Development and validation of regression models from NIR spectra to predict the composition of sugarcane, soybean meal, and cornmeal
DOI:
https://doi.org/10.5433/1679-0359.2023v44n2p859Keywords:
Chemometrics, Partial least squares regression, Spectroscopy.Abstract
This study aimed to develop and assess regression models for predicting the chemical composition of sugarcane, soybean meal, and cornmeal using portable near-infrared (NIR) spectroscopy combined with chemometric techniques. A total of 95 sugarcane samples, 92 soybean meal samples, and 120 cornmeal samples were used. The samples were ground, and NIR spectra were obtained for each sample. Reference values were determined through conventional chemical analysis. Partial least squares regression and leave-one-out cross-validation were employed to construct the models. Models with the lowest root mean squared error in cross-validation were further validated externally. The goodness-of-fit of the models was evaluated by comparing the predicted values with those obtained through conventional laboratory methods. The constructed models properly estimated all constituents evaluated for sugarcane, soybean meal, and cornmeal (P ≥ 0.056). The models developed for predicting the contents of samples oven-dried at 55 °C (ADS) and 105 °C (ODS), total dry matter (DM), organic matter (OM), neutral detergent fiber (NDF), NDF corrected for ash and protein (NDFap), neutral detergent insoluble protein (NDIP), acid detergent fiber (ADF), crude protein (CP), non-fiber carbohydrates (NFC), and total digestible nutrients (TDN) in sugarcane; ODS, OM, NDF, ADF, indigestible NDF (iNDF), CP, TDN, and starch in soybean meal; and ODS and CP in cornmeal exhibited high accuracy and precision (R2 ≥ 0.50 and CCC ≥ 0.60). However, the models developed for predicting the levels of neutral detergent insoluble ash (NDIA) in sugarcane; ether extract (EE) and NDIA in soybean meal; and NDF, iNDF, NDIA, NFC, and EE in cornmeal demonstrated accuracy but lacked precision (R2 ≥ -0.04 and CCC ≥ 0.03). In conclusion, the portable NIR regression models provided accurate estimates and are therefore recommended for predicting the chemical composition of sugarcane, soybean meal, and cornmeal.
Downloads
References
Ciurczak, E. W., Igne, B., Workman, J., Jr., & Burns, D. A. (2021). Handbook of near-infrared analysis. CRC Press. DOI: https://doi.org/10.1201/b22513
Companhia Nacional de Abastecimento (2021). Boletim da safra de grãos, 3o Levantamento - Safra 2020/21. https://www.conab.gov.br/info-agro/safras/graos/boletim-da-safra-de-graos
Detmann, E., Silva, L. F. C., Rocha, G. C., Palma, M. N. N., & Rodrigues, J. P. P. (2021). Métodos para análise de alimentos. Suprema.
Ferreira, M. M. C. (2015). Quimiometria: conceitos, métodos e aplicações. Editora da Unicamp. DOI: https://doi.org/10.7476/9788526814714
Kennard, R. W., & Stone, L. A. (1969). Computer aided design of experiments. Technometrics, 11(1), 137-148. doi: 10.1080/00401706.1969.10490666 DOI: https://doi.org/10.1080/00401706.1969.10490666
Kobayashi, K., & Salam, M. U. (2000). Comparing simulated and measured values using mean squared deviation and its components. Agronomy Journal, 92(2), 345-352. doi: 10.2134/agronj2000.922345x DOI: https://doi.org/10.2134/agronj2000.922345x
Montgomery, D. C. (2009). Introdução ao controle estatístico da qualidade. Grupo Gen-LTC.
