm (ICA) and particle swarm optimization (PSO), ICA-PSO, is proposed to effectively identify the parameters of photovoltaic cells. The position updating strategy of PSO is adopted to replace the colony’s position updating strategy in the ICA. The hybrid algorithm ICA-PSO integrates the multi-swarm search characteristic and the powerful exploration ability of PSO together, leading to an enhanced optimization performance. Experimental results of applying ICA-PSO to parameter identification of photovoltaic cells show that ICA-PSO can extract the parameters of photovoltaic cells with higher accuracy and reliability, thus outperforming many other methods presented in the literature.

Identifying the parameters of photovoltaic cells using Gaussian bare-bone imperialist competitive algorithm with opposition-based learning mechanism

Extracting the precise parameters of photovoltaic (PV) cells has become very important for simulation, evaluation, control, and optimization of PV systems. However, it is still a challenging task to accurately and reliably extract the parameters of PV cells. To solve this difficult problem, in this paper, a new meta-heuristic algorithm called Gaussian bare-bone imperialist competitive algorithm with opposition-based learning (OBL-GBBICA) is proposed to extract the parameters of PV cells. To strengthen the exploring ability and speed up the convergence, opposition-based learning (OBL) is introduced into an imperialist competitive algorithm (ICA) for two considerations. First, OBL is adopted in the population initialization to produce a high-quality population. Second, the OBL is introduced into the assimilation step to guide ICA to explore more promising regions. The above improvements not only speed up the convergence of ICA but also enhance its searchability, which is beneficial to improving the accuracy and reliability of identification results. Experimental results show that OBL-GBBICA exhibits great superiority in extracting the PV cells parameters, compared with other methods in the literature.

Imperialist competition algorithm with quasi-opposition-based learning for function optimization and engineering design problems

Imperialist competitive algorithm (ICA) is an efficient meta-heuristic algorithm by simulating the competitive behaviour among imperialist countries. However, it still suffers from slow convergence and deficiency in exploration. To address these issues, an improved ICA is proposed by combining ICA with a quasi-opposition-based learning (QOBL) strategy, which is named QOBL-ICA. The improvements include two aspects. First, the QOBL strategy is adopted to generate a population of fitter individuals. Second, a QOBL-assisted assimilation strategy is proposed to enhance the exploration ability of ICA. As a result, the proposed QOBL-ICA has more powerful exploration ability than ICA as well as faster convergence speed. The effectiveness of the proposed QOBL-ICA is verified by testing on 20 benchmark functions and 3 engineering design problems. Experimental results show that the performance of QOBL-ICA is superior to most state-of-the-art meta-heuristic algorithms in terms of global optimum reached and convergence speed.

Solving the fuzzy p-hub center problem using imperialist competitive algorithm

Solving the fuzzy p-hub center problem using imperialist competitive algorithm

Waste management and water quality evaluation prediction in urban environments through advanced robust hybrid machine learning algorithms

Water quality management is a crucial aspect of environmental protection, requiring the monitoring and regulation of effluent discharges into surface water bodies. This research introduces a novel approach to predicting Water Quality Evaluation (WQE) through a unique hybrid model, ABC-DWKNN-ICA, which integrates the Distance-weighted K-Nearest Neighbors (DWKNN) algorithm with the Artificial Bee Colony (ABC), Firefly Algorithm (FA), Imperialist Competitive Algorithm (ICA), and Gravitational Search Algorithm (GSA). Utilizing a comprehensive dataset of 1106 data points from Telangana, India, spanning 2018–2020, the study examines a range of water quality parameters, including Ground Water Level (GWL), Potential of Hydrogen (PH), Electrical Conductivity (EC), and others. The ABC-DWKNN-ICA model demonstrates exceptional performance in terms of Recall, Precision, Accuracy, and F1 Score for WQE prediction, distinguishing itself with enhanced feature selection, improved classification accuracy, robustness to noise and outliers, reduced dimensionality, and scalability to large datasets. This hybrid model represents a significant advancement over existing approaches, including traditional Hybrid Machine Learning (HML) algorithms such as ABC-DWKNN, FA-DWKNN, ICA-DWKNN, and GSA-DWKNN. By focusing on the capabilities of ABC-DWKNN-ICA rather than comparing all HML algorithms, the research highlights its superior effectiveness in water quality prediction, with performance metrics of 0.83 for Recall, 0.86 for Precision, 0.91 for Accuracy, and 0.86 for F1 Score. This study thus fills a critical research gap by demonstrating the model's value in environmental data analysis and offering promising prospects for more effective management of water resources. Additionally, feature selection, dimensionality reduction, enhanced accuracy, noise handling, and imbalanced dataset management are key advantages of the proposed model.

