Bashar Alibrahim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bashar Alibrahim has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Ahed Habib
Sustainable Systems, Technologies and Infrastructure Research Center, Research Institute of Sciences and Engineering, University of Sharjah, Sharjah, United Arab Emirates
10 shared publications - Maan Habib
Faculty of Informatics Engineering, Al-Sham Private University, Damascus, Syria
9 shared publications - Eris Uygar
Eastern Mediterranean University
3 shared publications - Ausamah AL Houri
Department of Civil Engineering, Near East University, Nicosia, Cyprus
2 shared publications Ali Hossien Basheer Garoushi
Department of Civil Engineering, Engineering Faculty, Eastern Mediterranean University, Famagusta, Turkey
1 shared publicationEris Uygar
Department of Civil Engineering, Engineering Faculty, Eastern Mediterranean University, Famagusta, Turkey
1 shared publication
Latest Publications
- Open Access
- 3 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Developing a custom loss function for regulating underestimation and overestimation of concrete mechanical properties predictions in neural network models
Accurate prediction of concrete properties is a critical aspect of structural engineering. Conventional neural network models, while effective in various predictive tasks, often fall short in this context because they do not distinguish between the risks associated with underestimation and overestimation of strength. Existing codes of practice in civil engineering advocate a conservative estimation approach, prioritizing underestimation to preserve safety margins. Standard neural network models, which treat all prediction errors uniformly, are therefore not aligned with this conservative bias, which motivates the present study. The aim of this research is to design a custom loss function that embeds domain-specific safety requirements into artificial intelligence models. This function penalizes underestimations less severely than overestimations, reflecting the conservative principles of structural design. The problem formulation emphasizes the importance of conservative concrete strength prediction within the broader context of structural safety. Rubberized concrete is adopted as a case study to investigate the performance of the proposed custom loss function and to benchmark it against traditional loss functions. The study results show that the developed custom loss function effectively addresses conservative estimation needs by reducing the overestimation ratio from about 25–100% with traditional approaches to as low as 1%. At the same time, prediction accuracy remains comparable to conventional loss functions. Accordingly, the proposed custom loss function can serve as a technical enhancement that improves prediction behavior in line with conservative design philosophy and supports the reliable use of neural network models as one component within the structural design process.
- 3 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessDeveloping a custom loss function for regulating underestimation and overestimation of concrete mechanical properties predictions in neural network models
Accurate prediction of concrete properties is a critical aspect of structural engineering. Conventional neural network models, while effective in various predictive tasks, often fall short in this context because they do not distinguish between the risks associated with underestimation and overestimation of strength. Existing codes of practice in civil engineering advocate a conservative estimation approach, prioritizing underestimation to preserve safety margins. Standard neural network models, which treat all prediction errors uniformly, are therefore not aligned with this conservative bias, which motivates the present study. The aim of this research is to design a custom loss function that embeds domain-specific safety requirements into artificial intelligence models. This function penalizes underestimations less severely than overestimations, reflecting the conservative principles of structural design. The problem formulation emphasizes the importance of conservative concrete strength prediction within the broader context of structural safety. Rubberized concrete is adopted as a case study to investigate the performance of the proposed custom loss function and to benchmark it against traditional loss functions. The study results show that the developed custom loss function effectively addresses conservative estimation needs by reducing the overestimation ratio from about 25–100% with traditional approaches to as low as 1%. At the same time, prediction accuracy remains comparable to conventional loss functions. Accordingly, the proposed custom loss function can serve as a technical enhancement that improves prediction behavior in line with conservative design philosophy and supports the reliable use of neural network models as one component within the structural design process.
