Learning Methodology Research Articles

Deep Learning Assisted High Resolution Microscopy Image Processing for Phase Segmentation in Functional Composite Materials

In the domain of battery research, the processing of high-resolution microscopy images is a challenging task, as it involves dealing with complex images and requires a prior understanding of the components involved. The utilization of deep learning methodologies for image analysis has attracted considerable interest in recent years, with multiple investigations employing such techniques for image segmentation and analysis within the realm of battery research. However, the automated analysis of high-resolution microscopy images for detecting phases and components in composite materials is still an underexplored area.The presentation discusses the formulation of a sophisticated deep learning-assisted workflow tailored for the meticulous processing of high throughput, high-resolution microscopy images to detect, map and analyze the evolution of periodic components from a stack of high-resolution Transmission Electron Microscopy (TEM) image. The developed methodology employs deep learning techniques and utilizes Fast Fourier Transform (FFT) patterns extracted from TEM images to analyze feature positions and ascertain periodic components. The approach incorporates innovative strategies to process high-resolution images, capitalizing on the symmetry within FFT patterns to enhance model performance. This methodology streamlines the detection and mapping of components while the intensity profiles derived from the frames provide valuable insights into the evolution of periodic components within the sample during the imaging period.High-resolution images obtained through a beam damage analysis investigation of lithium fluoride (LiF), a prevalent constituent within the solid-electrolyte interphase (SEI) of cycled lithium metal anodes, were employed to assess the program's scalability and robustness. The study elucidated decomposition products and their spatial distribution. Furthermore, the intensity profile of periodic components detected across multiple frames aided in evaluating the beam damage mechanism of the LiF component.Our research has resulted in an open-source Python GUI program that the research community can freely access and experiment with. Figure 1

(Invited) Evolution of Single Atom Catalysts during CO2 Electrocatalytic Reduction

The re-utilization of CO2 via its electrocatalytic reduction (CO2RR) into value-added chemicals and fuels is a promising avenue to minimize the impact of existing technologies on the climate change. This requires the development of low cost, efficient, selective and durable electrocatalysts based of their rational understanding. Moreover, it should be considered that even morphologically and chemically well-defined pre-catalysts can be susceptible to drastic modifications under operation, especially when the reaction conditions themselves change dynamically.This talk will address the transformations that Metal-N-C catalysts (M=Cu, Ni, Co, Fe, Sn, Zn) experience during static and pulsed CO2RR using operando quick X-ray absorption spectroscopy (XAS) and Raman spectroscopy. In particular, I will illustrate the astonishing behaviordisplayed by Cu-N-C catalystsduring CO2RR, featuring reversible transformations from single atom sites towards Cu nanoparticles. The switchable nature of these species that can be achieved by applying different potential pulses holds the key for the on-demand control of the distribution of the CO2RR products and thus, a wide-spread adoption of this process.Moreover, I will elucidate the nature of the ligands forming under CO2RR at singly dispersed Ni sites in Ni-N-C catalysts, which are currently drawing great attention for their high performances in the CO formation. This will be achieved by a synergistic combination of conventional XAS, high energy resolution fluorescence detected X-ray absorption near edge structure (HERFD-XANES) spectroscopy, and X-ray emission spectroscopy (XES) coupled with unsupervised and supervised machine learning methodologies and density functional theory.Overall, my lecture will feature the importance of operando characterization of electrocatalysts in order to unveil structure/composition-reactivity correlations during CO2RR.

A lightweight deep learning architecture for malaria parasite-type classification and life cycle stage detection

Malaria is an endemic in various tropical countries. The gold standard for disease detection is to examine the blood smears of patients by an expert medical professional to detect malaria parasite called Plasmodium. In the rural areas of underdeveloped countries, with limited infrastructure, a scarcity of healthcare professionals, an absence of sufficient computing devices, and a lack of widespread internet access, this task becomes more challenging. A severe case of malaria can be fatal within one week, so the correct detection of the malaria parasite and its life cycle stage is crucial in treating the disease correctly. Though computer vision-based malaria detection has been adequately explored lately, the malaria life cycle stage classification is still a relatively unexplored field. In this paper, we introduce a fast and robust deep learning methodology to not only classify the malaria parasite-type detection but also the life cycle stage identification of the infected cell. The proposed deep learning architecture is more than twenty times lighter than the widely used DenseNet and has less than 0.4 million parameters, making it a good candidate to be used in the mobile applications of such economically challenged states for malaria detection. We have used four different publicly available malaria datasets to test the proposed architecture and gained significantly better results than the current state of the art on malaria parasite-type and malaria life cycle classification.

