Feasibility of chemometric and machine learning strategy for lignin type identification using FT-IR spectroscopic data
Source abstract
Abstract
Abstract Proto-lignin and technical lignin differ in functional groups, degree of condensation, and purity. Rapid and reliable classification between these types supports optimized valorization in biorefineries. This study presents a chemometric and machine learning approach for the reliable classification of lignin types using Fourier-transform infrared (FT-IR) spectroscopic data. FT-IR spectra, in combination with advanced preprocessing and classification algorithms, were employed to distinguish between proto-lignin and technical lignin with high accuracy (>83 %). Among the tested classifiers, partial least squares discriminant analysis (PLS-DA) demonstrated superior performance in terms of accuracy, precision, sensitivity, and specificity. Extensive model optimization was performed using various spectral pretreatment techniques, and the combination of standard normal variate (SNV) with Savitzky–Golay (S–G) first-derivative filtering yielded the highest classification efficiency. FT-IR spectral data covering the full range (4,000–650 cm −1 ) and its three segmented regions were evaluated separately; however, the full-range spectra produced the most robust model, achieving R 2 values of 99.35 % for calibration and 93.30 % for validation. The proposed methodology offers a rapid, non-destructive, and cost-effective screening tool for distinguishing lignin types, providing a valuable analytical strategy for lignin characterization and quality control in biorefinery applications.
Source: crossref · Quality: baseline
Affiliations
Pulp and Paper Research Division, Bangladesh Council of Scientific and Industrial Research Laboratories , Dr. Qudrat-i-Khuda Road , Dhaka , 1205 , Bangladesh
Department of Forest Biomaterials , North Carolina State University , Raleigh , NC , USA
Funding
Bangladesh Council of Scientific and Industrial Research
References (51)
Show source-provided references
1. Al-Mbaideen, A.A. (2019). Application of moving average filter for the quantitative analysis of the NIR spectra. J. Anal. Chem. 74: 686–692, https://doi.org/10.1134/s1061934819070013.10.1134/S1061934819070013 ↗
2. Ballabio, D., and Consonni, V. (2013). Classification tools in chemistry. Part 1: linear models. PLS-DA. Anal. Methods 5: 3790–3798, https://doi.org/10.1039/c3ay40582f.10.1039/c3ay40582f ↗
3. Banerjee, P., Dehnbostel, F.O., and Preissner, R. (2018). Prediction is a balancing act: importance of sampling methods to balance sensitivity and specificity of predictive models based on imbalanced chemical data sets. Front. Chem. 6: 362, https://doi.org/10.3389/fchem.2018.00362.10.3389/fchem.2018.00362 ↗
4. Barker, M., and Rayens, W. (2003). Partial least squares for discrimination. J. Chemometrics 17: 166–173, https://doi.org/10.1002/cem.785.10.1002/cem.785 ↗
5. Bausch, F., Khaliliyan, H., Tsetsgee, O., Owusu, D.D., Böhmdorfer, S., Rosenau, T., and Potthast, A. (2025). Classification of papyrus fragments by chemometric analysis of near-infrared spectra. Spectrochim. Acta. A Mol. Biomol. Spectrosc. 325: 125103, https://doi.org/10.1016/j.saa.2024.125103.10.1016/j.saa.2024.125103 ↗
