Applied Chemical Engineering

AI-based prediction of the optimal incorporation rate of dredged sediments in concrete: Mechanical performance analysis

Khadija Benhaddou

Laboratory of Applied Geophysics, Geotechnics, Engineering Geology, and Environmental (L3GIE), Mohammadia Engineering School, Mohammed V University in Rabat, Avenue Ibn Sina, BP 765, Agdal, Rabat, 10000, Morocco

Ayoub Souileh

Laboratory of Applied Geophysics, Geotechnics, Engineering Geology, and Environmental (L3GIE), Mohammadia Engineering School, Mohammed V University in Rabat, Avenue Ibn Sina, BP 765, Agdal, Rabat, 10000, Morocco

Achraf Mabrouk

LAFH, Faculty of Sciences and Techniques, Hassan 1st University, BP 577, Settat, 26000, Morocco

Latifa Ouadif

Laboratory of Applied Geophysics, Geotechnics, Engineering Geology, and Environmental (L3GIE), Mohammadia Engineering School, Mohammed V University in Rabat, Avenue Ibn Sina, BP 765, Agdal, Rabat, 10000, Morocco

Sabihi Abdelhak

Experimental Center for Major Works, Public Laboratory for Testing and Studies (LPEE), Casablanca, 20250, Morocco

Khadija Baba

Civil and Environmental Engineering Laboratory (LGCE), Mohammadia Engineering School, Mohammed V University in Rabat, Avenue Ibn Sina, BP 765, Agdal, Rabat, 10000, Morocco

Mustapha Rharouss

Laboratory of Applied Geophysics, Geotechnics, Engineering Geology, and Environmental (L3GIE), Mohammadia Engineering School, Mohammed V University in Rabat, Avenue Ibn Sina, BP 765, Agdal, Rabat, 10000, Morocco

Azzeddine Imali

Regional Directorate of Equipment, Transport, and Logistics of Rabat-Salé-Kénitra (DRETL RSK), Ministry of Equipment and Water, Avenue Al Araar, Hay Riad, Rabat, 10100, Morocco

DOI: https://doi.org/10.59429/ace.v8i2.5639

Keywords: random forests; experimental data; optimal incorporation percentage; model predictions; artificial intelligence; compressive strength

---

Abstract

The management of marine dredged sediments is a critical environmental and economic issue, particularly in port cities where dredging is a necessary activity to maintain navigability. These sediments are typically viewed as waste products and often require costly and environmentally challenging disposal methods. However, repurposing dredged sediments as a component in concrete production presents a promising solution for both waste management and the creation of sustainable construction materials. Despite this potential, determining the optimal percentage of sediment incorporation and accurately predicting the mechanical properties, such as compressive strength, remain significant challenges. This study proposes an artificial intelligence (AI)-based approach to predict the optimal incorporation percentage of marine dredged sediments from Moroccan ports into concrete and to forecast the resulting compressive strength. A dataset consisting of 104 samples, including dune sand and port sediments from JEBHA, was used. The data includes key properties such as granulometry, cleanliness, fineness modulus, and the compressive strength of the concrete mixtures. These experimental data were employed to train and validate several machine learning models, including linear regression, Random Forest, Gradient Boosting, and XGBoost, chosen for their ability to model complex, non-linear relationships between sediment characteristics and concrete performance. The performance of these models was evaluated using two key metrics: the coefficient of determination (R²) and the root mean square error (RMSE). Among the models tested, the Random Forest Regressor delivered the best results, with an R² value greater than 0.98 and an RMSE of less than 0.20 MPa, indicating highly accurate predictions of both the optimal sediment incorporation rate and the compressive strength of the concrete. This model’s exceptional performance underscores its potential as a reliable tool for optimizing the use of dredged sediments in concrete production. The findings of this study demonstrate the considerable potential of AI in optimizing the incorporation of marine dredged sediments into concrete. By accurately predicting the mechanical properties of the resulting material, this approach enables the development of more sustainable construction practices while reducing the environmental burden associated with sediment disposal. Moreover, this work illustrates the broader applicability of AI in addressing environmental challenges, offering a pathway to valorize waste materials in the construction industry. The study not only advances our understanding of sediment utilization in concrete but also contributes to the growing field of sustainable material science, offering promising avenues for future research and development.

Nevertheless, further research is needed to validate the model’s scalability to other sediment types and assess practical limitations in industrial applications.

---

References

[1]. Benhaddou K, Souileh A, Mabrouk A, Ouadif L, Abdelhak S, Baba K et al. Sustainable valorization of marine dredged sediments from Jebha port as a partial sand replacement in eco-friendly concrete. Journal of Ecological Engineering. 2025;26(6).