Advancing Virtual Interviews: AI-Driven Facial Emotion Recognition for Better Recruitment

Behavior analysis involves the detailed process of identifying, modeling, and comprehending the various nuances and patterns of emotional expressions exhibited by individuals. It poses a significant challenge to accurately detect and predict facial emotions, especially in contexts like remote interviews, which have become increasingly prevalent. Notably, many participants struggle to convey their thoughts to interviewers with a happy expression and good posture, which may unfairly diminish their chances of employment, despite their qualifications. To address this challenge, artificial intelligence techniques such as image classification offer promising solutions. By leveraging AI models, behavior analysis can be applied to perceive and interpret facial reactions, thereby paving the way to anticipate future behaviors based on learned patterns to the participants. Despite existing works on facial emotion recognition (FER) using image classification, there is limited research focused on platforms like remote interviews and online courses. In this paper, our primary focus lies on emotions such as happiness, sadness, anger, surprise, eye contact, neutrality, smile, confusion, and stooped posture. We have curated our dataset, comprising a diverse range of sample interviews captured through participants' video recordings and other images documenting facial expressions and speech during interviews. Additionally, we have integrated existing datasets such as FER 2013 and the Celebrity Emotions dataset. Through our investigation, we explore a variety of AI and deep learning methodologies, including VGG19, ResNet50V2, ResNet152V2, Inception-ResNetV2, Xception, EfficientNet B0, and YOLO V8 to analyze facial patterns and predict emotions. Our results demonstrate an accuracy of 73% using the YOLO v8 model. However, we discovered that the categories of happy and smile, as well as surprised and confused, are not disjoint, leading to potential inaccuracies in classification. Furthermore, we considered stooped posture as a non-essential class since the interviews are conducted via webcam, which does not allow for the observation of posture. By removing these overlapping categories, we achieved a remarkable accuracy increase to around 76.88% using the YOLO v8 model.

Navigating the new frontier: the impact of artificial intelligence on students’ entrepreneurial competencies

PurposeArtificial intelligence (AI) technologies have led to significant transformations across industries and society, including the field of education. The integration of AI in educational settings has the potential to improve students' learning experience and support their individual competencies when paired with non-AI methods. Despite the growing importance of AI in modern education, there remains a noticeable research gap regarding its use in entrepreneurship education and the effects of Chatbots on students' entrepreneurial competencies. To address this gap, an exploratory study was conducted on undergraduate students who were tasked with using ChatGPT to improve their business model canvas.Design/methodology/approachThe chosen methodology aligned with the research purpose, aiming to explore the relationship between Generative AI and competencies. Due to the novel nature of the research problem, an exploratory study was conducted using a mixed methods approach. A survey with open- and closed-ended questions was designed, and statistical and text analyses were performed to interpret data and test identified propositions.FindingsThe findings of this study indicate that ChatGPT can enhance the types of students' entrepreneurial competencies considered in this study: spotting opportunities, creativity, vision, valuing ideas and ethical and sustainable thinking. The results show that ChatGPT can be particularly helpful to improve the ability of students of valuing ideas.Originality/valueOverall, this study highlights the potential of adopting ChatGPT in experiential learning methodologies for enhancing students' entrepreneurial competencies and improving their learning outcomes.

Leveraging AI-powered mobile learning: A pedagogically informed framework

The convergence of Artificial Intelligence (AI) and mobile learning (mLearning) has revolutionized digital education, heralding a transformative paradigm shift in learning methodologies. AI-powered mLearning holds promise but requires deep understanding of pedagogical principles. Concerns over smartphone overuse have heightened discussions about mLearning integration. In this context, with the rising penetration of AI in various educational settings, it is crucial that research delves into the pedagogically sound integration of AI into mLearning environments. A systematic literature review of forty-two articles has yielded a framework summarizing mLearning attributes, functionalities, and their impact on transversal learning principles highlighting the profound impact of AI.

