Predicting biomass Gasification outputs with the aid of machine-learning

Document Type : Research Paper

Authors

1 Department of Mechanical Engineering of Agricultural Machinery, Faculty of Agricultural Engineering and Technology, College of Agriculture and Natural Resources, University of Tehran, Iran

2 Department of Mechanical Engineering of Agricultural Machinery, Faculty of Agricultural Engineering and Technology, College of Agriculture and Natural Resources, University of Tehran,

3 Department of Mechanical Engineering of Agricultural Machinery, Faculty of Agricultural Engineering and Technology, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran

Abstract

Optimizing existing technologies in this field has become inevitable with the increasing demand for renewable energy sources. Among the renewable resources that have attracted much attention in research, biomass resources can be mentioned. In this study, an attempt has been made to examine one of the technologies for extracting energy from biomass resources - gasification - and to optimize and control this technology as much as possible, after forming a database extracted from a comprehensive review of related articles, its outputs have been predicted using several techniques in the field of artificial intelligence and machine learning. The statistical artificial intelligence methods used in this study were selected after reviewing similar articles. They included linear regression, gradient boosting regression, decision tree regression, random forest regression, support vector regression, and kernel ridge regression. Finally, this research resulted in several AI-based forecasting models with different forecast accuracies, which were evaluated with the relevant statistical parameters. Among the aforementioned machine learning techniques and considering the various parameters for evaluating the accuracy of the models, the most important of which is the squared error in the test data, the linear regression, gradient boosting regression, and random forest regression methods, whose squared error rates in each of the models were 0.909, 0.829, and 0.818, respectively, showed better performance than other proposed technologies.

Keywords

Main Subjects

EXTENDED ABSTRACT

 

Introduction

With the increasing demand for renewable energy sources, the optimization of existing technologies in this field has become inevitable. Among different renewable energy sources, biomass showed great potential possessing features such as being abundant, environmental-friendly (e.g. lower environmental impact, being carbon-neutral, etc.), low-cost, and producing a wide variety of desirable products. The mentioned advantageous characteristics resulted in its importance in the current global energy supply and accountability for above 70 percent of green energy production.

Materials and Methods

In this research, an attempt has been made to examine one of the technologies for extracting energy from biomass sources - gasification - and in order to optimize and control this technology as much as possible, after gathering data and making the database, its outputs by using several techniques in the field of artificial intelligence and learning Machines are predicted. The statistical artificial intelligence methods used in this research were selected after reviewing similar articles and include linear regression (LR), gradient boosting regression (GBR), decision tree regression (DTR), random forest regression (RFR), Support vector regression (SVR) and kernel Ridge Regression (KRR).

Results and Discussion

Machine learning (ML) shows great potential for being a fast, relatively inexpensive, and accurate approach to predicting gasification outputs. Although some efforts have been made to predict the effect of control parameters on the gasification output, this paper offers a comprehensive approach to evaluate the relationship between different biomass precursor characteristics and the energy output of the gasification process with the aid of different data-driven ML techniques. Finally, this research resulted in several prediction models based on artificial intelligence with different prediction accuracies. Among the mentioned machine learning techniques and taking into account various parameters for assessing the accuracy of models, among the most important of which we can mention the square error in the test data, linear regression (LR), gradient boosting regression (GBR) and Random Forest Regression (RFR) with r-squared of 0.909, 0/829 and 0/818  performed better than the rest of the proposed technologies.

Conclusion

This research resulted in several prediction models based on artificial intelligence with different prediction accuracies. Among the mentioned machine learning techniques and taking into account various parameters for assessing the accuracy of models, among the most important of which we can mention the square error in the test data, linear regression (LR), gradient boosting regression (GBR) and Random Forest Regression (RFR) with r-squared of 0.909, 0.829 and 0.818  performed better than the rest of the proposed technologies.

Author Contributions

All authors contributed equally to the conceptualization of the article and writing of the original and subsequent drafts.

Data Availability  Statement

Data available on request from the authors.

Ethical considerations

The study was approved by the Ethics Committee of the University of ABCD (Ethical code: IR.UT.RES.2024.500). The authors avoided data fabrication, falsification, plagiarism, and misconduct.

Conflict of interest

The author declares no conflict of interest.