6. Biancolillo, A., and Marini, F. (2018). Chemometric methods for spectroscopy-based pharmaceutical analysis. Front. Chem. 6: 576, https://doi.org/10.3389/fchem.2018.00576.10.3389/fchem.2018.00576 ↗
7. Bishop, C.M. (1995). Neural networks for pattern recognition. Oxford University Press, Oxford.10.1093/oso/9780198538493.001.0001 ↗
8. Brereton, R.G. (2003). Chemometrics: data analysis for the laboratory and chemical plant. John Wiley & Sons, Chichester, England.10.1002/0470863242 ↗
9. Brereton, R.G. (2018). Chemometrics: data driven extraction for science. John Wiley & Sons.10.1002/9781118904695 ↗
10. Brown, S.D., Tauler, R., and Walczak, B. (2009). Comprehensive chemometrics. Chemical and biochemical data analysis. Anal. Bioanal. Chem. 396: 551–552.10.1007/s00216-009-3284-9 ↗
11. Cover, T., and Hart, P. (1967). Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13: 21–27, https://doi.org/10.1109/tit.1967.1053964.10.1109/TIT.1967.1053964 ↗
12. Cristianini, N., and Shawe-Taylor, J. (2000). An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, Cambridge.10.1017/CBO9780511801389 ↗
13. Faix, O. (1991). Classification of lignins from different botanical origins by FT-IR spectroscopy. Holzforschung 45: 21–28, https://doi.org/10.1515/hfsg.1991.45.s1.21.10.1515/hfsg.1991.45.s1.21 ↗
14. Ferdous, T., Quaiyyum, M.A., Salam, A., and Jahan, M.S. (2020). Pulping of bagasse (Saccrarum officinarum), kash (Saccharum spontaneum) and corn stalks (Zea mays). Curr Res Green Sust Chem 3: 100017.10.1016/j.crgsc.2020.100017 ↗
15. Fink, F., Stawski, T.M., Emmerling, F., and Falkenhagen, J. (2025). A novel machine-learning approach to unlock technical lignin classification by NIR spectroscopy-bench to handheld. Chemom. Intell. Lab. Syst. 264: 105467, https://doi.org/10.1016/j.chemolab.2025.105467.10.1016/j.chemolab.2025.105467 ↗
16. Ganewatta, M.S., Lokupitiya, H.N., and Tang, C. (2019). Lignin biopolymers in the age of controlled polymerization. Polymers 11: 1176, https://doi.org/10.3390/polym11071176.10.3390/polym11071176 ↗
17. Herrera, R., Hermoso, E., Labidi, J., and Fernandez-Golfin, J.I. (2022). Non-destructive determination of core-transition-outer wood of Pinus nigra combining FTIR spectroscopy and prediction models. Microchem. J. 179: 107532, https://doi.org/10.1016/j.microc.2022.107532.10.1016/j.microc.2022.107532 ↗
18. Ho, T.K. (1998). The random subspace method for constructing decision forests. IEEE Trans. Pattern Anal. Mach. Intell. 20: 832–844.10.1109/34.709601 ↗
19. Hosmer, D.W., Lemeshow, S., and Sturdivant, R.X. (2013). Applied logistic regression, 3rd ed. John Wiley & Sons, New York, USA.10.1002/9781118548387 ↗
20. Jahan, M.S., and Mun, S.P. (2006). Characteristics of milled wood lignins isolated from different ages of nalita wood (Trema orientalis). Cellulose Chem. Technol. 40: 457–467.
21. Jahan, M.S., and Rahman, M.M. (2025). Organosolv lignin: extraction. In: Handbook of lignin. Springer Nature Singapore, Singapore, pp. 163–175.10.1007/978-981-96-7633-0_8 ↗
22. Jesus, E., Franca, T., Calvani, C., Lacerda, M., Gonçalves, D., Oliveira, S.L., and Cena, C. (2024). Making wood inspection easier: FTIR spectroscopy and machine learning for Brazilian native commercial wood species identification. RSC Adv. 14: 7283–7289, https://doi.org/10.1039/d4ra00174e.10.1039/D4RA00174E ↗
23. Jiao, Y., Li, Z., Chen, X., and Fei, S. (2020). Preprocessing methods for near‐infrared spectrum calibration. J. Chemometrics 34: e3306, https://doi.org/10.1002/cem.3306.10.1002/cem.3306 ↗