Ozaki, Y., Huck, C., Tsuchikawa, S., & Engelsen, S. B. (2021). Near-infrared spectroscopy: theory, spectral analysis, instrumentation, and applications. Springer. DOI: https://doi.org/10.1007/978-981-15-8648-4
Peternelli, L. A., Gonçalves, M. T. V., Fernandes, J. G., Brasileiro, B. P., & Teófilo, R. F. (2020). Selection of sugarcane clones via multivariate models using near-infrared (NIR) spectroscopy data. Australian Journal of Crop Science, 14(6), 889-895. doi: 10.21475/ajcs.20.14.06.p2099 DOI: https://doi.org/10.21475/ajcs.20.14.06.p2099
Pinto, A. C. J., & Millen, D. D. (2019). Nutritional recommendations and management practices adopted by feedlot cattle nutritionists: the 2016 Brazilian survey. Canadian Journal of Animal Science, 99(2), 392-407. doi: 10.1139/cjas-2018-0031 DOI: https://doi.org/10.1139/cjas-2018-0031
Porep, J. U., Kammerer, D. R., & Carle, R. (2015). On-line application of near infrared (NIR) spectroscopy in food production. Trends in Food Science & Technology, 46(2), 211-230. doi: 10.1016/j.tifs.2015.10.002 DOI: https://doi.org/10.1016/j.tifs.2015.10.002
Sarraguça, M. C., & Lopes, J. A. (2009). Quality control of pharmaceuticals with NIR: from lab to process line. Vibrational Spectroscopy, 49(2), 204-210. doi: 10.1016/j.vibspec.2008.07.013 DOI: https://doi.org/10.1016/j.vibspec.2008.07.013
Silva, B. C., Godoi, L. A., Valadares, S. C., Fº., Zanetti, D., Benedeti, P. D. B., & Detmann, E. (2019a). A suitable enzymatic method for starch quantification in different organic matrices. MethodsX, 6(2019), 2322-2328. doi: 10.1016/j.mex.2019.09.040 DOI: https://doi.org/10.1016/j.mex.2019.09.040
Silva, D. P., Pedroso, A. M., Pereira, M. C. S., Bertoldi, G. P., Watanabe, D. H. M., Melo, A. C. B., & Millen, D. D. (2019b). Survey of management practices used by brazilian dairy farmers and recommendations provided by 43 dairy cattle nutritionists. Canadian Journal of Animal Science, 99(4), 890-904. doi: 10.1139/cjas-2018-0004 DOI: https://doi.org/10.1139/cjas-2018-0004
Silvestre, A. M., & Millen, D. D. (2021). The 2019 brazilian survey on nutritional practices provided by feedlot cattle consulting nutritionists. Revista Brasileira de Zootecnia, 50(9), 1-25. doi: 10.37496/RBZ5020200189 DOI: https://doi.org/10.37496/rbz5020200189
Souza, R. C., Reis, R. B., Lopez, F. C. F., Mourthe, M. H. F., Lana, A. M. Q., Barbosa, F. A., & Sousa, B. M. (2015). Efeito da adição de teores crescentes de ureia na cana-de-açúcar em dietas de vacas em lactação sobre a produção e composição do leite e viabilidade econômica. Arquivo Brasileiro de Medicina Veterinária e Zootecnia, 67(2-3), 564-572. doi: 10.1590/1678-7799 DOI: https://doi.org/10.1590/1678-7799
Tedeschi, L. O. (2006). Assessment of the adequacy of mathematical models. Agricultural Systems, 89(1-2), 225-247. doi: 10.1016/j.agsy.2005.11.004 DOI: https://doi.org/10.1016/j.agsy.2005.11.004
Thomson, A. L., Humphries, D. J., Rymer, C., Archer, J. E., Grant, N. W., & Reynolds, C. K. (2018). Assessing the accuracy of current near infra-red reflectance spectroscopy analysis for fresh grass-clover mixture silages and development of new equations for this purpose. Animal Feed Science and Technology, 239(2018) 94-106. doi: 10.1016/j.anifeedsci.2018.03.009 DOI: https://doi.org/10.1016/j.anifeedsci.2018.03.009
Valadares, S. C., F., Lopes, S. A., Silva, B. C., & Chizzotti, M. L. L. Z. B. (2018). Tabelas brasileiras de composição de alimentos para ruminantes (CQBAL 4.0).
Valadares, S. C. F., L., Silva F. C., Gionbelli, M. P., Rotta, P. P., Marcondes, M. I., Chizzotti, M. L., & Prados, L. F. (2016). Exigências Nutricionais de Zebuínos Puros e Cruzados - BR-CORTE. Editora Federal de Viçosa. DOI: https://doi.org/10.5935/978-85-8179-111-1.2016B001
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Semina: Ciências Agrárias
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Semina: Ciências Agrárias adopts the CC-BY-NC license for its publications, the copyright being held by the author, in cases of republication we recommend that authors indicate first publication in this journal.
This license allows you to copy and redistribute the material in any medium or format, remix, transform and develop the material, as long as it is not for commercial purposes. And due credit must be given to the creator.
The opinions expressed by the authors of the articles are their sole responsibility.
The magazine reserves the right to make normative, orthographic and grammatical changes to the originals in order to maintain the cultured standard of the language and the credibility of the vehicle. However, it will respect the writing style of the authors. Changes, corrections or suggestions of a conceptual nature will be sent to the authors when necessary.