References

Akbarian, A., Andooz, A., Kowsari, E., Ramakrishna, S., Asgari, S., & Cheshmeh, Z. A. (2022a). Challenges and opportunities of lignocellulosic biomass gasification in the path of circular bioeconomy. Bioresource Technology, 362(August), 127774. https://doi.org/10.1016/j.biortech.2022.127774
Akbarian, A., Andooz, A., Kowsari, E., Ramakrishna, S., Asgari, S., & Cheshmeh, Z. A. (2022b). Challenges and opportunities of lignocellulosic biomass gasification in the path of circular bioeconomy. Bioresource Technology, 362, 127774. https://doi.org/https://doi.org/10.1016/j.biortech.2022.127774
Alfarra, F., Ozcan, H. K., Cihan, P., Ongen, A., Guvenc, S. Y., & Ciner, M. N. (2024). Artificial intelligence methods for modeling gasification of waste biomass: a review. Environmental Monitoring and Assessment, 196(3), 309. https://doi.org/10.1007/s10661-024-12443-2
Ascher, S., Wang, X., Watson, I., Sloan, W., & You, S. (2022). Interpretable machine learning to model biomass and waste gasification. Bioresource Technology, 364, 128062. https://doi.org/https://doi.org/10.1016/j.biortech.2022.128062
Ascher, S., Watson, I., & You, S. (2022). Machine learning methods for modelling the gasification and pyrolysis of biomass and waste. Renewable and Sustainable Energy Reviews, 155, 111902. https://doi.org/https://doi.org/10.1016/j.rser.2021.111902
Ayodele, B. V., Mustapa, S. I., Kanthasamy, R., Mohammad, N., AlTurki, A., & Babu, T. S. (2022). Performance analysis of support vector machine, Gaussian Process Regression, sequential quadratic programming algorithms in modeling hydrogen-rich syngas production from catalyzed co-gasification of biomass wastes from oil palm. International Journal of Hydrogen Energy, 47(98), 41432–41443. https://doi.org/https://doi.org/10.1016/j.ijhydene.2022.05.066
Aziz, M. M. A., Kassim, K. A., Shokravi, Z., Jakarni, F. M., Liu, H. Y., Zaini, N., Tan, L. S., Islam, A. B. M. S., & Shokravi, H. (2020). Two-stage cultivation strategy for simultaneous increases in growth rate and lipid content of microalgae: A review. Renewable and Sustainable Energy Reviews, 119, 109621. https://doi.org/https://doi.org/10.1016/j.rser.2019.109621
Bongomin, O., Nzila, C., Mwasiagi, J. I., & Maube, O. (2024). Exploring Insights in Biomass and Waste Gasification via Ensemble Machine Learning Models and Interpretability Techniques. International Journal of Energy Research, 2024(1), 6087208. https://doi.org/https://doi.org/10.1155/2024/6087208
Chu, C., Boré, A., Liu, X. W., Cui, J. C., Wang, P., Liu, X., Chen, G. Y., Liu, B., Ma, W. C., Lou, Z. Y., Tao, Y., & Bary, A. (2022). Modeling the impact of some independent parameters on the syngas characteristics during plasma gasification of municipal solid waste using artificial neural network and stepwise linear regression methods. Renewable and Sustainable Energy Reviews, 157, 112052. https://doi.org/https://doi.org/10.1016/j.rser.2021.112052
Elmaz, F., Yücel, Ö., & Mutlu, A. Y. (2020). Predictive modeling of biomass gasification with machine learning-based regression methods. Energy, 191, 116541. https://doi.org/https://doi.org/10.1016/j.energy.2019.116541
Fiazi, C., Zarei, C., Samimi Akhijahanii, H., & Maleki, M. 2024. Improving biogas production from fruit waste: using chemical, mechanical and thermal pretreatments and co-digestion with cow manure. Agricultural mechanization., 9(1).
Kardani, N., Zhou, A., Nazem, M., & Lin, X. (2021). Modelling of municipal solid waste gasification using an optimised ensemble soft computing model. Fuel, 289, 119903. https://doi.org/https://doi.org/10.1016/j.fuel.2020.119903
Li, J., Pan, L., Suvarna, M., & Wang, X. (2021). Machine learning aided supercritical water gasification for H2-rich syngas production with process optimization and catalyst screening. Chemical Engineering Journal, 426, 131285. https://doi.org/https://doi.org/10.1016/j.cej.2021.131285
Liu, S., Yang, Y., Yu, L., Zhu, F., Cao, Y., Liu, X., Yao, A., & Cao, Y. (2022). Predicting gas production by supercritical water gasification of coal using machine learning. Fuel, 329, 125478. https://doi.org/https://doi.org/10.1016/j.fuel.2022.125478
Long, X., Spiegl, N., Berrueco, C., Paterson, N., & Millan, M. (2020). Fluidised bed oxy-fuel gasification of coal: Interactions between volatiles and char at varying pressures and fuel feed rates. Chemical Engineering Science: X, 8, 100068. https://doi.org/https://doi.org/10.1016/j.cesx.2020.100068