Multistage transfer learning for medical images

Deep learning is revolutionizing various domains and significantly impacting medical image analysis. Despite notable progress, numerous challenges remain, necessitating the refinement of deep learning algorithms for optimal performance in medical image analysis. This paper explores the growing demand for precise and robust medical image analysis by focusing on an advanced deep learning technique, multistage transfer learning. Over the past decade, multistage transfer learning has emerged as a pivotal strategy, particularly in overcoming challenges associated with limited medical data and model generalization. However, the absence of well-compiled literature capturing this development remains a notable gap in the field. This exhaustive investigation endeavors to address this gap by providing a foundational understanding of how multistage transfer learning approaches confront the unique challenges posed by insufficient medical image datasets. The paper offers a detailed analysis of various multistage transfer learning types, architectures, methodologies, and strategies deployed in medical image analysis. Additionally, it delves into intrinsic challenges within this framework, providing a comprehensive overview of the current state while outlining potential directions for advancing methodologies in future research. This paper underscores the transformative potential of multistage transfer learning in medical image analysis, providing valuable guidance to researchers and healthcare professionals.

The Use of Machine Learning to Predict Prevalence of Subclinical Mastitis in Dairy Sheep Farms.

The objective of the study was to develop a computational model with which predictions regarding the level of prevalence of mastitis in dairy sheep farms could be performed. Data for the construction of the model were obtained from a large Greece-wide field study with 111 farms. Unsupervised learning methodology was applied for clustering data into two clusters based on 18 variables (17 independent variables related to health management practices applied in farms, climatological data at the locations of the farms, and the level of prevalence of subclinical mastitis as the target value). The K-means tool showed the highest significance for the classification of farms into two clusters for the construction of the computational model: median (interquartile range) prevalence of subclinical mastitis among farms was 20.0% (interquartile range: 15.8%) and 30.0% (16.0%) (p = 0.002). Supervised learning tools were subsequently used to predict the level of prevalence of the infection: decision trees, k-NN, neural networks, and Support vector machines. For each of these, combinations of hyperparameters were employed; 83 models were produced, and 4150 assessments were made in total. A computational model obtained by means of Support vector machines (kernel: 'linear', regularization parameter C = 3) was selected. Thereafter, the model was assessed through the results of the prevalence of subclinical mastitis in 373 records from sheep flocks unrelated to the ones employed for the selection of the model; the model was used for evaluation of the correct classification of the data in each of 373 sets, each of which included a test (prediction) subset with one record that referred to the farm under assessment. The median prevalence of the infection in farms classified by the model in each of the two categories was 10.4% (5.5%) and 36.3% (9.7%) (p < 0.0001). The overall accuracy of the model for the results presented by the K-means tool was 94.1%; for the estimation of the level of prevalence (<25.0%/≥25.0%) in the farms, it was 96.3%. The findings of this study indicate that machine learning algorithms can be usefully employed in predicting the level of subclinical mastitis in dairy sheep farms. This can facilitate setting up appropriate health management measures for interventions in the farms.

Optimizing Curriculum Vitae Concordance: A Comparative Examination of Classical Machine Learning Algorithms and Large Language Model Architectures

Digital recruitment systems have revolutionized the hiring paradigm, imparting exceptional efficiencies and extending the reach for both employers and job seekers. This investigation scrutinized the efficacy of classical machine learning methodologies alongside advanced large language models (LLMs) in aligning resumes with job categories. Traditional matching techniques, such as Logistic Regression, Decision Trees, Naïve Bayes, and Support Vector Machines, are constrained by the necessity of manual feature extraction, limited feature representation, and performance degradation, particularly as dataset size escalates, rendering them less suitable for large-scale applications. Conversely, LLMs such as GPT-4, GPT-3, and LLAMA adeptly process unstructured textual content, capturing nuanced language and context with greater precision. We evaluated these methodologies utilizing two datasets comprising resumes and job descriptions to ascertain their accuracy, efficiency, and scalability. Our results revealed that while conventional models excel at processing structured data, LLMs significantly enhance the interpretation and matching of intricate textual information. This study highlights the transformative potential of LLMs in recruitment, offering insights into their application and future research avenues.

An Explainable Deep Learning Approach for Stress Detection in Wearable Sensor Measurements.

Stress has various impacts on the health of human beings. Recent success in wearable sensor development, combined with advancements in deep learning to automatically detect features from raw data, opens several interesting applications related to detecting emotional states. Being able to accurately detect stress-related emotional arousal in an acute setting can positively impact the imminent health status of humans, i.e., through avoiding dangerous locations in an urban traffic setting. This work proposes an explainable deep learning methodology for the automatic detection of stress in physiological sensor data, recorded through a non-invasive wearable sensor device, the Empatica E4 wristband. We propose a Long-Short Term-Memory (LSTM) network, extended through a Deep Generative Ensemble of conditional GANs (LSTM DGE), to deal with the low data regime of sparsely labeled sensor measurements. As explainability is often a main concern of deep learning models, we leverage Integrated Gradients (IG) to highlight the most essential features used by the model for prediction and to compare the results to state-of-the-art expert-based stress-detection methodologies in terms of precision, recall, and interpretability. The results show that our LSTM DGE outperforms the state-of-the-art algorithm by 3 percentage points in terms of recall, and 7.18 percentage points in terms of precision. More importantly, through the use of Integrated Gradients as a layer of explainability, we show that there is a strong overlap between model-derived stress features for electrodermal activity and existing literature, which current state-of-the-art stress detection systems in medical research and psychology are based on.

An Early Detection of Tuberculosis Using Chest X-Ray with Computer-Aided Diagnosis through Machine Learning and Deep Learning Methodology

An Early Detection of Tuberculosis Using Chest X-Ray with Computer-Aided Diagnosis through Machine Learning and Deep Learning Methodology

GAME-BASED LEARNING IN MATHEMATICS FOR PUPILS AND TEACHERS

Computer games are utilized as teaching aids in a method known as “game-based learning.” Enhancing teaching abilities, evaluating learners, tracking progress, and offering learning support are among the learning objectives. The Self-Determination Theory is employed in the study to evaluate the uptake of web apps. 41 fifth-grade pupils who were enrolled in the study completed a 5-point Likert scale questionnaire. These participants used a game-based learning platform. The results show that most participants embraced and adjusted to the game-based learning methodology. The outcomes show that fifth-grade pupils benefit and are positively impacted by this method.

Creating educational podcasts as an expository methodology for active learning and its relationship with satisfaction: A comparative study with live oral presentations

ABSTRACT The educational podcast is a didactic resource requiring specific planning to create a digital audio file with educational content. These podcasts promote meaningful learning and stimulate cognitive skills. This study aimed to analyze the effectiveness of educational podcasts in increasing students’ satisfaction and performance in content acquisition compared to live oral presentations. An experimental methodology was used, involving 148 students from the University of Zaragoza (2022-2023). Students were divided into two groups: one used podcasts, and the others gave live oral presentations. They assessed both types of presentations using an evaluation rubric and collaborated on content development. Data on academic performance, satisfaction, ratings, gender, age, and admission cut-off marks were collected for statistical analysis. Both groups reported high satisfaction, with in-class presentations deemed slightly more appropriate. Exam performance was similar across groups. Collaborative, student-centered learning increased satisfaction, but intra-group conflicts prevented clear distinctions between the methodologies.

Hyper-local black carbon prediction by integrating land use variables with explainable machine learning model

This research introduces an innovative framework that effectively integrates the Land Use Regression (LUR) model with an explainable machine learning methodology, thereby enhancing the causal understanding of how land use variables impact Black Carbon (BC) concentrations in complex urban landscapes. Through the development and application of a LUR-based Bayesian Network (BN) model to detailed, mobile-based BC measurements, we have successfully decoded the causal relationships and conditional probabilities linking diverse urban land use variables to BC levels. The BN model demonstrates notable prediction accuracy on the test set, with an R2 of 0.59 and an NRMSE of 0.65. Among the varied land use variables analyzed, proximity to the port is identified as the dominant factor contributing to BC hotspots. Moreover, the synergistic effect of port proximity and truck routes emerges as a key driver of spatially clustered BC hotspots, a complex phenomenon not adequately captured by conventional machine learning and deep learning models. The insights revealed through this study are vital not just for enhancing air pollution prediction and exposure analysis but also for informing urban planning and policymaking, offering valuable, actionable insights.

Comparative analysis of semantic segmentation and multi-boosted faster R-CNN for robotic tool detection in diabetes patient care

Diabetes, a common chronic illness, need meticulous patient care and treatment, which frequently necessitates advanced robotic help. The identification of robotic tools is critical in guaranteeing precise and safe medical procedures. With the growing use of robots in healthcare, reliable identification of instruments inside a patient care setting is critical for allowing smooth and efficient medical procedures. We used a Multi-Boosted Faster-Region-based Convolutional Neural Network (MBF-RCNN) to estimate Robotic Tool Detection in Diabetes Patient Care in the present research. Semantic Segmentation is a machine learning methodology centered on classifying pictures pixel-by-pixel, whereas Multi-Boosted Faster R-CNN recognizes objects using a variety of boosting strategies. Decimal Scaling Normalization is used during the preprocessing step to optimize the input data for both procedures. The effectiveness of both approaches is improved by doing extraction of features using Linear Discriminant Analysis (LDA) to find key trends in the information that is provided.The Multi-Boosted Faster-Region-based Convolutional Neural Network (MBF-RCNN) is an improved variation of the Faster R-CNN design that uses the boosting approach to improve object identification performance.Accuracy, Precision, Recall, F1-score, and the Receiver Operating Characteristic (ROC) curve among the assessment metrics used. The findings show that the suggested approaches are effective in identifying and localizing robotic equipment, which is critical for effective treatments in controlling diabetes.This research promotes computer vision applications in healthcare, particularly in the care of diabetic patients. It assesses the efficiency and dependability of Semantic Segmentation and MBF-RCNN for robotic tool identification, opening the way for more efficient and dependable automation for healthcare contexts.

Optimized quantum LSTM using modified electric Eel foraging optimization for real-world intelligence engineering systems

The integration of metaheuristics with machine learning methodologies presents significant advantages, particularly in optimization and computational intelligence. This amalgamation leverages the global search capabilities of metaheuristics alongside the pattern recognition and predictive prowess of machine learning, facilitating enhanced convergence rates and solution quality in complex problem spaces. The Quantum Long Short-Term Memory (QLSTM) emerges as a highly efficient deep learning model tailored to tackle such intricate engineering problems. The QLSTM's architecture, comprising data encoding, variational, and quantum measurement layers, facilitates the effective encoding and processing of civil engineering data, leading to heightened prediction accuracy. However, the task of determining optimal values for QLSTM parameters presents challenges due to its NP-problem nature and time-consuming characteristics. To address this, we propose an alternative technique to optimize the QLSTM based on a modified Electric Eel Foraging Optimization (MEEFO). The MEEFO is a modified version of the original EEFO that applies triangular mutation operators to boost the search capability of the traditional EEFO. Thus, the MEEFO optimizes the QLSTM and boosts its prediction performance. To validate the efficacy of our proposed method, we conduct comprehensive experiments utilizing five real-world engineering datasets related to construction and structure engineering. The evaluation outcomes unequivocally demonstrate that the MMEFO significantly enhances the performance of the QLSTM.

Thermoelectric properties enhancement and optimization of SnTe-based material with single doping: RSM-ANN approach

Tin Telluride (SnTe) stands out among semiconductor materials, drawing attention as an environmentally friendly alternative to conventional Lead Telluride (PbTe). This study explores the novel incorporation of titanium (Ti) and zirconium (Zr) as dopant elements in SnTe-based materials, an approach that has never been previously investigated. Leveraging mathematical modeling and machine learning methodologies, we use Response Surface Methodology (RSM) and Artificial Neural Network-Genetic Algorithm (ANN-GA) to predict thermoelectric properties of SnTe-based materials and find the optimum dopant element addition and operating temperature. Eleven samples featuring varying Ti and Zr concentrations are employed in experimental investigations, with dopant amounts ranging from 0 to 0.05 M. Characterization of each sample is conducted across a temperature spectrum from 50 to 450 °C, yielding a comprehensive dataset of 99 entries for neural network model construction. The generated RSM and ANN models demonstrate remarkable predictive accuracy for the thermoelectric properties of SnTe-based materials, showcasing coefficient of determination (R2) values spanning from 0.986 to 0.998. This study uses RSM and ANN-GA to predict an optimized zT value of 0.558. This value surpasses the highest zT value from the experiment by 3.33 %. In conclusion, this investigation underscores the potency of RSM and ANN as valuable tools for advancing research on SnTe-based thermoelectric materials, exemplifying their capacity to hasten the exhausting process of finding the optimum dopant addition and operating temperature.