- Open Access
- 1 January 2026
- Published by Walter de Gruyter GmbH in Open Geosciences
- Vol. 18 (1)
A graphical approach to solving the van Genuchten soil-water retention equation
Accurate prediction of unsaturated soil behaviour depends on the reliable estimation of the soil-water retention curve (SWRC) and the corresponding hydraulic conductivity function (HCF). Although the van Genuchten-Mualem (VG-M) model is widely accepted for this purpose, its parameter estimation typically relies on nonlinear optimisation methods, which may produce values with limited physical meaning. This research presents a graphical method for directly identifying model parameters from essential characteristics of the SWRC, including the saturated and residual water contents, the inflection point, and the residual suction. The proposed approach removes the requirement for repetitive numerical fitting, improves the clarity and physical understanding of the parameters. The method was applied to measured SWRC datasets representing different soil textures. The graphical fits produced R 2 values of 0.9619–0.9926 and RMSE values of 0.0065–0.0172. For comparison, nonlinear least-squares fitting produced R 2 of 0.9909–0.9989 and RMSE values of 0.0020–0.0118. Although optimisation yielded lower errors, the graphical method retained a direct physical interpretation of the parameters. The graphically derived parameters for the VG-M HCF model captured the general hydraulic conductivity trend ( R 2 of 0.8540). Deviations at high suction were mainly associated with known limitations of the VG-M model at the dry end, rather than the graphical procedure itself.
- 1 January 2026
- Published by Walter de Gruyter GmbH in Open Geosciences
- Vol. 18 (1)
Open AccessA graphical approach to solving the van Genuchten soil-water retention equation
Accurate prediction of unsaturated soil behaviour depends on the reliable estimation of the soil-water retention curve (SWRC) and the corresponding hydraulic conductivity function (HCF). Although the van Genuchten-Mualem (VG-M) model is widely accepted for this purpose, its parameter estimation typically relies on nonlinear optimisation methods, which may produce values with limited physical meaning. This research presents a graphical method for directly identifying model parameters from essential characteristics of the SWRC, including the saturated and residual water contents, the inflection point, and the residual suction. The proposed approach removes the requirement for repetitive numerical fitting, improves the clarity and physical understanding of the parameters. The method was applied to measured SWRC datasets representing different soil textures. The graphical fits produced R 2 values of 0.9619–0.9926 and RMSE values of 0.0065–0.0172. For comparison, nonlinear least-squares fitting produced R 2 of 0.9909–0.9989 and RMSE values of 0.0020–0.0118. Although optimisation yielded lower errors, the graphical method retained a direct physical interpretation of the parameters. The graphically derived parameters for the VG-M HCF model captured the general hydraulic conductivity trend ( R 2 of 0.8540). Deviations at high suction were mainly associated with known limitations of the VG-M model at the dry end, rather than the graphical procedure itself.
- Open Access
- 16 July 2025
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 5 (1) , 1-15
Utilizing soil–water characteristic curve parameters in custom artificial neural network models to predict the unsaturated hydraulic conductivity
- 16 July 2025
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 5 (1) , 1-15
Open AccessUtilizing soil–water characteristic curve parameters in custom artificial neural network models to predict the unsaturated hydraulic conductivity
- Open Access
- 24 April 2025
- Published by Springer Nature in Discover Materials
- Vol. 5 (1) , 1-24
Comprehensive assessment on estimating the thermodynamic and mechanical properties of multicomponent Fe–Cr-based alloys using machine learning techniques
- 24 April 2025
- Published by Springer Nature in Discover Materials
- Vol. 5 (1) , 1-24
Open AccessComprehensive assessment on estimating the thermodynamic and mechanical properties of multicomponent Fe–Cr-based alloys using machine learning techniques
- Open Access
- 22 April 2025
- Published by Springer Nature in Discover Sustainability
- Vol. 6 (1) , 1-14
Novel closed-loop thermal gradient system for sustainable atmospheric water harvesting
- 22 April 2025
- Published by Springer Nature in Discover Sustainability
- Vol. 6 (1) , 1-14
Open AccessNovel closed-loop thermal gradient system for sustainable atmospheric water harvesting
- Open Access
- 30 January 2025
- Published by Taylor & Francis in International Journal of Sustainable Engineering
- Vol. 18 (1)
Behavior and sustainability benefits of modular steel buildings
- 30 January 2025
- Published by Taylor & Francis in International Journal of Sustainable Engineering
- Vol. 18 (1)
Open AccessBehavior and sustainability benefits of modular steel buildings
- Open Access
- 15 January 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-17
Developing a brain inspired multilobar neural networks architecture for rapidly and accurately estimating concrete compressive strength