24. Jolliffe, I.T., and Cadima, J. (2016). Principal component analysis: a review and recent developments. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 374: 20150202, https://doi.org/10.1098/rsta.2015.0202.10.1098/rsta.2015.0202 ↗
25. Lacerda, M., Franca, T., Calvani, C., Marangoni, B., Teodoro, P., Campos, C.N.S., and Cena, C. (2024). A simple method for eucalyptus species discrimination: FTIR spectroscopy and machine learning. Results Chem. 7: 101233, https://doi.org/10.1016/j.rechem.2023.101233.10.1016/j.rechem.2023.101233 ↗
26. Lavine, B.K., and Workman, Jr, J. (2013). Chemometrics. Anal. Chem. 85: 705–714.10.1021/ac303193j ↗
27. Lavine, B.K., Davidson, C.E., Moores, A.J., and Griffiths, P.R. (2001). Raman spectroscopy and genetic algorithms for the classification of wood types. Appl. Spectrosc. 55: 960–966, https://doi.org/10.1366/0003702011953108.10.1366/0003702011953108 ↗
28. Likhon, M.N.A., Rahman, M.M., Jiang, B., Jin, Y., and Jahan, M.S. (2026). Structural and compositional characteristics of technical lignin derived from non‐wood biomass: bagasse and kash. Adv. Polym. Technol. 2026: 2203670, https://doi.org/10.1155/adv/2203670.10.1155/adv/2203670 ↗
29. Lupoi, J.S., Gjersing, E., and Davis, M.F. (2015). Evaluating lignocellulosic biomass, its derivatives, and downstream products with Raman spectroscopy. Front. Bioeng. Biotechnol. 3: 50, https://doi.org/10.3389/fbioe.2015.00050.10.3389/fbioe.2015.00050 ↗
30. Maleki, M.R., Mouazen, A.M., Ramon, H., and De Baerdemaeker, J. (2007). Multiplicative scatter correction during on-line measurement with near infrared spectroscopy. Biosyst. Eng. 96: 427–433, https://doi.org/10.1016/j.biosystemseng.2006.11.014.10.1016/j.biosystemseng.2006.11.014 ↗
31. Mueller, D., Ferrão, M.F., Marder, L., Da Costa, A.B., and de Cássia de Souza Schneider, R. (2013). Fourier transform infrared spectroscopy (FTIR) and multivariate analysis for identification of different vegetable oils used in biodiesel production. Sensors 13: 4258–4271, https://doi.org/10.3390/s130404258.10.3390/s130404258 ↗
32. Otto, M. (2023). Chemometrics: statistics and computer application in analytical chemistry. John Wiley & Sons, New York, USA.10.1002/9783527843800 ↗
33. Rahman, M.M., Arafat, K.M.Y., Jin, Y., Chen, H., and Jahan, M.S. (2023). Structural characterization of potassium hydroxide liquor lignin and its application in biorefinery. Biomass Convers. Biorefinery 13: 727–737, https://doi.org/10.1007/s13399-020-01202-1.10.1007/s13399-020-01202-1 ↗
34. Rashidi, H.H., Albahra, S., Robertson, S., Tran, N.K., and Hu, B. (2023). Common statistical concepts in the supervised machine learning arena. Front. Oncol. 13: 1130229, https://doi.org/10.3389/fonc.2023.1130229.10.3389/fonc.2023.1130229 ↗
35. Rinnan, A., van den Berg, F., and Engelsen, S.B. (2009). Review of the most common pre-processing techniques for near-infrared spectra. TrAC Trends Anal. Chem. 28: 1201–1222, https://doi.org/10.1016/j.trac.2009.07.007.10.1016/j.trac.2009.07.007 ↗
36. Schölkopf, B. and Smola, A.J. (2002). Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT press, Cambridge, MA.10.7551/mitpress/4175.001.0001 ↗
