Abstract
This study demonstrated the application of a hybrid Bayesian algorithm (BA) and support vector regression (SVR) as a potential super-learner tool (BA-SVR) to predict biohydrogen production from food waste-originated feedstocks. The novelty of the present approach, as compared to the existing response surface methodology (RSM), includes (i) hybridization of BA with SVR for modeling of biohydrogen production and minimization of biomethane formation, (ii) performance evaluation and comparison of the developed BA-SVR models with the existing RSM models based on the several indicators such as coefficient of determination (R2), relative error (RE), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE), (iii) analysis of the robustness of the model and (iv) testing generalization ability. The calculated values of these indicators suggested that the proposed super leaner models demonstrated better performance predicting the biohydrogen and biomethane (products) responses than those using the existing RSM models - as reported in Rafieenia et al. 2019 [45]. The estimated low errors for biohydrogen: MAE = 0.5919, RMSE = 0.592, MAPE = 11.1387; for biomethane: MAE = 0.2681, RMSE = 0.2688, MAPE = 0.3708, signifie the reliable model predictions. The BA-SVR model also provided high adj R2 (>0.99 for both biohydrogen and biomethane), indicating an excellent fitting of the model. Concerning the MAPE, the proposed BA-SVR models for both the biohydrogen and biomethane responses showed superior performances (as compared to the RSM models) with a performance enhancement of 64.16% and 98.81%, respectively.
| Original language | English |
|---|---|
| Pages (from-to) | 18586-18600 |
| Number of pages | 15 |
| Journal | International Journal of Hydrogen Energy |
| Volume | 48 |
| Issue number | 49 |
| DOIs | |
| State | Published - 8 Jun 2023 |
Bibliographical note
Funding Information:All authors would like to thank the Deputyship for Research & Innovation, Ministry of Education in Saudi Arabia, for funding this research work through project number RDO-2019-001-CSIT. S. M. Zakir Hossain would also like to acknowledge the Department of Chemical Engineering at the University of Bahrain.
Funding Information:
Further, the residual analyses (relative error vs. observation and residual vs. observation) were conducted to compare the performance of the proposed BA-SVR super learner models to the existing RSM models. The comparative results of the residual analysis are shown in Fig. 6. Generally, the model is acceptable if the relative errors or residuals are dispersed across a zero reference line. Clearly, all the relative errors (see Fig. 6a–b) and residuals (see Fig. 6c–d) plots for the BA-SVR models specify that both the relative errors and residuals are better scattered around the zero-reference line with minimal deviations than RSM models, supporting the reliability and validity of the developed models.All authors would like to thank the Deputyship for Research & Innovation, Ministry of Education in Saudi Arabia, for funding this research work through project number RDO-2019-001-CSIT. S. M. Zakir Hossain would also like to acknowledge the Department of Chemical Engineering at the University of Bahrain.
Publisher Copyright:
© 2023 Hydrogen Energy Publications LLC
Keywords
- Bayesian algorithm
- Biohydrogen
- Biomethane
- Food waste
- Machine learning
- Support vector regression
ASJC Scopus subject areas
- Renewable Energy, Sustainability and the Environment
- Fuel Technology
- Condensed Matter Physics
- Energy Engineering and Power Technology
