Biomass higher heating value prediction machine learning insights into ultimate, proximate, and structural analysis datasets

ABSTRACT

In this study machine learning (ML) models have been employed to predict the higher heating value (HHV) of biomass by utilizing input variables derived from ultimate, proximate, and structural analyses. In total, 180 models were developed, with 124 utilizing ultimate analysis data, 28 based on proximate analysis, and 28 relying on structural analysis. Various ML techniques, including polynomial models (SOP), support vector machines (SVM), random forest regression (RFR), and artificial neural networks (ANN), were employed for analysis. The study found that ANN models, when “fed” with FC and VM data, provided considerable accuracy in prediction results, with the best results obtained with 2-12-1 architecture (R² = 0.96). In addition, a separate model configuration that processed inputs on biomass constituents such as cellulose, lignin, and hemicellulose showed remarkable agreement with empirical data. Additional findings revealed that the models created using SOP (R² = 0.95), SVM (R² = 0.95), and RFR (R² = 0.90) demonstrated minimal discrepancies when predicting HHV. This study provides significant insights into the investigation of biomass analysis techniques employing ML tools, paving the way for future research aimed at constructing a robust tool for HHV prediction. Subsequent models may explore integrating inputs from diverse analysis methods and leveraging advanced machine learning techniques to enhance accuracy further.

KEYWORDS:

• Energy properties
• mathematical modeling
• ultimate analysis
• proximate analysis
• structural analysis

Acknowledgements

The publication was supported by the Croatian Science Foundation, under project No. IP-2018-01-7472 “Sludge management via energy crops production” and within the project “Young Researchers’ Career Development Project—Training of Doctoral Students”, co-financed by the European Union, under the OP “Efficient Human Resources 2014–2020” from the ESF funds.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Supplementary material

Supplemental data for this article can be accessed online at https://doi.org/10.1080/15567036.2024.2309303

Credit author statement

Ivan Brandić: Conceptualization, Methodology, Investigation, Data curation, Visualization, Writing- Original draft preparation, Writing- Reviewing and Editing; Neven Voća: Conceptualization, Supervision, Validation; Jerko Gunjača: Conceptualization, Methodology, Investigation, Writing- Original draft preparation; Biljana Lončar: Conceptualization, Methodology, Investigation, Writing- Original draft preparation; Nikola Bilandžija: Conceptualization, Methodology, Investigation, Writing- Original draft preparation; Anamarija Peter: Writing- Reviewing and Editing; Jona Šurić: Conceptualization, Methodology, Investigation, Writing- Original draft preparation; Lato Pezo: Conceptualization, Writing- Original draft preparation, Writing- Reviewing and Editing;

Additional information

Notes on contributors

Ivan Brandić

Ivan Brandić – Research Assistant (Ph.D. Candidate) at the Department of Sustainable Technologies and Renewable Energy, Faculty of Agriculture, University of Zagreb. Research interests encompass mathematical modeling in renewable energy sources and biomass

Neven Voća

Neven Voća – Full Professor at the Department of Sustainable Technologies and Renewable Energy, Faculty of Agriculture, University of Zagreb. Research areas include biomass, renewable energy sources, and waste management.

Jerko Gunjača

Jerko Gunjača - Full Professor at the Department of Plant Breeding, Genetics, and Biometrics, Faculty of Agriculture, University of Zagreb. Specializes in Quantitative Genetics, Genotype by Environment Interaction, Molecular Data Analysis, Genetic Similarity and Diversity, and Association Mapping.

Biljana Lončar

Biljana Lončar – Senior Research Associate at the Faculty of Technology, University of Novi Sad, Novi Sad. Focuses on Food Engineering and Chemical Engineering.

Nikola Bilandžija

Nikola Bilandžija - Associate Professor in the Department of Mechanization and Autonomous Systems in Agriculture, Faculty of Agriculture, University of Zagreb. Research interests include Agricultural Biomass and Energy Crops, Energy Consumption and Potential in Agriculture, Energy Crop Cultivation Engineering, and Horticultural Production Engineering.

Anamarija Peter

Anamarija Peter - Assistant at the Department of Sustainable Technologies and Renewable Energy, Faculty of Agriculture, University of Zagreb. Research focuses on Renewable Energy Sources, Biomass and Biofuels, Waste Management, Biological Diversity, Invasive Plant Species, and Wild Plant Species.

Jona Šurić

Jona Šurić - Research Assistant (Ph.D. Candidate) at the Department of Sustainable Technologies and Renewable Energy, Faculty of Agriculture, University of Zagreb. Research interests are in Renewable Energy Sources, Biomass and Biofuels, and Waste Management.

Lato Pezo

Lato Pezo – Researcher at the University of Belgrade Institute of General and Physical Chemistry. Research areas include Industrial Design, Biochemistry, and Chemical Kinetics.