Midilli, A., Kucuk, H., Topal, M. E., Akbulut, U., & Dincer, I. (2021). A comprehensive review on hydrogen production from coal gasification: Challenges and Opportunities. International Journal of Hydrogen Energy, 46(50), 25385–25412. https://doi.org/https://doi.org/10.1016/j.ijhydene.2021.05.088
Mutlu, A. Y., & Yucel, O. (2018). An artificial intelligence based approach to predicting syngas composition for downdraft biomass gasification. Energy, 165, 895–901. https://doi.org/https://doi.org/10.1016/j.energy.2018.09.131
Onsree, T., & Tippayawong, N. (2021). Machine learning application to predict yields of solid products from biomass torrefaction. Renewable Energy, 167, 425–432. https://doi.org/https://doi.org/10.1016/j.renene.2020.11.099
Ozbas, E. E., Aksu, D., Ongen, A., Aydin, M. A., & Ozcan, H. K. (2019a). Hydrogen production via biomass gasification, and modeling by supervised machine learning algorithms. International Journal of Hydrogen Energy, 44(32), 17260–17268. https://doi.org/https://doi.org/10.1016/j.ijhydene.2019.02.108
Ozbas, E. E., Aksu, D., Ongen, A., Aydin, M. A., & Ozcan, H. K. (2019b). Hydrogen production via biomass gasification, and modeling by supervised machine learning algorithms. International Journal of Hydrogen Energy, 44(32), 17260–17268. https://doi.org/10.1016/j.ijhydene.2019.02.108
Pandey, D. S., Raza, H., & Bhattacharyya, S. (2023). Development of explainable AI-based predictive models for bubbling fluidised bed gasification process. Fuel, 351, 128971. https://doi.org/10.1016/j.fuel.2023.128971
Rodionova, M. V, Bozieva, A. M., Zharmukhamedov, S. K., Leong, Y. K., Chi-Wei Lan, J., Veziroglu, A., Veziroglu, T. N., Tomo, T., Chang, J.-S., & Allakhverdiev, S. I. (2022). A comprehensive review on lignocellulosic biomass biorefinery for sustainable biofuel production. International Journal of Hydrogen Energy, 47(3), 1481–1498. https://doi.org/https://doi.org/10.1016/j.ijhydene.2021.10.122
Sánchez, J., Curt, M. D., Robert, N., & Fernández, J. (2019). Chapter Two - Biomass Resources (C. Lago, N. Caldés, & Y. B. T.-T. R. of B. in the B. Lechón (eds.); pp. 25–111). Academic Press. https://doi.org/https://doi.org/10.1016/B978-0-12-813056-8.00002-9
Shafizadeh, A., Shahbeik, H., Rafiee, S., Moradi, A., Shahbaz, M., Madadi, M., Li, C., Peng, W., Tabatabaei, M., & Aghbashlo, M. (2023). Machine learning-based characterization of hydrochar from biomass: Implications for sustainable energy and material production. Fuel, 347, 128467. https://doi.org/https://doi.org/10.1016/j.fuel.2023.128467
Umenweke, G. C., Afolabi, I. C., Epelle, E. I., & Okolie, J. A. (2022). Machine learning methods for modeling conventional and hydrothermal gasification of waste biomass: A review. Bioresource Technology Reports, 17, 100976. https://doi.org/https://doi.org/10.1016/j.biteb.2022.100976
Víllora, G., Pulgar, G., Moreno, D. A., & Romero, L. (1998). Eggplant yield response to increasing rates of N-P-K fertilization. Phyton-International Journal of Experimental Botany, 63, 87–91.
Wen, H. T., Lu, J. H., & Phuc, M. X. (2021). Applying artificial intelligence to predict the composition of syngas using rice husks: A comparison of artificial neural networks and gradient boosting regression. Energies, 14(10), 1–18. https://doi.org/10.3390/en14102932
Yang, Y., Shahbeik, H., Shafizadeh, A., Rafiee, S., Hafezi, A., Du, X., Pan, J., Tabatabaei, M., & Aghbashlo, M. (2023). Predicting municipal solid waste gasification using machine learning: A step toward sustainable regional planning. Energy, 278, 127881. https://doi.org/https://doi.org/10.1016/j.energy.2023.127881
Yu, J., Guo, Q., Gong, Y., Ding, L., Wang, J., & Yu, G. (2021). A review of the effects of alkali and alkaline earth metal species on biomass gasification. Fuel Processing Technology, 214(December 2020), 106723. https://doi.org/10.1016/j.fuproc.2021.106723
Zhou, S., Dai, F., Chen, Y., Dang, C., Zhang, C., Liu, D., & Qi, H. (2019). Sustainable hydrothermal self-assembly of hafnium–lignosulfonate nanohybrids for highly efficient reductive upgrading of 5-hydroxymethylfurfural. Green Chem., 21(6), 1421–1431. https://doi.org/10.1039/C8GC03710H
Iranian Journal of Biosystems Engineering
Volume 55, Issue 3
October 2025
Pages 73-85

Files

History

  • Receive Date: 23 June 2024
  • Revise Date: 31 December 2024
  • Accept Date: 02 February 2025

Share

How to cite

Statistics