Biomass chemical exergy estimation using novel intelligent tool: application to biorefinery sustainability

ABSTRACT In response to the growing importance of sustainable energy and environmental considerations in biorefinery technologies, this study introduces a novel hybrid artificial intelligence approach for predicting biomass chemical exergy. The proposed least-squares support vector machine method based on an imperialist competitive algorithm (ICA-LSSVM) combines composition and energy analysis methods to model the chemical energy of biomass accurately. Extensive data were collected to train the model, resulting in a high-precision prediction with a coefficient of determination (R2) of 0.999 and a root mean square error (RMSE) of 30.3. The main point of this study is the development of this accurate model to determine the chemical energy, and also different forms of comparison are used to prove this issue. The sensitivity analysis highlights the direct impact of carbon (C%), hydrogen (H%), and oxygen (O%) percentages on biomass chemical exergy, while nitrogen (N%) and sulfur (S%) exhibit an inverse relationship. The model outperforms existing correlations in the literature, emphasizing its accuracy and practicality for biomass chemical exergy prediction, and contributing to both laboratory and industrial applications. The study emphasizes the model’s real-data reliance and suggests further exploration with an expanded dataset for enhanced industrial applicability.

Heat transfer modeling in a transformer using magneto-CFD analysis and GWO algorithm considering dynamic thermal model

One of the most expensive power system components is transformer. The correct use and health of the transformer increase the reliability of the power network.The transformer health is depend on careful planning for it. Therefore, hot spot temperature must be calculated for accurate transformer planning. Also, in order to increase the accuracy of transformer hot spot temperature estimation, the dynamic thermal model is used. On the other hand, the use of meta-heuristic algorithms has been less considered by researchers to calculate the transformer hot spot temperature. Thus, in this paper, the grey wolf, imperialist competitive and artificial bee colony algorithms are used to estimate the transformer hot spot temperature. Besides, electromagnetic analysis of the transformer is investigated using ANSYS-MAXWEL software. On the other hand, conjugate heat transfer modeling in the transformer is presented to compare the results with the grey wolf optimization algorithm. The results show that the grey wolf optimization algorithm can be a good alternative for transformer hot spot temperature estimation.

Improving the Technical and Economic Indexes of Distribution Network by Three-Stage Enhanced Imperialist Competitive Algorithm

Improving the Technical and Economic Indexes of Distribution Network by Three-Stage Enhanced Imperialist Competitive Algorithm

An effective channel allocation designed using hybrid memory dragonfly with imperialist competitive algorithm in distributed mobile adhoc network

SummaryThe channel availability problem reaches a higher degree in mobile ad hoc networks (MANETs) and garners a lot of attention in communication networks. Because increased mobile usage might result in a lack of channel allocation, an improved channel allocation technique is presented to tackle the availability problem. The distributed dynamic channel allocation (DDCA) model is built in this paper using the hybrid memory dragonfly with imperialist competitive (HMDIC) method. Based on optimization logic, this strategy assigns the channel to mobile hosts. The MANET provides a dispersed network within the coverage region in the absence of base station infrastructure. The HMDIC optimizer approach in this circumstance randomly begins every respective node to update and store their pbest value utilizing RAM dragonfly employing satellite images. The constraint values are then used to construct the cost function, which results in a strong kind of global optimum solution. The channels are therefore distributed in an effective manner. The HMDIC algorithm is used in this research to build a novel channel allocation system. It makes advantage of the exploration capabilities to successfully explore the individual node using MDA (Modified Dragonfly Algorithm) and locate the global best solution using imperialist competitive algorithm (ICA). Both of these combined tactics are more effective in accelerating the convergence of the allocation model. To validate the performance, the HMDIC‐based DDCA system provides promising results in terms of assigning available channels, thereby enhancing channel reuse efficiency and fractional interference.

Hybrid artificial neural network models for bearing capacity evaluation of a strip footing on sand based on Bolton failure criterion

This paper employs the Bolton failure criterion, incorporating strength-dilatancy relationships, to analyze the bearing capacity factor of a strip footing on dense sand. Utilizing finite element limit analysis (FELA) based on the lower and upper bound theorems, the study presents the results as average bound solutions. By using the Bolton model, the b parameter is first calibrated and found that it should be about 3.50 to align the ultimate bearing capacity (qu) from FELA to have a good agreement with that from experimental test results from previous studies. The influence of parameters relevant to the Bolton failure criterion is analysed, showing that an increase in relative density (DR) significantly affects the variation in the bearing capacity factor (Nγ) at higher Q values, while lower Q values inhibit dilatancy due to soil crushing. The width of the strip footing (B) has a decreasing effect on Nγ at higher Q values, and the unit weight (γ) changes minimally impact Nγ within the range of 16–22 kN/m3. Additionally, an increase in the critical state friction angle (ϕcv) consistently increases Nγ, highlighting its direct correlation with soil shear strength. A hybrid artificial neural network (ANN) model integrates machine learning with four optimization algorithms: Imperialist Competitive Algorithm (ICA), Ant Lion Optimization (ALO), Teaching Learning Based Optimization (TLBO), and New Self-Organizing Hierarchical Particle Swarm Optimizer with Jumping Time-Varying Acceleration Coefficients (NHPSO-JTVAC). Comparative rank analysis of hybrid ANN models based on the selection of the optimal number of hidden neurons demonstrates that the ANN-TLBO model excels in predicting the bearing capacity factor, achieving a score of 48. This conclusion is corroborated by an error heatmap matrix, which indicates a minimized percentage of error relative to other hybrid ANN models. Importance analysis identifies particle crushing strength (Q) as the most significant factor influencing the bearing capacity factor (Nγ).

