Interpreting the relationship between properties of wood and pulping & paper via machine learning algorithms combined with SHAP analysis
Source abstract
Abstract
Abstract The pulping ability and quality of paper high relay on the wood properties. However, the relationship between them are profound. Based on the extracting digital information from the anatomical, chemical, and physical properties of poplar wood, predictive models were developed for paper properties (tensile index, burst index and tear index) and pulping properties (Kappa number and pulp yield) using six algorithms, namely PLSR, ENR, RF, XGBoost, LightGBM, and CatBoost. The prediction results revealed that among the six algorithms, PLSR, ENR, and RF exhibited results of most prediction greater than 0.79. Notably, XGBoost, LightGBM, and CatBoost algorithms demonstrated superior predictive performance, with results greater than 0.9, except for the tear index. Furthermore, SHAP analysis suggested that the cellulose content is the primary factors to modulate pulping ability and the morphological features of cell wall shows apparent effects on mechanical properties of paper. It hopes the result will benefit to provide information to evaluate the value of poplar wood from different resources and then deliver instructions to genetic breeding program and forest management of poplar plantation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Wood Treatment and Properties · Lignin and Wood Chemistry · Natural Fiber Reinforced Composites
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of National Forestry and Grassland Administration “Wood Quality Improvement & Efficient Utilization”, School of Materials and Chemistry , 12486 Anhui Agricultural University , Hefei 230036 , China
Funding
National Natural Science Foundation of China
References (56)
Show source-provided references
1. Amidon, T.E. (1981). Effect of the wood properties of hardwoods on kraft paper properties. Tappi 64: 123–126.
2. Bangdiwala, S.I. (2018). Regression: multiple linear. Inter. J. Inj. Control and Saf. Promot. 25: 232–236, https://doi.org/10.1080/17457300.2018.1452336.10.1080/17457300.2018.1452336 ↗
3. Baptista, M.L., Goebel, K., and Henriques, E.M.P. (2022). Relation between prognostics predictor evaluation metrics and local interpretability SHAP values. Artif. Intell. 306, https://doi.org/10.1016/j.artint.2022.1033667.10.1016/j.artint.2022.103667 ↗
4. Barrett, J.P. (1974). The coefficient of determination–some Limitations. Am. Statistician 28: 19–20, https://doi.org/10.1080/00031305.1974.10479056.10.1080/00031305.1974.10479056 ↗
5. Bentéjac, C., Csörgő, A., Martínez-Muñoz, G. (2021). A comparative analysis of gradient boosting algorithms. Artif. Intell. Rev. 54:1937–1967, https://doi.org/10.1007/s10462-020-09896-5.10.1007/s10462-020-09896-5 ↗
6. Brumen, B., Černezel, A., and Bošnjak, L. (2021). Overview of machine learning process modelling. Entropy 23: 112, https://doi.org/10.3390/e23091123, https://www.mdpi.com/1099-4300/23/9/1123.10.3390/e23091123 ↗
7. Chen, Y., Yan, Z., Liang, L., Ran, M., Wu, T., Wang, B., Zou, X., Zhao, M., Fang, G., and Shen, K. (2020). Comparative evaluation of organic acid pretreatment of eucalyptus for kraft dissolving pulp production. Materials 13: 361, https://doi.org/10.3390/ma13020361, https://www.mdpi.com/1996-1944/13/2/361.10.3390/ma13020361 ↗
8. Cheng, J., Sun, J., Yao, K., Xu, M., and Cao, Y. (2022). A variable selection method based on mutual information and variance inflation factor. Spectrochim. Acta : Mol. Biomol. Spectrosc. 268, https://doi.org/10.1016/j.saa.2021.120652.10.1016/j.saa.2021.120652 ↗
9. Chow, K.Y. (1947). A comparative study of the structure and composition of tension wood in beech. (Fagus sylvatica L.). Forestry 20: 62–77, https://doi.org/10.1093/forestry/20.1.62.10.1093/forestry/20.1.62 ↗
10. Cui, Z., Li, X., Li, T., and Li, M. (2023). Improvement and assessment of convolutional neural network for tree species identification based on bark characteristics. Forests 14, https://doi.org/10.3390/f14071292, https://www.mdpi.com/1999-4907/14/7/1292.10.3390/f14071292 ↗
11. Duplooy, A.B.J. (1980). The relationship between wood and pulp properties of E. grandis (Hill ex-Maiden) grown in South Africa. Appita 33: 257–264.
