Beyond Elemental Composition: Leveraging Fuel Classification Systems for Robust Machine Learning-Based Higher Heating Value Prediction

Mert Akin Insel

doi:10.21541/apjess.1890616

Beyond Elemental Composition: Leveraging Fuel Classification Systems for Robust Machine Learning-Based Higher Heating Value Prediction

Abstract

Accurate prediction of higher heating value (HHV) is essential for the design, optimization, and performance assessment of energy conversion systems involving biomass, fossil fuels, and waste-derived materials. Although machine learning-based approaches have demonstrated strong predictive capability using ultimate and proximate analysis variables, most existing studies implicitly assume that fuels constitute a homogeneous population once numerical descriptors are provided, thereby overlooking the potential value of fuel classification information. In this study, fuel classification is reframed as an explicit and quantifiable information source for HHV modeling through a unified machine learning framework that integrates three independent classification systems, ECN Phyllis, NTA 8003, and the data-driven HOM Classification System, alongside numerical compositional features using one-hot encoding. A dataset of 929 solid fuel samples was used to evaluate multiple regression models under a consistent five-fold cross-validation protocol with structured hyperparameter optimization. To move beyond aggregate performance metrics, a comprehensive analysis framework combining correlation screening, permutation-based feature importance, ΔRMSE evaluation, ablation experiments, and SHAP-based interpretability analysis was employed to quantify the contribution of individual features and classification systems. The results demonstrate that incorporating fuel classification information leads to consistent improvements in HHV prediction accuracy compared to numerical-only baselines. Among the examined systems, the HOM Classification System provides the strongest and most robust contribution, supplying non-redundant predictive information beyond elemental composition and supporting stable performance across heterogeneous fuel categories. Overall, the findings establish fuel classification, particularly the HOM system, as an active predictor rather than descriptive metadata and offer a more generalizable, interpretable, and robust framework for HHV prediction in biomass and waste-to-energy applications.

Keywords

References

S. A. Channiwala and P. P. Parikh, “A unified correlation for estimating HHV of solid, liquid and gaseous fuels,” Fuel, vol. 81, no. 8, pp. 1051–1063, 2002, doi: 10.1016/S0016-2361(01)00131-4.
J. Parikh, S. A. Channiwala, and G. K. Ghosal, “A correlation for calculating HHV from proximate analysis of solid fuels,” Fuel, vol. 84, no. 5, pp. 487–494, 2005, doi: 10.1016/j.fuel.2004.10.010.
E. Akkaya, “ANFIS based prediction model for biomass heating value using proximate analysis components,” Fuel, vol. 180, pp. 687–693, 2016, doi: https://doi.org/10.1016/j.fuel.2016.04.112.
I. Estiati, F. B. Freire, J. T. Freire, R. Aguado, and M. Olazar, “Fitting performance of artificial neural networks and empirical correlations to estimate higher heating values of biomass,” Fuel, vol. 180, pp. 377–383, 2016, doi: https://doi.org/10.1016/j.fuel.2016.04.051.
H. Uzun, Z. Yıldız, J. L. Goldfarb, and S. Ceylan, “Improved prediction of higher heating value of biomass using an artificial neural network model based on proximate analysis,” Bioresour. Technol., vol. 234, pp. 122–130, Jan. 2017, doi: 10.1016/j.biortech.2017.03.015.
H. Yaka, M. A. Insel, O. Yucel, and H. Sadikoglu, “A comparison of machine learning algorithms for estimation of higher heating values of biomass and fossil fuels from ultimate analysis,” Fuel, vol. 320, Jul. 2022, doi: 10.1016/j.fuel.2022.123971.
M. A. Insel, O. Yucel, and H. Sadikoglu, “Optimizing waste-to-energy conversion: Unveiling the potential of unsupervised clustering through the new HOM classification system,” Sustainable Energy Technologies and Assessments, vol. 65, May 2024, doi: 10.1016/j.seta.2024.103796.
D. R. Nhuchhen and P. Abdul Salam, “Estimation of higher heating value of biomass from proximate analysis: A new approach,” Fuel, vol. 99, pp. 55–63, 2012, doi: 10.1016/j.fuel.2012.04.015.

