Abstract
The combination of computer technology and non-destructive testing technology can facilitate the development of forestry in a more intelligent direction. In this paper, a Shapley additive explanations (SHAP)-based method is used to analyse the importance of band features in the near-infrared spectrum of black walnut wood, which ranges from 900 to 1650 nm. The spectral data from the SHAP analysis are fed into an integrated framework of machine learning algorithms based on four different theories. In the comparison tests, three different pre-processed NIR spectral data are entered into the integrated framework. The result of the SHAP analysis shows that the wavelengths that are positively correlated with the air-dry density of black walnut are 1354.59, 1400.23, 1341.51, 1426.26, 1413.25 nm. The model predictions show that the SHAP-treated spectral data outperformed the other two treatments for each model. For the SHAP-treated spectral data, the KNN model gives the best results with an R2 of 0.947 and an MSE of 0.0010.
Funding source: The Postgraduate Research Practice Innovation Program of Jiangsu Province
Award Identifier / Grant number: SJCX22_0317
Funding source: Technological innovation in the cultivation and efficient use of forestry resources
Award Identifier / Grant number: 2016YFD0600703-2
Acknowledgements
In this paper, the mathematical model SHAP has been used to analyze the importance of the features of the spectral bands, mainly for spectral analysis and dimensionality reduction. An integrated algorithmic framework is built to optimize the machine learning model that is most suitable for predicting the air-dry density of black walnut wood.
-
Research ethics: Not applicable.
-
Author contributions: The first author was responsible for the entire study. The second and corresponding authors provided relevant research ideas and guidance during the course of the study. The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: The authors state no conflict of interest.
-
Research funding: The Postgraduate Research Practice Innovation Program of Jiangsu Province SJCX22_0317.
-
Data availability: The raw data can be obtained on request from the corresponding author.
References
Alves, A., Santos, A., Rozenberg, P., Pâques, L., Charpentier, J., Schwanninger, M., and Rodrigues, J. (2012). A common near infrared-based partial least squares regression model for the prediction of wood density of Pinus pinaster and Larix × eurolepis. Wood Sci. Technol. 46: 157–175, https://doi.org/10.1007/s00226-010-0383-x.Search in Google Scholar
Ato, K., Iwamoto, K., Kawano, N., Noda, Y., Ozaki, N., and Noda, A. (2018). Differential effects of physical activity and sleep duration on cognitive function in young adults. J. Sport Health Sci. 7: 227–236, https://doi.org/10.1016/j.jshs.2017.01.005.Search in Google Scholar PubMed PubMed Central
Bächle, H., Zimmer, B., Windeisen, E., and Wegener, G. (2010). Evaluation of thermally modified beech and spruce wood and their properties by FT-NIR spectroscopy. Wood Sci. Technol. 44: 421–433, https://doi.org/10.1007/s00226-010-0361-3.Search in Google Scholar
Baillères, H., Davrieux, F., and Pichavant, F.H. (2002). Near infrared analysis as a tool for rapid screening of some major wood characteristics in a eucalyptus breeding program. Ann. For. Sci. 59: 479–490, https://doi.org/10.1051/forest:2002032.10.1051/forest:2002032Search in Google Scholar
Birkett, M.D. and Gambino, M.J. (1989). Estimation of pulp kappa number with near-infrared spectroscopy. Tappi J. 72: 193–197.Search in Google Scholar
Breiman, L. (2001). Random forests. Mach. Learn. 45: 5–32.10.1023/A:1010933404324Search in Google Scholar
Carter, E.A. (2011). Spectrochim. Acta Part A: Mol. Biomol. Spectrosc. 80: 1.Search in Google Scholar
Chambi-Legoas, R., Tomazello-Filho, M., Vidal, C., and Chaix, G. (2023). Wood density prediction using near-infrared hyperspectral imaging for early selection of Eucalyptus grandis trees. Trees 37: 981–991, https://doi.org/10.1007/s00468-023-02397-2.Search in Google Scholar
Cortes, C. and Vapnik, V. (1995). Support-vector networks. Mach. Learn 20: 273–297, https://doi.org/10.1007/bf00994018.Search in Google Scholar
Esteves, B. and Pereira, H. (2008). Quality assessment of heat-treated wood by NIR spectroscopy. Holz Roh- Werkst. 66: 323–332, https://doi.org/10.1007/s00107-008-0262-4.Search in Google Scholar
Fengel, D. and Wegener, G. (1983). Wood: chemistry, ultrastructure, reactions. Walter de Gruyter, Berlin, New York.10.1515/9783110839654Search in Google Scholar