12. Freund, Y. (2001). An adaptive version of the boost by majority algorithm. Mach. Learn. 43: 293–318, https://doi.org/10.1023/A:1010852229904.10.1023/A:1010852229904 ↗
13. Gao, W., Zhou, L., Jiang, Q., Guan, Y., Hou, R., Hui, B., and Liu, S. (2022a). Reliable and realistic models for lignin content determination in poplar wood based on FT-Raman spectroscopy. Ind. Crops Prod. 182, https://doi.org/10.1016/j.indcrop.2022.114884.10.1016/j.indcrop.2022.114884 ↗
14. Gao, W., Zhou, L., Liu, S., Guan, Y., Gao, H., and Hui, B. (2022b). Machine learning prediction of lignin content in poplar with Raman spectroscopy. Bioresour. Technol. 348, https://doi.org/10.1016/j.biortech.2022.126812.10.1016/j.biortech.2022.126812 ↗
15. Gewers, F.L., Ferreira, G.R., Arruda, H.F.D., Silva, F.N., Comin, C.H., Amancio, D.R., and Costa, L.D.F. (2021). Principal component analysis. ACM Comput. Survey. 54: 1–34, https://doi.org/10.1145/3447755.10.1145/3447755 ↗
16. Gobeyn, S., Mouton, A.M., Cord, A.F., Kaim, A., Volk, M., and Goethals, P.L.M. (2019). Evolutionary algorithms for species distribution modelling: a review in the context of machine learning. Ecological Modell. 392: 179–195, https://doi.org/10.1016/j.ecolmodel.2018.11.013.10.1016/j.ecolmodel.2018.11.013 ↗
17. Greenacre, M., Groenen, P.J.F., Hastie, T., D’Enza, A.I., Markos, A., and Tuzhilina, E. (2022). Principal component analysis. Nat. Rev. Methods Prim. 2: 100, https://doi.org/10.1038/s43586-022-00184-w.10.1038/s43586-022-00184-w ↗
18. Hajihosseinlou, M., Maghsoudi, A., and Ghezelbash, R. (2023). A novel scheme for mapping of MVT-Type Pb–Zn Prospectivity: LightGBM, a highly efficient gradient boosting decision tree machine learning algorithm. Nat. Resour. Res. 32: 2417–2438, https://doi.org/10.1007/s11053-023-10249-6.10.1007/s11053-023-10249-6 ↗
19. Konstantinov, A.V. and Utkin, L.V. (2021). Interpretable machine learning with an ensemble of gradient boosting machines. Knowl.-Base. Syst. 222, https://doi.org/10.1016/j.knosys.2021.106993.10.1016/j.knosys.2021.106993 ↗
20. Kotsiantis, S. (2011). Combining bagging, boosting, rotation forest and random subspace methods. Artif. Intell. Rev. 35: 223–240, https://doi.org/10.1007/s10462-010-9192-8.10.1007/s10462-010-9192-8 ↗
21. Kumar, A., Srivastava, N.K., and Gera, P. (2021). Removal of color from pulp and paper mill wastewater- methods and techniques. A Rev. J. Environ. Manage. 298, https://doi.org/10.1016/j.jenvman.2021.113527.10.1016/j.jenvman.2021.113527 ↗
22. Kumar, D., Sood, S.K., and Rawat, K.S. (2023). Early health prediction framework using XGBoost ensemble algorithm in intelligent environment. Artif. Intell. Rev. 56: 1591–1615, https://doi.org/10.1007/s10462-023-10565-6.10.1007/s10462-023-10565-6 ↗
23. Lee, Y.-G., Oh, J.-Y., Kim, D., and Kim, G. (2023). SHAP Value-Based feature importance analysis for Short-Term load forecasting. J. Electrical Eng. Technol. 18: 579–588, https://doi.org/10.1007/s42835-022-01161-9.10.1007/s42835-022-01161-9 ↗
24. Li, R., Wang, X., Lei, L., and Song, Y. (2019a). L21 -Norm based loss function and regularization extreme learning machine. IEEE Access 7: 6575–6586, https://doi.org/10.1109/ACCESS.2018.2887260.10.1109/ACCESS.2018.2887260 ↗
25. Li, Y., Liang, Z., Hu, Y., Li, B., Xu, B., and Wang, D. (2019b). A multi-model integration method for monthly streamflow prediction: modified stacking ensemble strategy. J. Hydroinf. 22: 310–326, https://doi.org/10.2166/hydro.2019.066.10.2166/hydro.2019.066 ↗
26. Liang, L., Wei, L., Fang, G., Xu, F., Deng, Y., Shen, K., Tian, Q., Wu, T., and Zhu, B. (2020). Prediction of holocellulose and lignin content of pulp wood feedstock using near infrared spectroscopy and variable selection. Spectrochim. Acta : Molecul. Biomol. Spectrosc. 225, https://doi.org/10.1016/j.saa.2019.117515.10.1016/j.saa.2019.117515 ↗
27. Liu, Y., Wu, X., Zhang, J., Liu, S., Semple, K., and Dai, C. (2023). Maturation stress and wood properties of poplar (Populus × euramericana cv. ‘Zhonglin46’) Tension Wood. Forests 14, https://doi.org/10.3390/f14071505, https://www.mdpi.com/1999-4907/14/7/1505.10.3390/f14071505 ↗
28. Mabula, M.J., Kisanga, D., and Pamba, S. (2023). Application of machine learning algorithms and sentinel-2 satellite for improved bathymetry retrieval in lake victoria, Tanzania. Egypt. J. Rem. Sens. Space Sci. 26: 619–627, https://doi.org/10.1016/j.ejrs.2023.07.003.10.1016/j.ejrs.2023.07.003 ↗
29. Mahdi, G.J.M., Mohammed, N.J., and Al-Sharea, Z.I. (2021) Regression shrinkage and selection variables via an adaptive elastic net model. J. Phys.: Conf. Ser. 1879, https://doi.org/10.1088/1742-6596/1879/3/032014.10.1088/1742-6596/1879/3/032014 ↗
30. Mansfield, S.D. and Weineisen, H. (2010). Wood fiber quality and kraft pulping efficiencies of trembling aspen (Populus tremuloides Michx) Clones. J. Wood Chem. Technol. 27: 135–151, https://doi.org/10.1080/02773810700786.10.1080/02773810701700786 ↗
31. McMillin, C.W. (1969a). Quality of refiner groundwood pulp as related to handsheet properties and gross wood characteristics. Wood Sci. Technol. 3: 287–300, https://doi.org/10.1007/BF00367214.10.1007/BF00352303 ↗
32. Mcmillin, C.W. (1969b). Wood chemical composition as related to properties of handsheets made from loblolly pine refiner groundwood. Wood Sci. Technol. 3: 232–238, https://doi.org/10.1007/bf00367214.10.1007/BF00367214 ↗
33. Molteberg, D. and Høibø, O. (2006). Development and variation of wood density, kraft pulp yield and fibre dimensions in young Norway spruce (Picea abies). Wood Sci. Technol. 40: 173–189, https://doi.org/10.1007/s00226-005-0020-2.10.1007/s00226-005-0020-2 ↗
34. Na, K.-S. and Kim, E. (2019). A machine learning-based predictive model of return to work after sick leave. J. Occup. Environ. Med. 61: 191–199, https://doi.org/10.1097/jom.0000000000001567.10.1097/JOM.0000000000001567 ↗
35. Okwuashi, O., Ndehedehe, C., and Attai, H. (2020). Tide modeling using partial least squares regression. Ocean Dynam. 70: 1089–1101, https://doi.org/10.1007/s10236-020-01385-1.10.1007/s10236-020-01385-1 ↗
36. Oluwadare, A.O. and Sotannde, O.A. (2007). The relationship between fibre characteristics and pulp-sheet properties of leucaena leucocephala (Lam.) De Wit. Middle East J. Sci. Res. 2: 63–68.
37. Parham, R.A., Robinson, K.W., and Isebrands, J.G. (1977). Effects of tension wood on kraft paper from a short-rotation hardwood (Populus “Tristis No. 1”). Wood Sci. Technol. 11: 291–303, https://doi.org/10.1007/bf00356927.10.1007/BF00356927 ↗
38. Pattanayak, S. and Singh, T. (2022). Cardiovascular disease classification based on machine learning algorithms using gridSearchCV, cross validation and stacked ensemble methods, Vol. 4. Springer, Cham, pp. 219–230.10.1007/978-3-031-12638-3_19 ↗
39. Rajkomar, A., Dai, A.M., Sun, M., Hardt, M., Chen, K., Rough, K., and Dean, J. (2018). Reply: metrics to assess machine learning models. Npj Digit. Med. 1: 57, https://doi.org/10.1038/s41746-018-0063-z.10.1038/s41746-018-0063-z ↗
40. Ramirez, M., Rodriguez, J., Balocchi, C., Peredo, M., Elissetche, J.P., Mendonca, R., and Valenzuela, S. (2009). Chemical composition and wood anatomy of eucalyptus globulus clones: variations and relationships with pulpability and handsheet properties. J. Wood Chem. Technol. 29: 43–58, https://doi.org/10.1080/02773810802607559.10.1080/02773810802607559 ↗
41. Schonlau, M. and Zou, R.Y. (2020). The random forest algorithm for statistical learning. The Stata J. 20: 3–29, https://doi.org/10.1177/1536867X20909688.10.1177/1536867X20909688 ↗
