A robust hybrid data driven approach to model biochar yield in terms of biomass pyrolysis

Abstract

Biochar yield prediction plays a critical role in optimizing pyrolysis processes and advancing sustainable biomass utilization. This study introduces a hybrid machine learning framework that integrates Decision Tree models with four optimization strategies including Tabu Search, Ant Colony Optimization, Evolutionary Strategies, and Batch Bayesian Optimization (DT-BBO). A curated dataset of 211 samples was preprocessed using Leverage outlier detection and normalization to ensure model robustness. Among all tested models, the DT-BBO approach achieved the highest accuracy, with an R² of 0.98, an MSE of 1.9, and an AARE% of 2.2%, outperforming the other optimization techniques. SHAP analysis revealed that pyrolysis temperature, residence time, and ash content were the most influential parameters governing biochar yield. Comparative benchmarking against previously published models confirmed the superior predictive capability and stability of the proposed framework. The results demonstrate that the DT-BBO model offers a scalable, interpretable, and high-performing solution for biochar yield prediction, contributing to methodological innovation and sustainable biomass valorization.

Keywords

Biochar yield / Data analysis / Optimization / Decision tree / Biomass pyrolysis

References

[1] Abdelfattah W, Abosaoda MK, Vaghela K, Sahu PK, Singh KU, Sivaranjani R, J G, Chauhan R, Singla S, Sherzod S. Predicting biochar yield from biomass pyrolysis: a comprehensive data-driven approach using machine learning and SHAP analysis. Results Eng, 2025

[2] Abdelfattah W, Abosaoda MK, Vaghela K, Sahu PK, Singh KU, Sivaranjani R, Sherzod S. Accurate modeling of biochar yield based on proximate analysis. Energy Explor Exploitation, 2025, 43(6): 2397-2423

[3] Abido MA. Optimal power flow using tabu search algorithm. Electr Power Compon Syst, 2002, 30(5): 469-483

[4] Akkaya A, KÖZkurt C (2024) Bibliometric analysis of ant colony optimization algorithm (1992–2024). BIDGE Publications

[5] Awadallah MA, Makhadmeh SN, Al-Betar MA, Dalbah LM, Al-Redhaei A, Kouka S, Enshassi OS. Multi-objective ant colony optimization. Arch Comput Methods Eng, 2025, 32(2): 995-1037

[6] Azimi J, Fern A, Fern X. Batch Bayesian optimization via simulation matching. Adv Neural Inf Process Syst, 2010, 23: 586

[7] Azimi J, Jalali A, Fern X (2012) Hybrid batch B''[ayesian optimization. arXiv preprint arXiv:1202.5597

[8] Birhanu A, Hailu AM, Worku Z, Tessema I, Angassa K, Tibebu S. Optimization of pyrolysis conditions for Catha edulis waste-based biochar production using response surface methodology. Bioresources Bioprocess, 2025, 12(1): 62

[9] Blum C. Ant colony optimization: a bibliometric review. Phys Life Rev, 2024, 51: 87-95

[10] Cabello-Solorzano K, Ortigosa de Araujo I, Peña M, Correia L, Tallón-Ballesteros AJ (2023) The impact of data normalization on the accuracy of machine learning algorithms: a comparative analysis

[11] Chaihad N, Anniwaer A, Karnjanakom S, Kasai Y, Kongparakul S, Samart C, Reubroycharoen P, Abudula A, Guan G. In-situ catalytic upgrading of bio-oil derived from fast pyrolysis of sunflower stalk to aromatic hydrocarbons over bifunctional Cu-loaded HZSM-5. J Anal Appl Pyrolysis, 2021, 155: 105079

[12] Chave AD, Thomson DJ. A bounded influence regression estimator based on the statistics of the hat matrix. J R Stat Soc C Appl Stat, 2003, 52(3): 307-322

[13] Chun Y, Lee SK, Yoo HY, Kim SW. Recent advancements in biochar production according to feedstock classification, pyrolysis conditions, and applications: a review. BioResources, 2021, 16(3): 6512

[14] da Conceicao Cunha M, Ribeiro L. Tabu search algorithms for water network optimization. Eur J Oper Res, 2004, 157(3): 746-758

[15] da Silva Medeiros DCC, Usman M, Chelme-Ayala P, El-Din MG. Biochar-enhanced removal of naphthenic acids from oil sands process water: influence of feedstock and chemical activation. Energy Environ Sustain, 2025, 1(2): 100028