Fujimoto, T., Kobori, H., and Tsuchikawa, S. (2012). Prediction of wood density independently of moisture conditions using near infrared spectroscopy. Near Infrared Spectrosc. 20: 353–359, https://doi.org/10.1255/jnirs.994.Search in Google Scholar
Jiang, Z.H., Huang, A.M., and Wang, B. (2006). Near infrared spectroscopy of wood sections and rapid density prediction. Spectrosc. Spectral Anal. 26: 1034–1037.Search in Google Scholar
Jiang, Z.H., Wang, Y.H., and Fei, B.H. (2007). Infrared spectroscopy for rapid prediction of the annual density of viburnum trees. Spectrosc. Spectr. Anal. 6: 1062–1065 (Chinese).Search in Google Scholar
Li, Y., Li, Y.X., Li, W.B., and Jiang, L.C. (2018). Model optimization of wood property and quality tracing based on wavelet transform and NIR spectroscopy. Spectrosc. Spectral Anal. 38: 1384–1392.Search in Google Scholar
Lundberg, S.M., Erion, G.G., and Lee, S.I. (2019). Consistent individualized feature attribution for tree ensembles. ArXiv.org (2019): ArXiv.org. Web.Search in Google Scholar
Ma, T., Inagaki, T., and Tsuchikawa, S. (2018). Non-destructive evaluation of wood stiffness and fiber coarseness, derived from SilviScan data, via near infrared hyperspectral imaging. J. Near Infrared Spectrosc. 26: 398–405, https://doi.org/10.1177/0967033518808053.Search in Google Scholar
Mitsui, K., Inagaki, T., and Tsuchikawa, S. (2008). Monitoring of hydroxyl groups in wood during heat treatment using NIR spectroscopy. Biomacromolecules 9: 286–288, https://doi.org/10.1021/bm7008069.Search in Google Scholar PubMed
Santos, A.J.A., Alves, A.M.M., Simoe, R.M.S., Pereira, H., Rodrigues, J., and Schwanninger, M. (2012). Estimation of wood basic density of Acacia melanoxylon (R. Br.) by near infrared spectroscopy. J. Near Infrared Spectrosc. 20: 267–274, https://doi.org/10.1255/jnirs.986.Search in Google Scholar
Schwanninger, M., Hinterstoisser, B., Gierlinger, N., Wimmer, R., and Hanger, J. (2004). Application of Fourier transform near infrared spectroscopy (FT-NIR) to thermally modified wood. Holz Roh- Werkst. 62: 483–485, https://doi.org/10.1007/s00107-004-0520-z.Search in 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. J. Near Infrared Spectrosc. 19: 287–308, https://doi.org/10.1255/jnirs.955.Search in Google Scholar
Shukla, S.R. and Sharma, S.K. (2021). Estimation of density, moisture content and strength properties of Tectona grandis wood using near infrared spectroscopy. Maderas: Ciencia y Tecnologia 23: 1–12, https://doi.org/10.4067/s0718-221x2021000100418.Search in Google Scholar
Su, Y.L., Zhang, H.Z., and Zhu, L. (2011). Research status and development of wood density testing methods. Forest engineering. 27: 23–26 (Chinese).10.1016/j.sepro.2011.08.005Search in Google Scholar
Tan, N., Wang, X.S., Huang, A.M., and Wang, C. (2018). Wood density prediction of Cunninghamia lanceolata based on Gray Wolf algorithm SVM and NIR. For. Sci. 12: 137.Search in Google Scholar
Tham, V.T.H., Inagaki, T., and Tsuchikawa, S. (2018). A novel combined application of capacitive method and near-infrared spectroscopy for predicting the density and moisture content of solid wood. Wood Sci. Technol. 52: 115–129, https://doi.org/10.1007/s00226-017-0974-x.Search in Google Scholar
Via, B.K., So, C.L., Shupe, T.F., Stine, M., and Groom, L.H. (2005). Ability of near infrared spectroscopy to monitor air-dry density distribution and variation of wood. Wood Fiber Sci. 37: 394–402.Search in Google Scholar
Wang, H.Y., Zuo, X., and Wang, D.L. (2017). The estimation of forest residue resources in China. J. Central South Univ. For. Technol. 37: 29–38, 43.Search in Google Scholar
Watanabe, A., Morita, S., and Ozaki, Y. (2006). Temperature-dependent structural changes in hydrogen bonds in microcrystalline cellulose studied by infrared and near-infrared spectroscopy with perturbation-correlation moving-window two-dimensional correlation analysis. Appl. Spectrosc. 60: 611–618, https://doi.org/10.1366/000370206777670549.Search in Google Scholar PubMed
Williams, P., Antoniszyn, J., and Manley, M. (2019). Near infrared technology: Getting the best out of light, 1st ed African Sun Media, South Africa.10.18820/9781928480310Search in Google Scholar
Yin, S.K., Li, C.K., and Meng, Y.B. (2020). Near-infrared spectral estimation and model optimization of basic density of linden wood based on different pre-treatments. J. Central South Univ. For. Technol. 40: 171–180 (Chinese).Search in Google Scholar
Zobel, B.J. and Buijtenen, J.P. (1989). Wood variation: its causes and control. Springer, New York, USA, pp. 1–34.10.1007/978-3-642-74069-5_1Search in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston
