Mohamed Ghrici
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mohamed Ghrici has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Amar Benyahia
University of Chlef
2 shared publications- Mohamed Said Mansour
Civil Engineering Department, Geomaterials Laboratory, University of Hassiba Benbouali, Chlef, Algeria
2 shared publications Said Choucha
Department of Civil Engineering Hassiba Benbouali University of Chlef P.O. Box c 78 : 02180 Chlef Algeria
2 shared publicationsAli Benzaamia
Geomaterials Laboratory, Civil Engineering Department, Hassiba Benbouali University, Chlef, Algeria
1 shared publicationBillal Sari Ahmed
Geomaterials Laboratory, Civil Engineering Department, Hassiba Benbouali University, Chlef, Algeria
1 shared publicationJamal Khatib
Department of Civil Engineering Beirut Arab University Beirut Lebanon
1 shared publication
Latest Publications
- Open Access
- 9 September 2025
- Published by Springer Nature in Journal of Engineering and Applied Science
- Vol. 72 (1) , 1-25
Interpretable machine learning for predicting compression index of clays using SHAP and gradient boosting models
This study introduces a novel, interpretable machine learning framework for predicting the compression index (Cc) of clay soils by integrating three advanced gradient boosting algorithms—XGBoost, CatBoost, and LightGBM—with SHapley Additive exPlanations (SHAP). A comprehensive dataset of 1,243 clay samples, compiled from peer-reviewed literature, includes four geotechnical input variables: plastic limit (PL), plasticity index (PI), initial void ratio (e₀) and water content (w). Data were standardized and partitioned into training (70%) and testing (30%) subsets. Model development employed fivefold cross-validation and Optuna-based hyperparameter optimization. Among the models, XGBoost demonstrated the highest generalization capability, achieving an R2 of 0.913, RMSE of 0.197, and MAE of 0.100 on the test set. SHAP analysis revealed that initial void ratio (e₀) and water content (w) were the most influential features, with mean SHAP values of 0.20 and 0.10, respectively, aligning with established geotechnical principles. The proposed framework enhances transparency in machine learning predictions by making the model’s decision process understandable, thereby addressing the limitations of traditional “black-box” AI. It offers a reliable and efficient alternative to conventional oedometer testing, particularly beneficial for preliminary geotechnical design where timely and interpretable predictions are essential. Graphical Abstract
- 9 September 2025
- Published by Springer Nature in Journal of Engineering and Applied Science
- Vol. 72 (1) , 1-25
Open AccessInterpretable machine learning for predicting compression index of clays using SHAP and gradient boosting models
This study introduces a novel, interpretable machine learning framework for predicting the compression index (Cc) of clay soils by integrating three advanced gradient boosting algorithms—XGBoost, CatBoost, and LightGBM—with SHapley Additive exPlanations (SHAP). A comprehensive dataset of 1,243 clay samples, compiled from peer-reviewed literature, includes four geotechnical input variables: plastic limit (PL), plasticity index (PI), initial void ratio (e₀) and water content (w). Data were standardized and partitioned into training (70%) and testing (30%) subsets. Model development employed fivefold cross-validation and Optuna-based hyperparameter optimization. Among the models, XGBoost demonstrated the highest generalization capability, achieving an R2 of 0.913, RMSE of 0.197, and MAE of 0.100 on the test set. SHAP analysis revealed that initial void ratio (e₀) and water content (w) were the most influential features, with mean SHAP values of 0.20 and 0.10, respectively, aligning with established geotechnical principles. The proposed framework enhances transparency in machine learning predictions by making the model’s decision process understandable, thereby addressing the limitations of traditional “black-box” AI. It offers a reliable and efficient alternative to conventional oedometer testing, particularly beneficial for preliminary geotechnical design where timely and interpretable predictions are essential. Graphical Abstract
- Open Access
- 27 December 2024
- Published by Bentham Science Publishers Ltd. in The Open Civil Engineering Journal
- Vol. 18 (1)
Effect of Silica Fume on the Performances of Self-compacting Repair Mortar
