A chemistry-based explainable machine learning model based on NIR spectra for predicting wood properties and understanding wavelength selection

References

• American Society for Testing and Materials (ASTM), 2006. Standards methods of testing small clear specimens of timber: ASTM: D143-94 (West Conshohocken, PA, ASTM Annual Book of Standards).
   Google Scholar
• Arrieta, A.B., et al. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115.
   Web of Science ®Google Scholar
• Ayanleye, S., et al., 2021. Effect of wood surface roughness on prediction of structural timber properties by infrared spectroscopy using ANFIS, ANN and PLS regression. European Journal of Wood and Wood Products, 79, 101–115. https://doi.org/10.1007/s00107-020-01621-x
   Web of Science ®Google Scholar
• Çalik, M.K., Aydin, E.S., and Yücel, Ö., 2020. Prediction of proximate analysis and process temperature of torrefied and pyrolyzed wood pellets by near-infrared spectroscopy coupled with machine learning. Mugla Journal of Science and Technology, 6 (2), 99–110.
   Google Scholar
• Carty, D.M., et al., 2015. Predicting and correlating the strength properties of wood composite process parameters by use of boosted regression tree models. Forest Products Journal, 65 (7-8), 365–371.
   Web of Science ®Google Scholar
• Cooper, P.A., et al., 2011. Potential of near-infrared spectroscopy to characterize wood products1 this article is a contribution to the series the role of sensors in the new forest products industry and bioeconomy. Canadian Journal of Forest Research, 41 (11), 2150–2157.
   Web of Science ®Google Scholar
• Costa, E.V.S., et al., 2018. Influence of spectral acquisition technique and wood anisotropy on the statistics of predictive near infrared–based models for wood density. Journal of Near Infrared Spectroscopy, 26 (2), 106–116.
   Web of Science ®Google Scholar
• Costa, L.R., et al., 2019. Artificial neural network and partial least square regressions for rapid estimation of cellulose pulp dryness based on near infrared spectroscopic data. Carbohydrate Polymers, 224, 115186.
   PubMed Web of Science ®Google Scholar
• Dahlen, J., et al., 2016. Near-infrared spectroscopy prediction of southern pine No. 2 lumber physical and mechanical properties. Wood Science and Technology, 51, 309–322.
   Web of Science ®Google Scholar
• Diesel, K.M., et al., 2014. Near-infrared spectroscopy and wavelength selection for estimating basic density in Mimosa tenuiflora [Willd.] Poiret wood. Wood Science and Technology, 48, 949–959.
   Web of Science ®Google Scholar
• dos Santos, L.M., et al., 2021. Estimating wood moisture by near infrared spectroscopy: testing acquisition methods and wood surfaces qualities. Wood Material Science & Engineering, 16 (5), 336–343.
   Web of Science ®Google Scholar
• Fathi, H., Nasir, V., and Kazemirad, S., 2020. Prediction of the mechanical properties of wood using guided wave propagation and machine learning. Construction and Building Materials, 262, 120848. https://doi.org/10.1016/j.conbuildmat.2020.120848
   Web of Science ®Google Scholar
• Fujimoto, T., et al., 2008. Application of near infrared spectroscopy for estimating wood mechanical properties of small clear and full length lumber specimens. Journal of Near Infrared Spectroscopy, 16 (6), 529–537.
   Web of Science ®Google Scholar
• Fujimoto, T., Yamamoto, H., and Tsuchikawa, S., 2007. Estimation of wood stiffness and strength properties of hybrid larch by near-infrared spectroscopy. Applied Spectroscopy, 61, 882–888. doi:10.1366/000370207781540150.
   PubMed Web of Science ®Google Scholar
• Hein, P.R.G., et al., 2009. Near infrared spectroscopy for estimating wood basic density in Eucalyptus urophylla and Eucalyptus grandis. Cerne, 15 (2), 133–141.
   Web of Science ®Google Scholar
• Hein, P.R.G., Lima, J.T., and Chaix, G., 2010. Effects of sample preparation on NIR spectroscopic estimation of chemical properties of eucalyptus urophylla S.T. Blake wood. Holzforschung, 64, 45–54.
   Web of Science ®Google Scholar
• Ho, T.X., et al., 2022. Utilization of genetic algorithms to optimize loblolly pine wood property models based on NIR spectra and SilviScan data. Wood Science and Technology, 56 (5), 1419–1437.