37. Sharma, V., Yadav, J., Kumar, R., Tesařová, D., Kučerová, V., and Havel, J. (2020). On the rapid and non-destructive approach for wood identification using ATR-FTIR spectroscopy and chemometric methods. Vib. Spectrosc. 110: 103097, https://doi.org/10.1016/j.vibspec.2020.103097.10.1016/j.vibspec.2020.103097 ↗
38. Sun, X., Zhou, M., and Sun, Y. (2016). Classification of textile fabrics by use of spectroscopy-based pattern recognition methods. Spectrosc. Lett. 49: 96–102, https://doi.org/10.1080/00387010.2015.1089446.10.1080/00387010.2015.1089446 ↗
39. Tsuchikawa, S., Yamato, K., and Inoue, K. (2003). Discriminant analysis of wood-based materials using near-infrared spectroscopy. J. Wood Sci. 49: 275–280, https://doi.org/10.1007/s10086-002-0471-0.10.1007/s10086-002-0471-0 ↗
40. Tuncer, F.D. (2023). Comparing modelling performance of chemometric methods for wood discrimination by near infrared spectroscopy. Wood Mater. Sci. Eng. 18: 422–433, https://doi.org/10.1080/17480272.2022.2039960.10.1080/17480272.2022.2039960 ↗
41. Uddin, M.N., Ferdous, T., Jin, Y., Rahman, M.M., and Jahan, M.S. (2025). Chemometric model for rapid determination of syringyl/guaiacyl ratio in non‐wood by FT‐NIR spectroscopic data. Anal. Sci. Adv. 6: e70005, https://doi.org/10.1002/ansa.70005.10.1002/ansa.70005 ↗
42. Uddin, M.N., Likhon, M.N.A., Rahman, M.M., Jin, Y., Jiang, B., Uddin, M.T., and Jahan, M.S. (2025). Determination of aliphatic and phenolic hydroxyl groups in lignin by chemometric analysis of FTIR spectroscopic data. TAPPI J. 24: 479–490, https://doi.org/10.32964/TJ24.10.479.10.32964/TJ24.10.479 ↗
43. Uddin, M.N., Majumder, A.K., Abdullah, A.T.M., and Kabir, M.A. (2017). Chemometrics assisted method for classification of mango juice as adulterated or safe with over use of artificial colours by UV spectroscopic data. J. Food Nutr. Sci. 5: 51–56.10.11648/j.jfns.20170502.15 ↗
44. Uddin, M.N., Ray, S.K., Islam, M.S., Karim, M.M., and Jahan, M.S. (2022). Quantification of components of textile fabrics by using chemometric techniques with FT-NIR spectroscopic data. Bangl. J. Sci. Ind. Res. 57: 229–238, https://doi.org/10.3329/bjsir.v57i4.63377.10.3329/bjsir.v57i4.63377 ↗
45. Vapnik, V.N. (1998). Statistical learning theory. Wiley, New York.
46. Wang, Z., and Deuss, P.J. (2023). The isolation of lignin with native-like structure. Biotechnol. Adv. 68: 108230, https://doi.org/10.1016/j.biotechadv.2023.108230.10.1016/j.biotechadv.2023.108230 ↗
47. Windig, W., Shaver, J., and Bro, R. (2008). Loopy MSC: a simple way to improve multiplicative scatter correction. Appl. Spectrosc. 62: 1153–1159, https://doi.org/10.1366/000370208786049097.10.1366/000370208786049097 ↗
48. Wold, S., Esbensen, K., and Geladi, P. (1987). Principal component analysis. Chemom. Intell. Lab. Syst. 2: 37–52, https://doi.org/10.1016/0169-7439(87)80084-9.10.1016/0169-7439(87)80084-9 ↗
49. Wold, S., Sjöström, M., and Eriksson, L. (2001). PLS-regression: a basic tool of chemometrics. Chemom. Intell. La. Syst. 58: 109–130, https://doi.org/10.1016/s0169-7439(01)00155-1.10.1016/S0169-7439(01)00155-1 ↗
50. Zhou, Z., Rahimi, S., and Avramidis, S. (2020). On-line species identification of green hem-fir timber mix based on near infrared spectroscopy and chemometrics. Eur. J. Wood Prod. 78: 151–160, https://doi.org/10.1007/s00107-019-01479-8.10.1007/s00107-019-01479-8 ↗
51. Zupan, J., and Gasteiger, J. (1999). Neural networks in chemistry and drug design. Wiley VCH, Weinheim.