Mohammed Hassani Zerrouk
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohammed Hassani Zerrouk has a total of 64 co-authors. Here are the top co-authors by number of shared publications:
- Fouad El Mansouri
Laboratory of Chemical Engineering and Resources Valorization (LGCVR), Faculty of Sciences and Techniques University Abdelmalek Essaadi Tangier Morocco
3 shared publications - Hicham Tikaoui
Laboratory for Research and Development in Engineering Sciences, FSTH, Abdelmalek Essaadi University, Tetouan, Morocco
3 shared publications Abdelhamid Ennoury
Laboratory of Biochemistry and Molecular Genetics, Faculty of Sciences and Technologies of Tangier, Tangier, Morocco
2 shared publications- Abderrahim El Mhouti
Abdelmalek Essaadi University
2 shared publications Ahde El Imache
Laboratory of Innovative Technologies, Process Engineering Department, Higher School of Technology Fez, USMBA, Fes, Morocco
2 shared publicationsAnass Kchikich
Laboratory of Analysis, Modeling, Engineering, Natural Substances and Environment, Polydisciplinary Faculty of Taroudant, Ibn Zohr University, Agadir, Morocco
2 shared publications
Latest Publications
- Open Access
- 23 October 2026
- Published by Elsevier in Atmospheric Environment
- Vol. 388
A multi-layered anomaly detection framework for volatile organic compounds (VOCs) in urban air quality monitoring
- 23 October 2026
- Published by Elsevier in Atmospheric Environment
- Vol. 388
Open AccessA multi-layered anomaly detection framework for volatile organic compounds (VOCs) in urban air quality monitoring
- 9 July 2026
- Published by IWA Publishing in Water Practice & Technology
- Vol. 21 (8) , 3485-3505
Machine learning-based prediction of biofouling and performance decline in reverse osmosis membranes treating urban wastewater
Flowchart illustrating a machine learning-based framework for predicting outcomes in a water-related system. The diagram shows input data sources (such as environmental or operational variables) feeding into data preprocessing steps, followed by model development using machine learning algorithms. The trained model generates predictions, which are evaluated and applied for decision-making or system optimization. Arrows indicate the sequential workflow from data input to final prediction and application. Biofouling in reverse osmosis (RO) membranes treating urban wastewater progressively reduces permeate flux, deteriorates salt rejection, and increases operational costs. To address this challenge, this study presents a novel machine learning-based surrogate modelling framework to predict RO membrane performance under non-disinfected wastewater conditions – an underexplored scenario with high environmental and industrial relevance, where biofouling is the primary performance driver. Using experimental data from a pilot-scale RO system, three algorithms were evaluated: Random Forest, Gradient Boosting, and Support Vector Regression. Gradient Boosting achieved the best results for flux prediction (R2 = 0.97, MAE = 0.56 L/m2·h), while Random Forest performed best for salt rejection (R2 = 0.65, MAE = 0.105). Operating time, temperature, and COD were identified as the most influential variables. The proposed models offer a practical tool for proactive maintenance and real-time monitoring in water reuse facilities, contributing to the sustainability of wastewater treatment processes.
- 9 July 2026
- Published by IWA Publishing in Water Practice & Technology
- Vol. 21 (8) , 3485-3505
Machine learning-based prediction of biofouling and performance decline in reverse osmosis membranes treating urban wastewater
Flowchart illustrating a machine learning-based framework for predicting outcomes in a water-related system. The diagram shows input data sources (such as environmental or operational variables) feeding into data preprocessing steps, followed by model development using machine learning algorithms. The trained model generates predictions, which are evaluated and applied for decision-making or system optimization. Arrows indicate the sequential workflow from data input to final prediction and application. Biofouling in reverse osmosis (RO) membranes treating urban wastewater progressively reduces permeate flux, deteriorates salt rejection, and increases operational costs. To address this challenge, this study presents a novel machine learning-based surrogate modelling framework to predict RO membrane performance under non-disinfected wastewater conditions – an underexplored scenario with high environmental and industrial relevance, where biofouling is the primary performance driver. Using experimental data from a pilot-scale RO system, three algorithms were evaluated: Random Forest, Gradient Boosting, and Support Vector Regression. Gradient Boosting achieved the best results for flux prediction (R2 = 0.97, MAE = 0.56 L/m2·h), while Random Forest performed best for salt rejection (R2 = 0.65, MAE = 0.105). Operating time, temperature, and COD were identified as the most influential variables. The proposed models offer a practical tool for proactive maintenance and real-time monitoring in water reuse facilities, contributing to the sustainability of wastewater treatment processes.
- 2 July 2026
- Published by Springer Nature
- p. 32-47
AI-Powered Energy Management Diagnostics: Expert System Integration with LLM for Predictive Maintenance
- 2 July 2026
- Published by Springer Nature
- p. 32-47
AI-Powered Energy Management Diagnostics: Expert System Integration with LLM for Predictive Maintenance
- 2 July 2026
- Published by Springer Nature
- p. 1-8
Vision-Based Angle Detection for Industrial Quality Inspection
- 2 July 2026
- Published by Springer Nature
- p. 1-8
Vision-Based Angle Detection for Industrial Quality Inspection
- Open Access
- 1 October 2024
- Published by Wydawnictwo Naukowe Gabriel Borowski (WNGB) in Ecological Engineering & Environmental Technology
- Vol. 25 (10) , 194-205
Assessing the Effects of Water Scarcity and Biofertilizer Application (Pseudomonas putida) on the Growth and Productivity of Different Eggplant (Solanum melongena) Genotypes in Northeastern Morocco
Drought had affected the crops production in Morocco, during the last decade. Plants breeding is still a solution to increase crops tolerance for water scarcity. Using natural biofertilizer based on microorganisms still a good practice to enhance the resilience of agriculture to drought. The...