Concrete compressive strength is a critical parameter in construction and structural engineering. Destructive experimental methods that offer a reliable approach to obtaining this property involve time-consuming procedures. Recent advancements in artificial neural networks (ANNs) have shown promise in simplifying this task by estimating it with high accuracy. Nevertheless, conventional ANNs often require deep networks to achieve acceptable results in cases with large datasets and where generalization is required for a variety of mixtures. This leads to increased training durations and susceptibility to noise, causing reduced accuracy and potential information loss in deep networks. In order to address these limitations, this study introduces a novel multi-lobar artificial neural network (MLANN) architecture inspired by the brain’s lobar processing of sensory information, aiming to improve the accuracy and efficiency of estimating concrete compressive strength. The MLANN framework employs various architectures of hidden layers, referred to as “lobes,” each with a unique arrangement of neurons to optimize data processing, reduce training noise, and expedite training time. Within the study context, an MLANN is developed, and its performance is evaluated to predict the compressive strength of concrete. Moreover, it is compared against two traditional cases, ANN and ensemble learning neural networks (ELNN). The study results indicated that the MLANN architecture significantly improves the estimation performance, reducing the root mean square error by up to 32.9% and mean absolute error by up to 25.9% while also enhancing the A20 index by up to 17.9%, ensuring a more robust and generalizable model. This advancement in model refinement can ultimately enhance the design and analysis processes in civil engineering, leading to more reliable and cost-effective construction practices.
- 15 January 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-17
Open AccessDeveloping a brain inspired multilobar neural networks architecture for rapidly and accurately estimating concrete compressive strength
Concrete compressive strength is a critical parameter in construction and structural engineering. Destructive experimental methods that offer a reliable approach to obtaining this property involve time-consuming procedures. Recent advancements in artificial neural networks (ANNs) have shown promise in simplifying this task by estimating it with high accuracy. Nevertheless, conventional ANNs often require deep networks to achieve acceptable results in cases with large datasets and where generalization is required for a variety of mixtures. This leads to increased training durations and susceptibility to noise, causing reduced accuracy and potential information loss in deep networks. In order to address these limitations, this study introduces a novel multi-lobar artificial neural network (MLANN) architecture inspired by the brain’s lobar processing of sensory information, aiming to improve the accuracy and efficiency of estimating concrete compressive strength. The MLANN framework employs various architectures of hidden layers, referred to as “lobes,” each with a unique arrangement of neurons to optimize data processing, reduce training noise, and expedite training time. Within the study context, an MLANN is developed, and its performance is evaluated to predict the compressive strength of concrete. Moreover, it is compared against two traditional cases, ANN and ensemble learning neural networks (ELNN). The study results indicated that the MLANN architecture significantly improves the estimation performance, reducing the root mean square error by up to 32.9% and mean absolute error by up to 25.9% while also enhancing the A20 index by up to 17.9%, ensuring a more robust and generalizable model. This advancement in model refinement can ultimately enhance the design and analysis processes in civil engineering, leading to more reliable and cost-effective construction practices.
- Open Access
- 1 January 2025
- Published by Walter de Gruyter GmbH in Open Geosciences
- Vol. 17 (1)
Applications of physics-informed neural networks in geosciences: From basic seismology to comprehensive environmental studies
Physics-informed neural networks (PINNs) have emerged as a powerful tool in the intersection of machine learning and physical sciences, offering novel approaches to solve complex differential equations inherent in geoscientific phenomena. Despite their growing application, a review of their applications and potential within geosciences remains missing. This review systematically examines the utilization of PINNs in various geosciences such as hydrology, seismology, atmospheric sciences, geophysics, and others, highlighting their ability to integrate physical laws into neural network training processes. It describes the potential of PINNs to improve predictive modeling accuracy, reduce computational costs, and overcome the limitations of traditional numerical methods. The importance of this research lies in its assessment of PINNs’ contributions to geosciences, offering valuable insights for researchers and practitioners seeking to use these advanced methodologies. The findings underscore the versatility and efficiency of PINNs, enhancing a deeper understanding of their role in advancing geoscientific research and applications. Ultimately, this review aims to bridge the current knowledge gap, promote the wider adoption and development of PINNs in geosciences, drive innovation, and enhance the accuracy and reliability of geoscientific models and predictions.