[16] Dorigo M, Stützle T. Ant colony optimization: overview and recent advances. Handbook Metaheuristics, 2018, 5: 311-351

[17] Dorigo M, Birattari M, Stutzle T. Ant colony optimization. IEEE Comput Intell Mag, 2007, 1(4): 28-39

[18] Dziwiński P, Bartczuk Ł (2023) A new hybrid particle swarm optimization and evolutionary algorithm with self-adaptation mechanism

[19] Zhuang Y, Liu L, Singh C, Shang J, Gao J (2024) Learning a decision tree algorithm with transformers. arXiv preprintarXiv:2402.03774

[20] Franzon G (2025) Exploring the biochar contribution in sustainable agriculture through techno-economic assessment and water impact simulations

[21] Ge Q, Li P, Liu M, Xiao G-M, Xiao Z-Q, Mao J-W, Gai X-K. Removal of Methylene blue by porous biochar obtained by KOH activation from bamboo biochar. Bioresources Bioprocess, 2023, 10(1): Article ID: 51

[22] González J, Dai Z, Hennig P, Lawrence NBatch Bayesian optimization via local penalization, 2016BerlinSpringer

[23] Gorriz JM, Segovia F, Ramirez J, Ortiz A, Suckling J (2024) Is K-fold cross validation the best model selection method for Machine Learning? arXiv preprint arXiv:2401.16407

[24] Guo P, Xue R, Zou Q, Ma X, Su C, Zeng Z, Li L. Enhanced ultramicropore of biomass-derived porous carbon for efficient and low-energy CO₂ capture: integration of adsorption and solar desorption. Energy Environ Mater, 2025, 5: e70140

[25] Gurevich Messina LI, Bonelli PR, Cukierman AL. In-situ catalytic pyrolysis of peanut shells using modified natural zeolite. Fuel Process Technol, 2017, 159: 160-167

[26] Hatefirad P, Hosseini M, Tavasoli A. Effect of Fe/Cu catalysts supported on zeolite/active carbon hybrid on bio-oil quality derived from catalytic pyrolysis of granular bacteria biomass. Fuel, 2022, 312: 122870

[27] He Y, Zhang B, Zhou S, Wei Y, Li B, Wang H. Stepwise removal mechanism of impurity using multi-flux during blister copper pyrometallurgical refining. Metall Mater Trans B, 2025, 5: 1-15

[28] Herath Bandara SJ. Exploring the potential of biochar in enhancing US agriculture. Reg Sci Environ Econ, 2025, 2(3): Article ID: 23

[29] Hou G, Alkhayyat A, Almalkawi A, Yadav A, Shreenidhi HS, Saini V, Shomurotova S, Singh D, Jain V, Khalid A, Smerat A. Development of robust machine learning models to estimate hydrochar higher heating value and yield based upon biomass proximate analysis. Bioresour Bioprocess, 2025, 12(1): 138

[30] Hu K, Mu C, Ge Z, Ao X. A modified SLD-ESD model for characterizing and predicting supercritical CH4 adsorption on shale at wide temperatures and pressures. Fuel, 2026, 416: 138561

[31] Ibitoye SE, Loha C, Mahamood RM, Jen T-C, Alam M, Sarkar I, Akinlabi ET. An overview of biochar production techniques and application in iron and steel industries. Bioresources Bioprocess, 2024, 11(1): 65

[32] Kang Z, Huang D, Zhao J, Fan S, Yang D, Lu Y. Hydrogen transfer and reaction mechanism during in-situ pyrolysis of Fushun oil shale with steam injection. Fuel, 2025, 381: 133583

[33] Kumar N, Dixit A, Vijay V (2025) Entropy measures and their applications: a comprehensive review. arXiv preprint arXiv:2503.15660

[34] Le AT, Pandey A, Sirohi R, Sharma P, Chen W-H, Pham NDK, Hoang AT. Precise prediction of biochar yield and proximate analysis by modern machine learning and shapley additive explanations. Energy Fuels, 2023, 37(22): 17310-17327

[35] Li Y, Nishu Y, Dominic LC, Liu R. Deactivation mechanism and regeneration effect of bi-metallic Fe-Ni/ZSM-5 catalyst during biomass catalytic pyrolysis. Fuel, 2022, 312: 122924

[36] Li X, Wang Z, Zhang Y, Zhang W, Zhang H, Liu P, Lei T. Hydrogen-rich gas formation from catalytic pyrolysis of biomass tar by aluminum dross coupled HZSM-5 co-loaded Ni-Fe bimetallic catalysts: influence of co-carrier characteristics. J Environ Manage, 2025, 389: 126016

[37] Liu M, Tao J, Mu L, Su H, Peng H, Cheng Z, Chen G. Machine learning-driven predictions of biochar yield and NPK composition: insights into biomass pyrolysis with data augmentation and model interpretability. Carbon Res, 2025, 4(1): 62

[38] Long L, Wen GY, Ming CB. Research progress on pyrolysis gasification and resource utilization of tobacco waste: component analysis and recovery strategies. J Anal Appl Pyrol, 2025, 52: 107425

[39] Ma P, Mahoney MW, Yu B. A statistical perspective on algorithmic leveraging. J Mach Learn Res, 2015, 16(1): 861-911

[40] Manyà JJ, Azuara M, Manso JA. Biochar production through slow pyrolysis of different biomass materials: seeking the best operating conditions. Biomass Bioenergy, 2018, 117: 115-123

[41] Mishra RK, Mohanty K. Pyrolysis of Cascabela thevetia seeds over ZSM-5 catalysts: fuel properties and compositional analysis. Biomass Convers Biorefinery, 2022, 12(5): 1449-1464

[42] Nguyen VG, Sharma P, Ağbulut Ü, Le HS, Cao DN, Dzida M, Osman SM, Le HC, Tran VD. Improving the prediction of biochar production from various biomass sources through the implementation of eXplainable machine learning approaches. Int J Green Energy, 2024, 21(12): 2771-2798

[43] Nguyen VG, Sharma P, Ağbulut Ü, Le HS, Truong TH, Dzida M, Tran VD. Machine learning for the management of biochar yield and properties of biomass sources for sustainable energy. Biofuels Bioproducts Biorefining, 2024, 18(2): 567-593

[44] Ozbay N, Yargic AS, Yarbay Sahin RZ, Yaman E. Valorization of banana peel waste via in-situ catalytic pyrolysis using Al-modified SBA-15. Renew Energy, 2019, 140: 633-646

[45] Panigrahy S, Dash S, Padhy S. Optimized deep belief networks based categorization of type 2 diabetes using tabu search optimization. Int J Adv Comput Sci Appl, 2024, 15(3): 667-676

[46] Park S-W, Jang C-H. Effects of pyrolysis temperature on changes in fuel characteristics of biomass char. Energy, 2012, 39(1): 187-195

[47] Park JH, Park YK, Kim Y-M. Kinetic analysis and catalytic pyrolysis of spent medicinal herb over HZSM-5 and HY. Environ Res, 2020, 187: 109632

[48] Paudel PP, Park S, Kim SJ, Kim SY, Kang KS, Kim Kyung J, Kim DH. Comprehensive study on microwave pyrolysis process variables and operating modes for optimized biochar production. Bioresource Technol, 2025, 52: 133120

[49] Peng Y, Chen G, Zhang M, Xue B. Proximal evolutionary strategy: improving deep reinforcement learning through evolutionary policy optimization. Memet Comput, 2024, 16(3): 445-466

[50] Puri L, Hu Y, Naterer G. Critical review of the role of ash content and composition in biomass pyrolysis. Front Fuels, 2024, 2: 1378361

[51] Rahic E, Hess CJ, Brown RC, Wen Z. Biomass pyrolysis-derived aqueous phase as a laccase inducer in Pleurotus ostreatus: laccase production, properties, and applications. Bioresources Bioprocess, 2026, 13(1): Article ID: 41

[52] Repalle NB, Sarala P, Mihet-Popa L, Kotha SR, Rajeswaran N. Implementation of a novel tabu search optimization algorithm to extract parasitic parameters of solar panel. Energies, 2022, 15(13): 4515

[53] Sepúlveda-Fontaine SA, Amigó JM. Applications of entropy in data analysis and machine learning: a review. Entropy, 2024, 26(12): 1126

[54] Shahsavari S, Sadrameli SM. Production of renewable aromatics and heterocycles by catalytic pyrolysis of biomass resources using Rhenium and Tin promoted ZSM-5 zeolite catalysts. Process Saf Environ Prot, 2020, 141: 305-320

[55] Shen Y, Chen L. Novel synthesis of activated biochar-supported catalysts for pyrolysis of cardboard waste derived from express package. Fuel, 2023, 332: 126136

[56] Sun J, He F, Pan Y, Zhang Z. Effects of pyrolysis temperature and residence time on physicochemical properties of different biochar types. Acta Agric Scandinavica Sect B Soil Plant Sci, 2017, 67(1): 12-22

[57] Wallace CA, Afzal MT, Saha GC. Effect of feedstock and microwave pyrolysis temperature on physio-chemical and nano-scale mechanical properties of biochar. Bioresources Bioprocess, 2019, 6(1): 1-11

[58] Wang G, Yang Y, Zhou S, Li B, Wei Y, Wang H. Data analysis and prediction model for Copper matte smelting process. Metall Mater Trans B Process Metall Mater Process Sci, 2024, 55(4): 2552-2567

[59] Wei X, Xue X, Wu L, Yu H, Liang J, Sun Y. High-grade bio-oil produced from Coconut shell: a comparative study of microwave reactor and core-shell catalyst. Energy, 2020, 212: 118692

[60] Wei X, Liu Y, Cao Y, Li J, Meng X, Zhang Z, Jiang Z. Hierarchical Gallium-modified ZSM-5@SBA-15 for the catalytic pyrolysis of biomass into hydrocarbons. Renew Energy, 2022, 200: 1037-1046

[61] Wu L, Xin J, Xia D, Sun J, Liang J. Enhanced production of hydrocarbons from the catalytic pyrolysis of Maize straw over hierarchical ZSM-11 zeolites. Appl Catal B Environ, 2022, 317: 121775

[62] Wu L, Zhang J, Xue X, Liang J, Sun Y. Hydrocarbon-rich bio-oil production from catalytic pyrolysis of biomass over the undervalued ZSM-11 zeolites. ACS EST Eng, 2022, 2(4): 670-680

[63] Xiao C, Peng J, Jiao Y, Shen Q, Zhao Y, Zhao F, Li H, Song Q. Strong and tough multilayer heterogeneous pyrocarbon based composites. Adv Funct Mater, 2024, 34(51): 2409881

[64] Xue X, Zhang C, Xia D, Wang Y, Liang J, Sun Y. Dual-catalyst catalytic pyrolysis of poplar sawdust: a systematic study on first-layered catalysts. Chem Eng J, 2022, 431: 134251

[65] Xue Y, Li Y, Zhong F, Bai Z, Wang P, Li K, Lei F, He Z, Yang Y, Yang X, Feng W. Bio-based benzoxazine containing phthalonitrile: nonsolvent synthesis, curing behavior and pyrolysis mechanism. Polym Degrad Stab, 2025

[66] Yang C, Li R, Qiu Q, Yang H, Zhang Y, Yang B, Wu J, Li B, Wang W, Ding Y, Zhang B. Pyrolytic behaviors of Scenedesmus obliquus over potassium fluoride on alumina. Fuel, 2020, 263: 116724

[67] Yarbay Şahin RZ, Özbay N. Perspective on catalytic biomass pyrolysis bio-oils: essential role of synergistic effect of metal species co-substitution in perovskite type catalyst. Catal Lett, 2021, 151(5): 1406-1417

[68] Zeng K, Yan H, Xia H, Zhang L, Zhang Q. Catalytic pyrolysis of Eupatorium adenophorum by sodium salt. J Mater Cycles Waste Manag, 2021, 23(4): 1626-1635

[69] Zhang Z-b, Lu Q, Ye X-N, Li W-T, Hu B, Dong C-Q. Production of phenolic-rich bio-oil from catalytic fast pyrolysis of biomass using magnetic solid base catalyst. Energy Convers Manag, 2015, 106: 1309-1317

[70] Zhao C, Yang H, Ma H, Chen A, Liu X, Chen J. Machine learning prediction of biochar yield based on different classification methods. J Renew Sustain Energy, 2025, 17(5): 523

[71] Zheng Y, Wang F, Yang X, Huang Y, Liu C, Zheng Z, Gu J. Study on aromatics production via the catalytic pyrolysis vapor upgrading of biomass using metal-loaded modified H-ZSM-5. J Anal Appl Pyrolysis, 2017, 126: 169-179

[72] Zhou Q, Liu Z, Wang X, Li Y, Qin X, Guo L, Zhou L, Xu W. Co3S4-pyrolysis lotus fiber flexible textile as a hybrid electrocatalyst for overall water splitting. J Energy Chem, 2024, 89: 336-344

[73] Zhu J, Fei X, Yin K. Assessment of waste-to-energy conversion technologies for biomass waste under different shared socioeconomic pathways. Energy Environ Sustain, 2025, 1(2): 100021

RIGHTS & PERMISSIONS

The Author(s)