   Web of Science ®Google Scholar
• Ho, T.X., Schimleck, L.R., and Sinha, A., 2021. Utilization of genetic algorithms to optimize Eucalyptus globulus pulp yield models based on NIR spectra. Wood Science and Technology, 55, 757–776.
   Web of Science ®Google Scholar
• Hoffmeyer, P. and Pedersen, J.G., 1995. Evaluation of density and strength of Norway spruce wood by near infrared reflectance spectroscopy. Holz als Roh und Werkstoff, 53, 165–170.
   Google Scholar
• Li, Y., et al., 2022. Spectral pre-processing and multivariate calibration methods for the prediction of wood density in Chinese white poplar by visible and near infrared spectroscopy. Forests, 13 (1), 62.
   Web of Science ®Google Scholar
• Liang, H., et al., 2018. Non-destructive methodology to determine modulus of elasticity in static bending of quercus mongolica using near-infrared spectroscopy. Sensors, 18, 1963. doi:10.3390/s18061963.
   PubMed Web of Science ®Google Scholar
• Liu, C., 2011. Use of confocal profilometry to quantify erosion of wood and screen chemicals for their ability to photostabilize wood. Doctoral dissertation. University of British Columbia.
   Google Scholar
• Liu, Y., et al., 2012. Effect of surface roughness on near infrared models for wood density analysis. In: Proceedings of 2012 international conference on biobase material science and engineering (BMSE 2012). Changsha, China, p. 341, IEEE, 75–78.
   Google Scholar
• Mancini, M., et al., 2020. Prediction of pellet quality through machine learning techniques and near-infrared spectroscopy. Computers & Industrial Engineering, 147, 106566.
   Web of Science ®Google Scholar
• Mao, K.Z., 2005. Identifying critical variables of principal components for unsupervised feature selection. IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), 35 (2), 339–344.
   PubMed Web of Science ®Google Scholar
• Miotto, R., et al., 2018. Deep learning for healthcare: review, opportunities and challenges. Briefings in Bioinformatics, 19 (6), 1236–1246.
   PubMed Web of Science ®Google Scholar
• Modeler, S.P., 2019. Introducing TreeNet gradient boosting machine (Minitab, LLC, State College, PA).
   Google Scholar
• Mora, C.R., et al., 2011. Determination of basic density and moisture content of loblolly pine wood disks using a near infrared hyperspectral imaging system. Journal of Near Infrared Spectroscopy, 19 (5), 401–409.
   Web of Science ®Google Scholar
• Nasir, V., et al., 2019. Classification and characterization of thermally modified timber using visible and near-infrared spectroscopy and artificial neural networks: a comparative study on the performance of different NDE methods and ANNs. Wood Science and Technology, 53, 1093–1109. https://doi.org/10.1007/s00226-019-01120-0
   Web of Science ®Google Scholar
• Nasir, V., et al., 2021a. Cutting tool temperature monitoring in circular sawing: measurement and multi-sensor feature fusion-based prediction. The International Journal of Advanced Manufacturing Technology, 112, 2413–2424. https://doi.org/10.1007/s00170-020-06473-6
   Web of Science ®Google Scholar
• Nasir, V., et al., 2021b. Tool wear monitoring by ensemble learning and sensor fusion using power, sound, vibration, and AE signals. Manufacturing Letters, 30, 32–38. https://doi.org/10.1016/j.mfglet.2021.10.002
   Google Scholar
• Nasir, V., et al., 2022. Acoustic emission monitoring of wood materials and timber structures: A critical review. Construction and Building Materials, 350, 128877. https://doi.org/10.1016/j.conbuildmat.2022.128877
   Web of Science ®Google Scholar
• Nasir, V., et al., 2023. Fiber quality prediction using NIR spectral data: tree-based ensemble learning vs. deep neural networks. Wood and Fiber Science, 55(1), 100–115. https://doi.org/10.22382/wfs-2023-10
   Web of Science ®Google Scholar
• Nasir, V., Fathi, H., and Kazemirad, S., 2021c. Combined machine learning–wave propagation approach for monitoring timber mechanical properties under UV aging. Structural Health Monitoring, 20 (4), 2035–2053. https://doi.org/10.1177/1475921721995987
   Web of Science ®Google Scholar
• Pitak, L., et al., 2021. Machine learning-based prediction of selected parameters of commercial biomass pellets using line scan near infrared-hyperspectral image. Processes, 9 (2), 316.