Background: Concrete is a widely utilized material in construction worldwide. However, concrete performance could be damaged under aggressive environments, therefore, many concrete structures may require repair and frequent maintenance. Objective: The aim of this study is to develop reinforced Self-Consolidating Repair Mortars (SCRMs) incorporating silica fume and polypropylene fibers. Methods: This research aimed to study the effect of silica fume as an alternative supplementary cementitious material (SCM) on the performance of fiber reinforced self-consolidating repair mortars (SCRMs). For this purpose, five SCRMs mixes incorporating 0%, 5%, 10%, 15%, and 20% of silica fume as partial cement replacement were prepared. Testing included slump flow, flow time, and unit weight, air-dry unit weight, compressive and flexural strengths, dynamic modulus of elasticity and water absorption. Results: The results indicated that the substitution of cement by 15% of silica fume improves the flexural strength and slightly reduce the compressive strength of the fiber-reinforced repair mortar. The lowest values of total shrinkage, water capillary absorption, and sorptivity were observed for repair mortars containing 10% silica fume. In addition, bonding results between repair mortars containing silica fume and old concrete substrate investigated by the bond flexural strength test showed good interlocking, justifying the effectiveness of these produced mortars. Conclusion: The results reveal that structural repair mortars containing 10 and 15% silica fume conform to the performance requirements of class R4 materials (European Standard EN 1504-3) and could be used in repair applications.
- 27 December 2024
- Published by Bentham Science Publishers Ltd. in The Open Civil Engineering Journal
- Vol. 18 (1)
Open AccessEffect of Silica Fume on the Performances of Self-compacting Repair Mortar
Background: Concrete is a widely utilized material in construction worldwide. However, concrete performance could be damaged under aggressive environments, therefore, many concrete structures may require repair and frequent maintenance. Objective: The aim of this study is to develop reinforced Self-Consolidating Repair Mortars (SCRMs) incorporating silica fume and polypropylene fibers. Methods: This research aimed to study the effect of silica fume as an alternative supplementary cementitious material (SCM) on the performance of fiber reinforced self-consolidating repair mortars (SCRMs). For this purpose, five SCRMs mixes incorporating 0%, 5%, 10%, 15%, and 20% of silica fume as partial cement replacement were prepared. Testing included slump flow, flow time, and unit weight, air-dry unit weight, compressive and flexural strengths, dynamic modulus of elasticity and water absorption. Results: The results indicated that the substitution of cement by 15% of silica fume improves the flexural strength and slightly reduce the compressive strength of the fiber-reinforced repair mortar. The lowest values of total shrinkage, water capillary absorption, and sorptivity were observed for repair mortars containing 10% silica fume. In addition, bonding results between repair mortars containing silica fume and old concrete substrate investigated by the bond flexural strength test showed good interlocking, justifying the effectiveness of these produced mortars. Conclusion: The results reveal that structural repair mortars containing 10 and 15% silica fume conform to the performance requirements of class R4 materials (European Standard EN 1504-3) and could be used in repair applications.
- 19 May 2018
- Published by Springer Nature in Asian Journal of Civil Engineering
- Vol. 19 (5) , 639-646
Correlation between compressive strength and other properties of engineered cementitious composites with high-volume natural pozzolana
- 19 May 2018
- Published by Springer Nature in Asian Journal of Civil Engineering
- Vol. 19 (5) , 639-646
Correlation between compressive strength and other properties of engineered cementitious composites with high-volume natural pozzolana
- 27 May 2017
- Published by Springer Nature in Frontiers of Structural and Civil Engineering
- Vol. 12 (3) , 261-269
Effect of natural pozzolan content on the properties of engineered cementitious composites as repair material
- 27 May 2017
- Published by Springer Nature in Frontiers of Structural and Civil Engineering
- Vol. 12 (3) , 261-269
Effect of natural pozzolan content on the properties of engineered cementitious composites as repair material