C. Qian, Q. Li, Z. Zhang, X. Wang, J. Hu, and W. Cao, “Prediction of higher heating values of biochar from proximate and ultimate analysis,” Fuel, vol. 265, p. 116925, 2020, doi: https://doi.org/10.1016/j.fuel.2019.116925.
Y. Maksimuk, Z. Antonava, V. Krouk, A. Korsakova, and V. Kursevich, “Prediction of higher heating value based on elemental composition for lignin and other fuels,” Fuel, vol. 263, p. 116727, 2020, doi: https://doi.org/10.1016/j.fuel.2019.116727.
S. A. Abdollahi, S. F. Ranjbar, and D. Razeghi Jahromi, “Applying feature selection and machine learning techniques to estimate the biomass higher heating value,” Sci. Rep., vol. 13, no. 1, p. 16093, 2023, doi: 10.1038/s41598-023-43496-x.
J. Xing, K. Luo, H. Wang, and J. Fan, “Estimating biomass major chemical constituents from ultimate analysis using a random forest model,” Bioresour. Technol., vol. 288, no. April, p. 121541, 2019, doi: 10.1016/j.biortech.2019.121541.
A. A. Adeleke et al., “Comparative studies of machine learning models for predicting higher heating values of biomass,” Digital Chemical Engineering, vol. 12, p. 100159, 2024, doi: https://doi.org/10.1016/j.dche.2024.100159.
E. Y. Kaya, I. Ali, Z. Ceylan, and S. Ceylan, “Prediction of higher heating value of hydrochars using Bayesian optimization tuned Gaussian process regression based on biomass characteristics and process conditions,” Biomass Bioenergy, vol. 180, p. 106993, 2024, doi: https://doi.org/10.1016/j.biombioe.2023.106993.
Phyllis2, “Database for (treated) biomass, algae, feedstocks for biogas production and biochar,” 2023. [Online]. Available: https://phyllis.nl/
M. A. Insel, O. Yucel, and H. Sadikoglu, “Higher heating value estimation of wastes and fuels from ultimate and proximate analysis by using artificial neural networks,” Waste Management, vol. 185, pp. 33–42, Jul. 2024, doi: 10.1016/j.wasman.2024.05.044.
S. Gungor, M. A. Insel, H. Sadikoglu, and M. Melikoglu, “Prediction of Biocrude Oil Yield From Biomass Hydrothermal Liquefaction Via Interpretable Machine Learning Using Higher Heating Value and Process Parameters,” Bioenergy Res., vol. 18, no. 1, Dec. 2025, doi: 10.1007/s12155-025-10906-z.
J. M. Vargas-Moreno, A. J. Callejón-Ferre, J. Pérez-Alonso, and B. Velázquez-Martí, “A review of the mathematical models for predicting the heating value of biomass materials,” Renewable and Sustainable Energy Reviews, vol. 16, no. 5, pp. 3065–3083, 2012, doi: https://doi.org/10.1016/j.rser.2012.02.054.
C. Qian, Q. Li, Z. Zhang, X. Wang, J. Hu, and W. Cao, “Prediction of higher heating values of biochar from proximate and ultimate analysis,” Fuel, vol. 265, no. September 2019, p. 116925, 2020, doi: 10.1016/j.fuel.2019.116925.
F. Elmaz, Ö. Yücel, and A. Y. Mutlu, “Predictive modeling of biomass gasification with machine learning-based regression methods,” Energy, vol. 191, 2020, doi: 10.1016/j.energy.2019.116541.

Details

Primary Language

English

Subjects

Adversarial Machine Learning, Supervised Learning, Machine Learning Algorithms

Journal Section

Research Article

Authors

Mert Akin Insel ^*
0000-0002-4347-1190
Türkiye

Publication Date

May 31, 2026

Submission Date

February 17, 2026

Acceptance Date

April 24, 2026

Published in Issue

Year 2026 Volume: 14 Number: 2

DOI

https://doi.org/10.21541/apjess.1890616

IZ

https://izlik.org/JA49HN52LS

Cite

RIS / Bibtex

APA

Insel, M. A. (2026). Beyond Elemental Composition: Leveraging Fuel Classification Systems for Robust Machine Learning-Based Higher Heating Value Prediction. Academic Platform Journal of Engineering and Smart Systems, 14(2), 125-139. https://doi.org/10.21541/apjess.1890616

AMA

1.Insel MA. Beyond Elemental Composition: Leveraging Fuel Classification Systems for Robust Machine Learning-Based Higher Heating Value Prediction. APJESS. 2026;14(2):125-139. doi:10.21541/apjess.1890616

Chicago

Insel, Mert Akin. 2026. “Beyond Elemental Composition: Leveraging Fuel Classification Systems for Robust Machine Learning-Based Higher Heating Value Prediction”. Academic Platform Journal of Engineering and Smart Systems 14 (2): 125-39. https://doi.org/10.21541/apjess.1890616.

EndNote

Insel MA (May 1, 2026) Beyond Elemental Composition: Leveraging Fuel Classification Systems for Robust Machine Learning-Based Higher Heating Value Prediction. Academic Platform Journal of Engineering and Smart Systems 14 2 125–139.

IEEE

[1]M. A. Insel, “Beyond Elemental Composition: Leveraging Fuel Classification Systems for Robust Machine Learning-Based Higher Heating Value Prediction”, APJESS, vol. 14, no. 2, pp. 125–139, May 2026, doi: 10.21541/apjess.1890616.

ISNAD

Insel, Mert Akin. “Beyond Elemental Composition: Leveraging Fuel Classification Systems for Robust Machine Learning-Based Higher Heating Value Prediction”. Academic Platform Journal of Engineering and Smart Systems 14/2 (May 1, 2026): 125-139. https://doi.org/10.21541/apjess.1890616.

JAMA

1.Insel MA. Beyond Elemental Composition: Leveraging Fuel Classification Systems for Robust Machine Learning-Based Higher Heating Value Prediction. APJESS. 2026;14:125–139.

MLA

Insel, Mert Akin. “Beyond Elemental Composition: Leveraging Fuel Classification Systems for Robust Machine Learning-Based Higher Heating Value Prediction”. Academic Platform Journal of Engineering and Smart Systems, vol. 14, no. 2, May 2026, pp. 125-39, doi:10.21541/apjess.1890616.

Vancouver

1.Mert Akin Insel. Beyond Elemental Composition: Leveraging Fuel Classification Systems for Robust Machine Learning-Based Higher Heating Value Prediction. APJESS. 2026 May 1;14(2):125-39. doi:10.21541/apjess.1890616