- 1 October 2024
- Published by Wydawnictwo Naukowe Gabriel Borowski (WNGB) in Ecological Engineering & Environmental Technology
- Vol. 25 (10) , 194-205
Open AccessAssessing the Effects of Water Scarcity and Biofertilizer Application (Pseudomonas putida) on the Growth and Productivity of Different Eggplant (Solanum melongena) Genotypes in Northeastern Morocco
Drought had affected the crops production in Morocco, during the last decade. Plants breeding is still a solution to increase crops tolerance for water scarcity. Using natural biofertilizer based on microorganisms still a good practice to enhance the resilience of agriculture to drought. The...
- 4 June 2024
- Published by Springer Nature in Waste and Biomass Valorization
- Vol. 15 (11) , 6171-6190
Biostimulant Effect of Sargassum Vulgare Extract on morpho-physiological and Biochemical Traits of Salt-stressed Tomato Plants (Solanum Lycopersicum L)
- 4 June 2024
- Published by Springer Nature in Waste and Biomass Valorization
- Vol. 15 (11) , 6171-6190
Biostimulant Effect of Sargassum Vulgare Extract on morpho-physiological and Biochemical Traits of Salt-stressed Tomato Plants (Solanum Lycopersicum L)
- 1 June 2024
- Published by Springer Nature
- p. 135-142
Continuous Approximation of Stochastic Petri Nets: Adaptive Maximal Firing Speeds
- 1 June 2024
- Published by Springer Nature
- p. 135-142
Continuous Approximation of Stochastic Petri Nets: Adaptive Maximal Firing Speeds
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2814 (1) , 040012
Limits of direct fluidification of stochastic Petri nets by timed CPNs
The Markov models and stochastic Petri nets have demonstrated their capabilities for the concrete analysis of reliability in many industrial processes. However,
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2814 (1) , 040012
Open AccessLimits of direct fluidification of stochastic Petri nets by timed CPNs
The Markov models and stochastic Petri nets have demonstrated their capabilities for the concrete analysis of reliability in many industrial processes. However,
- Open Access
- 3 October 2022
- Published by MDPI AG in Separations
- Vol. 9 (10) , 283
Efficient Removal of Eriochrome Black T Dye Using Activated Carbon of Waste Hemp (Cannabis sativa L.) Grown in Northern Morocco Enhanced by New Mathematical Models
In the present work, the adsorption behavior of Eriochrome Black T (EBT) on waste hemp activated carbon (WHAC) was examined. The surface of the WHAC was modified by H3PO4 acid treatment. The surface and structural characterization of the adsorbents was carried out using Fourier transform infrared spectroscopy (FTIR), and scanning electron microscopy (SEM) analysis. The effect of influential adsorption parameters (pH, contact time, dosage, and initial concentration) on the adsorption of EBT onto WHAC was examined in batch experiments; some adsorption parameters such as pH, concentration and dose were improved by new mathematical models. The adsorption behavior of EBT on the surfaces of WHAC was evaluated by applying different isotherm models (Langmuir, Freundlich, Temkin and Dubinin–Radushkevich) to equilibrium data. The adsorption kinetics was studied by using pseudo-first-order, pseudo-second-order, Elovich and intraparticle models on the model. Adsorption followed the pseudo-second-order rate kinetics. The maximum removal of EBT was found to be 44–62.08% by WHAC at pH = 7, adsorbent dose of 10–70 mg, contact time of 3 h and initial dye concentration of 10 mg.L−1. The maximum adsorption capacities were 14.025 mg.g−1 obtained by calculating according to the Langmuir model, while the maximum removal efficiency was obtained at 70 mg equal to 62.08% for the WHAC. The adsorption process is physical in the monolayer and multilayer.
- 3 October 2022
- Published by MDPI AG in Separations
- Vol. 9 (10) , 283
Open AccessEfficient Removal of Eriochrome Black T Dye Using Activated Carbon of Waste Hemp (Cannabis sativa L.) Grown in Northern Morocco Enhanced by New Mathematical Models
In the present work, the adsorption behavior of Eriochrome Black T (EBT) on waste hemp activated carbon (WHAC) was examined. The surface of the WHAC was modified by H3PO4 acid treatment. The surface and structural characterization of the adsorbents was carried out using Fourier transform infrared spectroscopy (FTIR), and scanning electron microscopy (SEM) analysis. The effect of influential adsorption parameters (pH, contact time, dosage, and initial concentration) on the adsorption of EBT onto WHAC was examined in batch experiments; some adsorption parameters such as pH, concentration and dose were improved by new mathematical models. The adsorption behavior of EBT on the surfaces of WHAC was evaluated by applying different isotherm models (Langmuir, Freundlich, Temkin and Dubinin–Radushkevich) to equilibrium data. The adsorption kinetics was studied by using pseudo-first-order, pseudo-second-order, Elovich and intraparticle models on the model. Adsorption followed the pseudo-second-order rate kinetics. The maximum removal of EBT was found to be 44–62.08% by WHAC at pH = 7, adsorbent dose of 10–70 mg, contact time of 3 h and initial dye concentration of 10 mg.L−1. The maximum adsorption capacities were 14.025 mg.g−1 obtained by calculating according to the Langmuir model, while the maximum removal efficiency was obtained at 70 mg equal to 62.08% for the WHAC. The adsorption process is physical in the monolayer and multilayer.