EUVIMEDEUVIMED entdecken
Crossref

A generalized hybrid machine learning framework for predicting biohydrogen production via dark fermentation of organic wastes

Nour Elislam Mougari, Djamal Eddine Ghersi, Farida Iachachene, Jean François Largeau, Müslüm Arici

Bioprocess and Biosystems Engineering · 2026-02 · 49 (2) · 351-372

DOI: 10.1007/s00449-025-03255-w ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioprocess and Biosystems Engineering, online erschienen am 08.11.2025. Verfasst von Nour Elislam Mougari und 4 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Energy, Mechanics and Engineering (LEMI), Department of Mechanical Engineering, Faculty of Technology, University M'Hamed Bougara Boume…. Hauptthemen laut MEDLINE: Machine Learning, Fermentation, Hydrogen, Neural Networks, Computer. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 68 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rising global demand for sustainable energy has directed significant attention towards biohydrogen production via dark fermentation of organic wastes. Accurate yield prediction is crucial for optimizing process conditions and enhancing overall process. This study aims to develop a robust and interpretable predictive framework that integrates kinetic modeling with a hybrid Bayesian Optimization-Artificial Neural Network (BO-ANN) approach for precise biohydrogen yield prediction. The core novelty lies in representing each substrate not as a simple category, but by its quantitative kinetic parameters from the Modified Gompertz equation, providing a biologically meaningful input. A comprehensive database compiled from the literature incorporates key process variables, including temperature, pH, residence time, and substrate concentration, along with kinetic parameters from the Modified Gompertz equation characterizing each substrate. The BO algorithm was employed to optimize the ANN architecture, and 5-fold cross-validation was used to evaluate model generalization ability. The proposed hybrid model achieved outstanding predictive performance (R² = 0.9980, RMSE = 0.0117, MAE = 0.0062), confirming its accuracy and robustness. Furthermore, SHAP analysis and correlation metrics provided interpretable insights into feature contributions, particularly the relevance of kinetic descriptors. Overall, the proposed BO-ANN framework offers a scalable, interpretable, and biologically grounded tool to improve predictive accuracy and support the design of more efficient and sustainable biohydrogen production systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningFermentationHydrogenNeural Networks, ComputerKineticsAlgorithmsBayes Theorem

Stichwörter der Autor:innen

Artificial neural networkBayesian optimizationBiohydrogen productionDark fermentationKinetic modeling

Substanzen

Hydrogen

Autor:innen und Institutionen

  • Laboratory of Energy, Mechanics and Engineering (LEMI), Department of Mechanical Engineering, Faculty of Technology, University M'Hamed Bougara Boumerdes (UMBB), Frantz Fanon city, 35000, Boumerdes, Algeria. n.mougari@u…
  • Laboratory of Theoretical and Applied Fluid Mechanics, Faculty of Physics, University of Science and Technology Houari Boumediene, BP 32 Bab Ezzouar, 16111, Algiers, Algeria.
  • Laboratory of Energy, Mechanics and Engineering (LEMI), Department of Mechanical Engineering, Faculty of Technology, University M'Hamed Bougara Boumerdes (UMBB), Frantz Fanon city, 35000, Boumerdes, Algeria.
  • Earth Physics Laboratory, Faculty of Hydrocarbon and Chemistry, University M'Hamed Bougara Boumerdes, 35000, Boumerdes, Algeria.
  • Icam School of Engineering, Nantes Campus, 35 av. du Champ de Manoeuvres, 44470, Carquefou, France.
  • IMT Atlantique, GEPEA UMR CNRS 6144, F-44307, Nantes, France.

Zitieren

APA

Mougari, N. E., Ghersi, D. E., Iachachene, F., Largeau, J. F., & Arici, M. (2026). A generalized hybrid machine learning framework for predicting biohydrogen production via dark fermentation of organic wastes. Bioprocess and Biosystems Engineering, 49(2), 351-372. https://doi.org/10.1007/s00449-025-03255-w

Vancouver

Mougari NE, Ghersi DE, Iachachene F, Largeau JF, Arici M. A generalized hybrid machine learning framework for predicting biohydrogen production via dark fermentation of organic wastes. Bioprocess and Biosystems Engineering. 2026;49(2):351-372. doi:10.1007/s00449-025-03255-w

BibTeX
@article{Mougari2026,
  author = {Mougari, Nour Elislam and Ghersi, Djamal Eddine and Iachachene, Farida and Largeau, Jean François and Arici, Müslüm},
  title = {A generalized hybrid machine learning framework for predicting biohydrogen production via dark fermentation of organic wastes},
  journal = {Bioprocess and Biosystems Engineering},
  year = {2026},
  volume = {49},
  number = {2},
  pages = {351--372},
  doi = {10.1007/s00449-025-03255-w}
}
Kostenlos starten →