Comparison of enhanced neural network and response surface models in predicting bio-dissolution of aluminum and vanadium from bauxite residue by isolated Aspergillus niger strains

Background: Recovery of Al and V from red mud, a hazardous residue of the Bayer process, using bioleaching is a nature-based waste management solution that simultaneously improves environment protection and metallurgical recoveries.Methods: For the first time, a novel hybrid multilayer Perceptron (MLP) network enhanced by an Imperialist Competitive Algorithm (ICA), and a response surface developed based on a factorial experiment design methodology (RSM) were employed and compared for, prediction optimization and optimization prediction of Al and V bioleaching by strains of A. Niger microorganisms isolated from pistachio shells and grape skins. The controlling variables were fungi source (A), adoption strategy (B), solid activation (C), solid percent (D), and bioleaching time. Considering the stochastic nature of ICA, a multi-criteria-ranking system based on accuracy and error indices was developed to select the best MLP. Probability value at 95% confidence interval, lack-of-fit, analysis of variance, R2, Adj. R2, and predicted R2 were the judges for the determination of the developed model's statistical significance.Significant Findings: Based on ANOVA, between A, B, C, and D, the effectiveness orders of A > D > C>AC>AD on Al, and A>AD>C>AC>D on V bioleaching were obtained. The superiority of the developed hybrid ICA-MLP model over the developed RSM model in predicting Al and V dissolution was determined by NSE, RSME, MAE, and MEDAE. Parameters optimization and consequently evaluating optimum condition repeatability through three repeating experiments resulted in maximum dissolution recoveries of RSM: 96.5% for Al and 91.2% for V, and ICA-MLP: 97.1% for Al and 90.3% for V. Considering the lower relative errors of repeating validation tests, it can be concluded that, although both models provide reasonable results, but the ICA-MLP methodology is more reliable (relative error <1.8%).

Solving water scarcity challenges in arid regions: A novel approach employing human-based meta-heuristics and machine learning algorithm for groundwater potential mapping

Addressing water scarcity challenges in arid regions is a pressing concern and demands innovative solutions for accurate groundwater potential mapping (GPM). This study presents a comprehensive evaluation of advanced modeling techniques to enhance the precision of GPM. This study, conducted in the Zayandeh Rood watershed, Iran, employed a spatial database comprising 16 influential factors on groundwater potential and data from 175 wells. This study introduced an innovative approach to GPM by enhancing the Random Forest (RF) algorithm. This enhancement involved integrating three metaheuristic algorithms inspired by human behavior: ICA (Imperialist Competitive Algorithm), TLBO (Teaching-Learning-Based Optimization), and SBO (Student Psychology Based Optimization). The modeling process used 70% training data and 30% evaluation data. Data preprocessing was performed using the multicollinearity test method and frequency ratio (FR) technique to refine the dataset. Subsequently, the GPM was generated using four distinct models, demonstrating the combined power of machine learning and human-inspired metaheuristic algorithms. The performance of the models was systematically assessed through extensive statistical analyses, including root mean squared error (RMSE), mean absolute error (MAE), area under the curve (AUC) for the receiver operating characteristic curve (ROC), Friedman tests, chi-squared tests, and Wilcoxon signed-rank tests. RF-ICA and RF-SPBO emerged as frontrunners, displaying statistically comparable accuracy and significantly outperforming RF-TLBO and the non-optimized RF model. The results of the GPM revealed the exceptional accuracy of RF-ICA, which exhibited a commanding AUC score of 0.865, underscoring its superiority in discriminating between different groundwater potential classes. RF-SPBO also displayed strong performance with an AUC of 0.842, highlighting its effectiveness in inaccurate classification. RF-TLBO and the non-optimized RF model achieved AUC values of 0.813 and 0.810, respectively, indicating comparable performance. The outcomes of this study provide valuable insights for policymakers, offering a robust framework for tackling water scarcity challenges in arid regions through precise and reliable groundwater potential assessments.