   Web of Science ®Google Scholar
• Rahimi, S., et al., 2023. The role of drying schedule and conditioning in moisture uniformity in wood: A machine learning approach. Polymers, 15 (4), 792. https://doi.org/10.3390/polym15040792
   PubMed Web of Science ®Google Scholar
• Schimleck, L.R., et al., 2005. Near infrared spectroscopy for the nondestructive estimation of clear wood properties of Pinus taeda L. from the southern United States. Forest Products Journal, 55 (12), 21–28.
   Web of Science ®Google Scholar
• Schimleck, L., et al., 2019. Non-destructive evaluation techniques and what they tell us about wood property variation. Forests, 10 (9), 728.
   Web of Science ®Google Scholar
• Schimleck, L., et al., 2022. Review of near infrared hyperspectral imaging applications related to wood and wood products. Applied Spectroscopy Reviews, 58(9), 585–609.
   Web of Science ®Google Scholar
• Schubert, M., Luković, M., and Christen, H., 2020. Prediction of mechanical properties of wood fiber insulation boards as a function of machine and process parameters by random forest. Wood Science and Technology, 54 (3), 703–713.
   Web of Science ®Google Scholar
• Schwanninger, M., Rodrigues, J.C., and Fackler, K., 2011. A review of band assignments in near infrared spectra of wood and wood components. Journal of Near Infrared Spectroscopy, 19, 287–308.
   Web of Science ®Google Scholar
• Steinberg, D. and Colla, P., 2009. CART: classification and regression trees. In X. Wu, and V. Kumar (eds.) The top ten algorithms in data mining, Volume 9. Boca Raton, FL, USA: CRC Press, 179–202.
   Google Scholar
• Sun, Y., et al., 2021. Wood species recognition with small data: A deep learning approach. International Journal of Computational Intelligence Systems, 14 (1), 1451–1460.
   Web of Science ®Google Scholar
• Thumm, A. and Meder, R., 2001. Stiffness prediction of radiata pine clearwood test pieces using near infrared spectroscopy. Journal of Near Infrared Spectroscopy, 9, 117–122.
   Web of Science ®Google Scholar
• Tsuchikawa, S. and Kobori, H., 2015. A review of recent application of near infrared spectroscopy to wood science and technology. Journal of Wood Science, 61 (3), 213–220.
   Web of Science ®Google Scholar
• van Blokland, J., et al., 2021. Machine learning-based prediction of internal checks in weathered thermally modified timber. Construction and Building Materials, 281, 122193. https://doi.org/10.1016/j.conbuildmat.2020.122193
   Web of Science ®Google Scholar
• Via, B., et al., 2003. Multivariate modelling of density, strength and stiffness from near infrared spectra for mature, juvenile and pith wood of longleaf pine (Pinus palustris). Journal of Near Infrared Spectroscopy, 11. doi:10.1255/jnirs.388.
   Web of Science ®Google Scholar
• Wang, S.Y., et al., 2008. Grading of softwood lumber using non-destructive techniques. Journal of Materials Processing Technology, 208 (1-3), 149–158.
   Web of Science ®Google Scholar
• Wang, J., et al., 2018. Deep learning for smart manufacturing: methods and applications. Journal of Manufacturing Systems, 48, 144–156.
   Web of Science ®Google Scholar
• Watanabe, K., et al., 2014. Application of near-infrared spectroscopy for evaluation of drying stress on lumber surface: A comparison of artificial neural networks and partial least squares regression. Drying Technology, 32 (5), 590–596.
   Web of Science ®Google Scholar
• Xu, Q., et al., 2011. Predictions of wood density and module of elasticity of balsam fir (Abies balsamea) and black spruce (Picea mariana) from near infrared spectral analyses. Canadian Journal of Forest Research, 41 (2), 352–358.
   Web of Science ®Google Scholar
• Yu, L., et al., 2020. Mechanical properties of wood materials using near-infrared spectroscopy based on correlation local embedding and partial least-squares. Journal of Forestry Research, 31 (3), 1053–1060.
   Web of Science ®Google Scholar
• Zhang, M., Liu, Y., and Yang, Z., 2015. Correlation of near infrared spectroscopy measurements with the surface roughness of wood. BioResources, 10 (4), 6953–6960.
   Web of Science ®Google Scholar