[2]. Safhi AEM, Mejjad N, El FadilI H, Bortali M (2024) Dredged materials in Morocco: Current practices, policies, and roadmap for sustainable management. Case Studies in Construction Materials 20:e03045. https://doi.org/10.1016/j.cscm.2024.e03045

[3]. Zhao Z, Benzerzour M, Abriak N-E, et al (2018) Use of uncontaminated marine sediments in mortar and concrete by partial substitution of cement. Cement and Concrete Composites 93:155–162. https://doi.org/10.1016/j.cemconcomp.2018.07.010

[4]. Soleimani T, Hayek M, Junqua G, et al (2023) Environmental, economic and experimental assessment of the valorization of dredged sediment through sand substitution in concrete. Science of The Total Environment 858:159980. https://doi.org/10.1016/j.scitotenv.2022.159980

[5]. Chou J-S, Lin J-W (2020) Risk-Informed Prediction of Dredging Project Duration Using Stochastic Machine Learning. Water 12:1643. https://doi.org/10.3390/w12061643

[6]. Safhi AEM, Dabiri H, Soliman A, Khayat KH (2024) Prediction of self-consolidating concrete properties using XGBoost machine learning algorithm: Rheological properties. Powder Technology 438:119623. https://doi.org/10.1016/j.powtec.2024.119623

[7]. Segovia JA, Toaquiza JF, Llanos JR, Rivas DR (2023) Meteorological Variables Forecasting System Using Machine Learning and Open-Source Software. Electronics 12:1007. https://doi.org/10.3390/electronics12041007

[8]. Jianing P, Bai K, Solangi YA, et al (2024) Examining the role of digitalization and technological innovation in promoting sustainable natural resource exploitation. Resources Policy 92:105036. https://doi.org/10.1016/j.resourpol.2024.105036

[9]. Cui Y, Wang L, Liu J, et al (2022) Impact of particle size of fly ash on the early compressive strength of concrete: Experimental investigation and modelling. Construction and Building Materials 323:126444. https://doi.org/10.1016/j.conbuildmat.2022.126444

[10]. Zhou A, Chen J, Li K, et al (2024) Developing green and economical low-alkalinity seawater sea sand concrete via innovative processing underground sediment. Journal of Cleaner Production 443:140927. https://doi.org/10.1016/j.jclepro.2024.140927

[11]. Afolayan A, Mildner M, Hotěk P, et al (2024) Characterization of Mineralogical and Mechanical Parameters of Alkali-Activated Materials Based on Water Sediments Activated by Potassium Silicate. Buildings 14:3077. https://doi.org/10.3390/buildings14103077

[12]. Hongwei Wang RZ, Wang D (2023) Predicting the compaction parameters of solidified dredged fine sediments with statistical approach. Marine Georesources & Geotechnology 41:195–210. https://doi.org/10.1080/1064119X.2021.2023827

[13]. Barhrhouj A, Ananou B, Ouladsine M (2025) Assessing the Impact of Temporal Data Aggregation on the Reliability of Predictive Machine Learning Models. In: Julian V, Camacho D, Yin H, et al (eds) Intelligent Data Engineering and Automated Learning – IDEAL 2024. Springer Nature Switzerland, Cham, pp 481–492

[14]. James G, Witten D, Hastie T, et al (2023) Linear Regression. In: An Introduction to Statistical Learning. Springer International Publishing, Cham, pp 69–134

[15]. Kang M-C, Yoo D-Y, Gupta R (2021) Machine learning-based prediction for compressive and flexural strengths of steel fiber-reinforced concrete. Construction and Building Materials 266:121117. https://doi.org/10.1016/j.conbuildmat.2020.121117

[16]. Chicco D, Warrens MJ, Jurman G (2021) The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science 7:e623. https://doi.org/10.7717/peerj-cs.623

[17]. Hodson TO (2022) Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not. Geosci Model Dev 15:5481–5487. https://doi.org/10.5194/gmd-15-5481-2022

[18]. Robeson SM, Willmott CJ (2023) Decomposition of the mean absolute error (MAE) into systematic and unsystematic components. PLoS ONE 18:e0279774. https://doi.org/10.1371/journal.pone.0279774

[19]. Ali R, Muayad M, Mohammed AS, Asteris PG (2023) Analysis and prediction of the effect of Nanosilica on the compressive strength of concrete with different mix proportions and specimen sizes using various numerical approaches. Structural Concrete 24:4161–4184. https://doi.org/10.1002/suco.202200718

[20]. Benayad A, Bikri S, Hindi Z, et al (2024) Transition toward Sustainability in the Moroccan Food System: Drivers, Outcomes, and Challenges. World 5:627–644. https://doi.org/10.3390/world5030032

[21]. Achour R, Zentar R, Abriak N-E, et al (2019) Durability study of concrete incorporating dredged sediments. Case Studies in Construction Materials 11:e00244. https://doi.org/10.1016/j.cscm.2019.e00244

[22]. Alloul A High-performance geopolymer and low-carbon cementitious binders using flash-calcined dredged sediments and excavated clays