- 1 January 2025
- Published by Walter de Gruyter GmbH in Open Geosciences
- Vol. 17 (1)
Open AccessApplications of physics-informed neural networks in geosciences: From basic seismology to comprehensive environmental studies
Physics-informed neural networks (PINNs) have emerged as a powerful tool in the intersection of machine learning and physical sciences, offering novel approaches to solve complex differential equations inherent in geoscientific phenomena. Despite their growing application, a review of their applications and potential within geosciences remains missing. This review systematically examines the utilization of PINNs in various geosciences such as hydrology, seismology, atmospheric sciences, geophysics, and others, highlighting their ability to integrate physical laws into neural network training processes. It describes the potential of PINNs to improve predictive modeling accuracy, reduce computational costs, and overcome the limitations of traditional numerical methods. The importance of this research lies in its assessment of PINNs’ contributions to geosciences, offering valuable insights for researchers and practitioners seeking to use these advanced methodologies. The findings underscore the versatility and efficiency of PINNs, enhancing a deeper understanding of their role in advancing geoscientific research and applications. Ultimately, this review aims to bridge the current knowledge gap, promote the wider adoption and development of PINNs in geosciences, drive innovation, and enhance the accuracy and reliability of geoscientific models and predictions.
- Open Access
- 27 December 2024
- Published by Springer Nature in Advanced Modeling and Simulation in Engineering Sciences
- Vol. 11 (1) , 1-20
Prediction and parametric assessment of soil one-dimensional vertical free swelling potential using ensemble machine learning models
Investigating soil swelling potential is indeed a critical research area in geotechnical engineering, given its significant influence on the stability and longevity of civil structures. This study aims to predict and assess the one-dimensional vertical free swelling potential of soils using ensemble machine learning models. Within the study context, a large dataset encompassing a wide array of soil parameters from 210 soil samples, including moisture content, unit weight, plasticity, and clay content, will be used. These parameters are critical in understanding the swelling behavior of soils under varying environmental and load conditions. The novel approach of this research lies in the application of ensemble machine learning techniques, which offer a robust framework to analyze complex, nonlinear relationships within soil properties. Another key aspect of this research is the parametric assessment, where the influence of individual soil properties on swelling potential is investigated using feature importance and partial dependence analyses. These analyses provide valuable insights into the relative importance of different soil parameters on soil behavior. The outcomes of this study contribute to soil mechanics and machine learning applications in geotechnical engineering and offer practical implications for engineers and practitioners. Besides, the predictive models developed in this study aid in more informed decision-making in the design and construction of civil structures, particularly in swelling-prone areas.
- 27 December 2024
- Published by Springer Nature in Advanced Modeling and Simulation in Engineering Sciences
- Vol. 11 (1) , 1-20
Open AccessPrediction and parametric assessment of soil one-dimensional vertical free swelling potential using ensemble machine learning models
Investigating soil swelling potential is indeed a critical research area in geotechnical engineering, given its significant influence on the stability and longevity of civil structures. This study aims to predict and assess the one-dimensional vertical free swelling potential of soils using ensemble machine learning models. Within the study context, a large dataset encompassing a wide array of soil parameters from 210 soil samples, including moisture content, unit weight, plasticity, and clay content, will be used. These parameters are critical in understanding the swelling behavior of soils under varying environmental and load conditions. The novel approach of this research lies in the application of ensemble machine learning techniques, which offer a robust framework to analyze complex, nonlinear relationships within soil properties. Another key aspect of this research is the parametric assessment, where the influence of individual soil properties on swelling potential is investigated using feature importance and partial dependence analyses. These analyses provide valuable insights into the relative importance of different soil parameters on soil behavior. The outcomes of this study contribute to soil mechanics and machine learning applications in geotechnical engineering and offer practical implications for engineers and practitioners. Besides, the predictive models developed in this study aid in more informed decision-making in the design and construction of civil structures, particularly in swelling-prone areas.
- 16 August 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (11) , 8425-8438
The Role of Calcium-Based Additives in Bentonite Stabilization: A Comparative Evaluation
- 16 August 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (11) , 8425-8438
The Role of Calcium-Based Additives in Bentonite Stabilization: A Comparative Evaluation