42. Seth, R.S. and Page, D.H. (1988). Fiber properties and tearing resistance. Tappi J. 71: 103–107.
43. Sheikh, M. and Coolen, A.C.C. (2019). Analysis of overfitting in the regularized cox model. J. Phys. A: Math. Theor. 52: 384002, https://doi.org/10.1088/1751-8121/ab375c.10.1088/1751-8121/ab375c ↗
44. Sheng-zuo, F., Wen-zhong, Y., and Xiang-xiang, F. (2004). Variation of microfibril angle and its correlation to wood properties in poplars. J. Fores. Res. 15: 261–267, https://doi.org/10.1007/bf02844949.10.1007/BF02844949 ↗
45. Sun, Z., Xu, B., Jin, F., Zhou, G., Lin, L. (2022). Machine learning approach for on-demand rapid constructing metasurface. IEEE J. Sel. Top. Quantum Electron. 28: 1–9, https://doi.org/10.1109/JSTQE.2021.3083565.10.1109/JSTQE.2021.3083565 ↗
46. Szadkowska, D., Zawadzki, J., Kozakiewicz, P., and Radomski, A. (2021). Identification of extractives from various poplar species. Forests 12: 647, https://doi.org/10.3390/f12050647, https://www.mdpi.com/1999-4907/12/5/647.10.3390/f12050647 ↗
47. Tavassoli, N., Poursorkh, Z., Bicho, P., and Grant, E. (2020). TOGA feature selection and the prediction of mechanical properties of paper from the Raman spectra of unrefined pulp. Anal. Bioanal. Chem. 412: 8401–8415, https://doi.org/10.1007/s00216-020-02978-x.10.1007/s00216-020-02978-x ↗
48. Tominaga, Y. and Fujiwara, I. (1997). Prediction-weighted partial least-squares regression method (PWPLS). Chemom. Intell. Lab. Syst. 38: 139–144, https://doi.org/10.1016/S0169-7439(97)00043-9.10.1016/S0169-7439(97)00043-9 ↗
49. Uzun, İ. (2023). Methods of determining the degree of crystallinity of polymers with X-ray diffraction: a review. J. Polym. Res. 30: 394, https://doi.org/10.1007/s10965-023-03744-0.10.1007/s10965-023-03744-0 ↗
50. Virtanen, P., Gommers, R., Oliphant, T.E., Haberland, M., Reddy, T., Cournapeau, D. (2020). SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat. Methods 17: 261–272, https://doi.org/10.1038/s41592-019-0686-2.10.1038/s41592-020-0772-5 ↗
51. Wheeler, D. and Tiefelsdorf, M. (2005). Multicollinearity and correlation among local regression coefficients in geographically weighted regression. J. Geograph. Syst. 7: 161–187, https://doi.org/10.1007/s10109-005-0155-6.10.1007/s10109-005-0155-6 ↗
52. Xia, J., Min, S., and Li, J. (2023). Rapid analysis the type of customs paper using Micro-NIR spectrometers and machine learning algorithms. Spectrochim. Acta : Mol. Biomol. Spectrosc. 290, https://doi.org/10.1016/j.saa.2022.122272.10.1016/j.saa.2022.122272 ↗
53. Xiao, T., Zhu, J., Liu, T. (2013). Bagging and Boosting statistical machine translation systems. Artif. Intell. 195: 496–527, https://doi.org/10.1016/j.artint.2012.11.005.10.1016/j.artint.2012.11.005 ↗
54. Yang, H., Liu, Y., Xiong, Z., and Liang, L. (2019). Rapid determination of holocellulose and lignin in wood by Near Infrared Spectroscopy and kernel extreme learning machine. Anal. Lett. 53: 1–15, https://doi.org/10.1080/00032719.2019.1700267.10.1080/00032719.2019.1700267 ↗
55. Yoon, H.I., Lee, H., Yang, J.-S., Choi, J.-H., Jung, D.-H., Park, Y.J., Park, J.-E., Kim, S.M., Park, S.H. (2023). Predicting models for plant metabolites based on PLSR, AdaBoost, XGBoost, and LightGBM algorithms using hyperspectral imaging of brassica juncea. Agriculture 13: 1477, https://doi.org/10.3390/agriculture13081477.10.3390/agriculture13081477 ↗
56. Zhang, W., Kasun, L.C., Wang, Q.J., Zheng, Y., and Lin, Z. (2022). A review of machine learning for Near-Infrared spectroscopy. Sensors 22: 9764, https://doi.org/10.3390/s22249764.10.3390/s22249764 ↗