https://doi.org/10.4081/jae.2025.1712
Use of machine learning tools to estimate drying rate of apple and apricot wood discs
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.
Published: 4 September 2025
This study compares three machine learning (ML) models -artificial neural networks (ANN), recurrent neural networks (RNN), and extreme gradient boosting (XGBoost)- for predicting the drying kinetics of wood biomass from the clearing of outdated apple and apricot orchards. The primary goal was to optimize and evaluate the performance of these models in predicting drying time and moisture content of the wood, which is crucial for improving energy efficiency in the drying process. Experiments were conducted under four temperature regimes (40°C, 50°C, 60°C, and 70°C) to simulate low- and high-temperature drying conditions. The models were trained and evaluated using statistical quality metrics such as root mean squared error (RMSE), mean absolute error MAE, and R². Results showed that all models performed with high accuracy, but XGBoost demonstrated the best statistical performance, exhibiting the lowest MAE and RMSE values. The RNN model exhibited the highest R² values and performed well in terms of MAE and RMSE, whereas the ANN model yielded slightly lower results. Despite small differences in performance, the models showed strong predictive capabilities and can be effectively used for modeling the drying process of moist wood biomass. This research emphasizes the significance of model optimization in enhancing the accuracy of drying time predictions and minimizing energy consumption in drying processes.
Downloads
Aghbashlo, M., Hosseinpour, S., Mujumdar, A.S. 2015. Application of artificial neural networks (ANNs) in drying technology: a comprehensive review. Dry Technol. 33:1397–1462. DOI: https://doi.org/10.1080/07373937.2015.1036288
Alsheikh, M. A., Niyato, D., Lin, S., Tan, H. P., Han, Z. 2016. Mobile big data analytics using deep learning and apache spark. IEEE Network 30:22-29. DOI: https://doi.org/10.1109/MNET.2016.7474340
Arel, I., Rose, D.C., Karnowski, T.P. 2010. Deep machine learning - A new frontier in artificial intelligence research [Research Frontier]. IEEE Comput. Intell. Mag. 5:13-18. DOI: https://doi.org/10.1109/MCI.2010.938364
Bovornset, S., Wongwise, S. 2007. Drying parawood with superheated steam. Am. J. Appl. Sci. 4:215– 219. DOI: https://doi.org/10.3844/ajassp.2007.215.219
Derčan, B., Lukić, T., Bubalo-Živković M., Durev, B., Stojsavljević, R., Pantelić, M. 2012. Possibility of efficient utilization of wood waste as a renewable energy resource in Serbia. Renew. Sustain. Energy Rev. 16:1516e1527. DOI: https://doi.org/10.1016/j.rser.2011.10.017
Doymaz, I. 2012. Evaluation of some thin-layer drying models of persimmon slices (Diospyros kaki L.). Energy Convers. Manag. 56:199–205. DOI: https://doi.org/10.1016/j.enconman.2011.11.027
Elustondo, D., Matan, N., Langrish, T., Pang, S. 2023. Advances in wood drying research and development. Dry Technol. 41:890–914. DOI: https://doi.org/10.1080/07373937.2023.2205530
Espinoza, O., Bond, B. 2016. Vacuum drying of wood— State of the art. Curr. For. Rep. 2:223–235. DOI: https://doi.org/10.1007/s40725-016-0045-9
Eurostat. 2024. Energy consumption in households. Available from: https://ec.europa.eu/eurostat/statistics-explained/SEPDF/cache/58200.pdf
Günaydına, S., Ropelewska, E., Sacilik, K., Çetin, N. 2014. Exploration of machine learning models based on the image texture of dried carrot slies for classification. J. Food Eng. 143:167–177.
Ghaderi, A., Abbasi, S., Motevali, A., Minaei, S. 2012. Comparison of mathematical models and artificial neural networks for prediction of drying kinetics of mushroom in microwave vacuum dryer. Chem. Ind. Chem. Eng. Q. 18:283–293. DOI: https://doi.org/10.2298/CICEQ110823005G
Haykin, S. 1999.Neural networks a comprehensive introduction. Upper Saddle River, Prentice Hall.
IEA 2008. Energy in the Western Balkans. Paris, IEA. Available from: https://www.iea.org/reports/energy-in-the-western-balkans
Ilic, M., Grubor, B., Tesic, M. 2004. The state of biomass energy in Serbia. Therm Sci. 8. 5-20. DOI: https://doi.org/10.2298/TSCI0402005I
IRENA. 2019. Global energy transformation: A roadmap to 2050 (2019 edition). Abu Dhabi, International Renewable Energy Agency.
Ji, W. 2024. Apple recognition and picking sequence planning for harvesting robot in a complex environment. J. Agric. Eng. 55:1549. DOI: https://doi.org/10.4081/jae.2024.1549
Keskes, S., Hanini, S., Hentabli, M., Laidi, M. 2020. Artificial intelligence and mathematical modelling of the drying kinetics of pharmaceutical powder. Kem. Ind. 69:137–152. DOI: https://doi.org/10.15255/KUI.2019.038
Kırbaşa, I., Doğuş, Tuncerb A., Şirinb, C., Usta, H. 2019. Modeling and developing a smart interface for various drying methods of pomelo fruit (Citrus maxima) peel using machine learning approaches. Comput. Electron. Agr. 165:104928. DOI: https://doi.org/10.1016/j.compag.2019.104928
Khan, M.I.H., Sablani, S.S., Joardder, M.U.H., Karim, M.A. 2022. Application of machine learning-based approach in food drying: opportunities and challenges. Dry Technol. 40:1051–1067. DOI: https://doi.org/10.1080/07373937.2020.1853152
Lerman, P., Scheepers, G. 2023. Determination of a mass-transfer coefficient for wood drying by means of thermography. Wood Mater. Sci. Eng. 18:2104-2111. DOI: https://doi.org/10.1080/17480272.2023.2243473
Li, X., Ma, L., Chen, P., Xu, H., Xing, Q., Yan, J, et al. 2022. Probabilistic solar irradiance forecasting based on XGBoost. Energy Rep. 8:1087-1095. DOI: https://doi.org/10.1016/j.egyr.2022.02.251
Martynenko, A. 2018. Artificial intelligence: is it a good fit for drying? Dry Technol. 36:891–892. DOI: https://doi.org/10.1080/07373937.2017.1362153
Milanović, M., Komatina, M., Janković, B., et al. 2022. The kinetic study of juice industry residues drying process based on TGA-DTG experimental data. J. Therm. Anal. Calorim. 147:10109–10129. DOI: https://doi.org/10.1007/s10973-022-11289-5
Morales-Reyes, J.L. 2023. Anthocyanins estimation in homogeneous bean landrace Phaseolus vulgaris L.) using probabilistic representation and convolution neural networks. J. Agric. Eng. 54:1421. DOI: https://doi.org/10.4081/jae.2023.1421
Perić, M., Antonijević, D., Komatina, M., Bugarski, B., Rakin, M. 2020. Life cycle assessment of wood chips supply chain in Serbia. Renew. Energy. 155: 1302-1311. DOI: https://doi.org/10.1016/j.renene.2020.04.026
Rajković, A., Jovanović, D., Milanović, M., Ećim-Đurić, O. 2023. Investigation of convective drying characteristics and specific energy consumption of apricot and apple tree discs. Proc. 6th Int. Symp. on Agricultural Engineering., pp. 219-24.
Ropelewska, E., Çetinb, N., Günaydınc, S. 2023. Non-destructive discrimination of vacuum-dried banana using image processing operation and machine learning approach. Food Bioprod. Process. 141:36-48. DOI: https://doi.org/10.1016/j.fbp.2023.07.001
Ryan, K., Agrawal, P., Franklin, S. 2020. The pattern theory of self in artificial general intelligence: A theoretical framework for modeling self in biologically inspired cognitive architectures. Cogn. Syst. Res. 62:44–56. DOI: https://doi.org/10.1016/j.cogsys.2019.09.018
Sagi, O., Rokach, L. 2021. Approximating XGBoost with an interpretable decision tree. Inf. Sci. 572:522–542. DOI: https://doi.org/10.1016/j.ins.2021.05.055
Salazar, M.A.G., Morini, M., Pinelli, M., Spina, P.R., Venturini, M., Finkenrath, M., Poganietz, W.R. 2014. Methodology for estimating biomass energy potential and its application to Colombia. Appl. Energy. 136:781-796. DOI: https://doi.org/10.1016/j.apenergy.2014.07.004
Samsonovich, A.V. 2020. Socially emotional brain-inspired cognitive architecture framework for artificial intelligence. Cognit. Syst. Res. 60:57-76. DOI: https://doi.org/10.1016/j.cogsys.2019.12.002
Shaozhi, Z., Yu, P., Dongpo, L., Youming, Z., Guangming, C., Heng, L.A. 2016. Thermophysical study on the freeze drying of wooden archaeological artifacts. J. Cult. Heritage. 17:95–101. DOI: https://doi.org/10.1016/j.culher.2015.07.003
Simpson, W.T. 1983. Drying wood: a review – Part I. Dry Technol. 2:235-264. DOI: https://doi.org/10.1080/07373938308959827
Statistical Office of the Republic of Serbia, 2024. Area and average number of apple and pear trees, by plantation age. Available from: https://data.stat.gov.rs/Home/Result/13050201?languageCode=en-US
Strehler, A. 2000. Technologies of wood combustion. Ecol. Eng. 16:25e40. DOI: https://doi.org/10.1016/S0925-8574(00)00049-5
Tian, K., Zeng, J., Song, T., Li, Z., Li, J. 2023. Tomato leaf diseases recognition based on deep convolutional neural networks. J. Agric. Eng. 54:1432. DOI: https://doi.org/10.4081/jae.2022.1432
Xiao, H., Pang, C., Wang, L., Bai, J., Yang, W., Gao, Z. 2010. Drying kinetics and quality of Monukka seedless grapes dried in an air-impingement jet dryer. Biosyst. Eng. 105:233-240. DOI: https://doi.org/10.1016/j.biosystemseng.2009.11.001
Yang, L., Liu, H. 2020. Effect of supercritical CO2 drying on moisture transfer and wood property of Eucalyptus urophydis. Forests 11:1115. DOI: https://doi.org/10.3390/f11101115
Zhang, Y., Wang, S., Ji, G., Phillips, P. 2014. Fruit classification using computer vision and feedforward neural network. J. Food Eng. 143:167-177. DOI: https://doi.org/10.1016/j.jfoodeng.2014.07.001
Złotek, U., Dziki, U.G., Dziki, D., Swieca, M., Nowak, R., Martinez, E. 2019. Influence of drying temperature on phenolic acids composition and antioxidant activity of sprouts and leaves of white and red quinoa. J. Chem. 7125169. DOI: https://doi.org/10.1155/2019/7125169
How to Cite
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
PAGEPress has chosen to apply the Creative Commons Attribution NonCommercial 4.0 International License (CC BY-NC 4.0) to all manuscripts to be published.