A Multi-Modal Machine Learning Methodology for Predicting Solitary Pulmonary Nodule Malignancy in Patients Undergoing PET/CT Examination

This study explores a multi-modal machine-learning-based approach to classify solitary pulmonary nodules (SPNs). Non-small cell lung cancer (NSCLC), presenting primarily as SPNs, is the leading cause of cancer-related deaths worldwide. Early detection and appropriate management of SPNs are critical to improving patient outcomes, necessitating efficient diagnostic methodologies. While CT and PET scans are pivotal in the diagnostic process, their interpretation remains prone to human error and delays in treatment implementation. This study proposes a machine-learning-based network to mitigate these concerns, integrating CT, PET, and manually extracted features in a multi-modal manner by integrating multiple image modalities and tabular features). CT and PET images are classified by a VGG19 network, while additional SPN features in combination with the outputs of VGG19 are processed by an XGBoost model to perform the ultimate diagnosis. The proposed methodology is evaluated using patient data from the Department of Nuclear Medicine of the University Hospital of Patras in Greece. We used 402 patient cases with human annotations to internally validate the model and 96 histopathological-confirmed cases for external evaluation. The model exhibited 97% agreement with the human readers and 85% diagnostic performance in the external set. It also identified the VGG19 predictions from CT and PET images, SUVmax, and diameter as key malignancy predictors. The study suggests that combining all available image modalities and SPN characteristics improves the agreement of the model with the human readers and the diagnostic efficiency.

Ageism toward older adults among social education students: the impact of a photovoice program

ABSTRACT This study describes the design, implementation, and evaluation of a photovoice program for Social Education students from a Polytechnic University in Portugal. The program was named ‘Ageism in Perspective’ and developed over six sessions during one semester. The design was based on principles of the original photovoice methodology, along with previous experiences of photovoice as an active and experiential learning methodology in higher education. Implementation included theoretical-pedagogical and ethical activities about the methodology (photovoice) and the topic under exploration (ageism). It went practically-technologically through the process of taking and presenting photographs in the group/classes, ending with a seminar and exhibition open to the community to share the main findings. Evaluation included a pre-posttest approach using the Negative Stereotypes Toward Aging Questionnaire (CENVE) and a final focus group addressing students’ overall experience with the program, the photovoice approach, and the impact on their perspectives about ageism. Participants (n = 45; mean age of 21.1, SD 4.1) were students of the second year in the degree course of Social Education. There was a statistically significant decrease in the CENVE score between the pre (30.1 ± 7.3) and the post (21.5 ± 4.0) test, meaning lower stereotypes after the program. Emerging themes from the focus group thematic analysis were (i) I am more willing to interact with older adults; (ii) Photovoice booster multiple perspectives and reflexivity; (iii) Becoming aware that ageism exists (even in myself). Findings suggest that photovoice is a good pedagogical tool to address students’ stereotypes about older adults, which should be as important as addressing the syllabus content.

Groundwater salinity modeling and mapping using machine learning approaches: a case study in Sidi Okba region, Algeria.

The groundwater salinization process complexity and the lack of data on its controlling factors are the main challenges for accurate predictions and mapping of aquifer salinity. For this purpose, effective machine learning (ML) methodologies are employed for effective modeling and mapping of groundwater salinity (GWS) in the Mio-Pliocene aquifer in the Sidi Okba region, Algeria, based on limited dataset of electrical conductivity (EC) measurements and readily available digital elevation model (DEM) derivatives. The dataset was randomly split into training (70%) and testing (30%) sets, and three wrapper selection methods, recursive feature elimination (RFE), forward feature selection (FFS), and backward feature selection (BFS) are applied to train the data. The resulting combinations are used as inputs for five ML models, namely random forest (RF), hybrid neuro-fuzzy inference system (HyFIS), K-nearest neighbors (KNN), cubist regression model (CRM), and support vector machine (SVM). The best-performing model is identified and applied to predict and map GWS across the entire study area. It is highlighted that the applied methods yield input variation combinations as critical factors that are often overlocked by many researchers, which substantially impacts the models' accuracy. Among different alternatives the RF model emerged as the most effective for predicting and mapping GWS in the study area, which led to the high performance in both the training (RMSE = 1.016, R = 0.854, and MAE = 0.759) and testing (RMSE = 1.069, R = 0.831, and MAE = 0.921) phases. The generated digital map highlighted the alarming situation regarding excessive GWS levels in the study area, particularly in zones of low elevations and far from the Foum Elgherza dam and Elbiraz wadi. Overall, this study represents a significant advancement over previous approaches, offering enhanced predictive performance for GWS with the minimum number of input variables.