T10SLRE: A novel ensemble learning approach for rapid and non-destructive prediction of bread loaf volume in wheat using NIR spectroscopy

Bread loaf volume is a critical indicator of wheat processing quality, but conventional bread-making tests are laborious and time-consuming. This study evaluated near-infrared spectroscopy combined with machine learning for rapid prediction of loaf volume. A dataset of 5003 wheat samples was divided...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Lei, Tian, Wenfei, Zhao, Zihui, Xiao, Yonggui, Zhang, Yong, Liu, Jindong, Velu, Govindan, Zhonghu, He, Ibba, Maria Itria
Formato: Journal Article
Lenguaje:Inglés
Publicado: Elsevier 2025
Materias:
Acceso en línea:https://hdl.handle.net/10568/179156
_version_ 1855514919077675008
author Li, Lei
Tian, Wenfei
Zhao, Zihui
Xiao, Yonggui
Zhang, Yong
Liu, Jindong
Velu, Govindan
Zhonghu, He
Ibba, Maria Itria
author_browse Ibba, Maria Itria
Li, Lei
Liu, Jindong
Tian, Wenfei
Velu, Govindan
Xiao, Yonggui
Zhang, Yong
Zhao, Zihui
Zhonghu, He
author_facet Li, Lei
Tian, Wenfei
Zhao, Zihui
Xiao, Yonggui
Zhang, Yong
Liu, Jindong
Velu, Govindan
Zhonghu, He
Ibba, Maria Itria
author_sort Li, Lei
collection Repository of Agricultural Research Outputs (CGSpace)
description Bread loaf volume is a critical indicator of wheat processing quality, but conventional bread-making tests are laborious and time-consuming. This study evaluated near-infrared spectroscopy combined with machine learning for rapid prediction of loaf volume. A dataset of 5003 wheat samples was divided into 4002 for model training and 1001 for independent testing. Conventional regression models and a convolutional neural network achieved testing set coefficient of determination (R2) of 0.70 to 0.73 with root mean square error (RMSE) of 23.29 to 25.08 mL/100 g. We propose a novel top 10 % sampling linear regression ensemble (T10SLRE) approach, which achieved a R2 of 0.74 and an RMSE of 22.92 mL/100 g, without spectral preprocessing or wavelength selections. It also classified wheat lines below the bread-making threshold of 850 mL/100 g with 97.90 % accuracy. This approach provides a practical tool that reduces cost and effort in wheat quality evaluation.
format Journal Article
id CGSpace179156
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1791562025-12-21T22:59:49Z T10SLRE: A novel ensemble learning approach for rapid and non-destructive prediction of bread loaf volume in wheat using NIR spectroscopy Li, Lei Tian, Wenfei Zhao, Zihui Xiao, Yonggui Zhang, Yong Liu, Jindong Velu, Govindan Zhonghu, He Ibba, Maria Itria soft wheat machine learning infrared spectrophotometry quality improvement Bread loaf volume is a critical indicator of wheat processing quality, but conventional bread-making tests are laborious and time-consuming. This study evaluated near-infrared spectroscopy combined with machine learning for rapid prediction of loaf volume. A dataset of 5003 wheat samples was divided into 4002 for model training and 1001 for independent testing. Conventional regression models and a convolutional neural network achieved testing set coefficient of determination (R2) of 0.70 to 0.73 with root mean square error (RMSE) of 23.29 to 25.08 mL/100 g. We propose a novel top 10 % sampling linear regression ensemble (T10SLRE) approach, which achieved a R2 of 0.74 and an RMSE of 22.92 mL/100 g, without spectral preprocessing or wavelength selections. It also classified wheat lines below the bread-making threshold of 850 mL/100 g with 97.90 % accuracy. This approach provides a practical tool that reduces cost and effort in wheat quality evaluation. 2025-12-25 2025-12-21T22:59:48Z 2025-12-21T22:59:48Z Journal Article https://hdl.handle.net/10568/179156 en Limited Access Elsevier Li, L., Tian, W., Zhao, Z., Xiao, Y., Zhang, Y., Liu, J., Govindan, V., He, Z., & Ibba, M. I. (2025). T10SLRE: A novel ensemble learning approach for rapid and non-destructive prediction of bread loaf volume in wheat using NIR spectroscopy. Food Chemistry, 496, 146818. https://doi.org/10.1016/j.foodchem.2025.146818
spellingShingle soft wheat
machine learning
infrared spectrophotometry
quality
improvement
Li, Lei
Tian, Wenfei
Zhao, Zihui
Xiao, Yonggui
Zhang, Yong
Liu, Jindong
Velu, Govindan
Zhonghu, He
Ibba, Maria Itria
T10SLRE: A novel ensemble learning approach for rapid and non-destructive prediction of bread loaf volume in wheat using NIR spectroscopy
title T10SLRE: A novel ensemble learning approach for rapid and non-destructive prediction of bread loaf volume in wheat using NIR spectroscopy
title_full T10SLRE: A novel ensemble learning approach for rapid and non-destructive prediction of bread loaf volume in wheat using NIR spectroscopy
title_fullStr T10SLRE: A novel ensemble learning approach for rapid and non-destructive prediction of bread loaf volume in wheat using NIR spectroscopy
title_full_unstemmed T10SLRE: A novel ensemble learning approach for rapid and non-destructive prediction of bread loaf volume in wheat using NIR spectroscopy
title_short T10SLRE: A novel ensemble learning approach for rapid and non-destructive prediction of bread loaf volume in wheat using NIR spectroscopy
title_sort t10slre a novel ensemble learning approach for rapid and non destructive prediction of bread loaf volume in wheat using nir spectroscopy
topic soft wheat
machine learning
infrared spectrophotometry
quality
improvement
url https://hdl.handle.net/10568/179156
work_keys_str_mv AT lilei t10slreanovelensemblelearningapproachforrapidandnondestructivepredictionofbreadloafvolumeinwheatusingnirspectroscopy
AT tianwenfei t10slreanovelensemblelearningapproachforrapidandnondestructivepredictionofbreadloafvolumeinwheatusingnirspectroscopy
AT zhaozihui t10slreanovelensemblelearningapproachforrapidandnondestructivepredictionofbreadloafvolumeinwheatusingnirspectroscopy
AT xiaoyonggui t10slreanovelensemblelearningapproachforrapidandnondestructivepredictionofbreadloafvolumeinwheatusingnirspectroscopy
AT zhangyong t10slreanovelensemblelearningapproachforrapidandnondestructivepredictionofbreadloafvolumeinwheatusingnirspectroscopy
AT liujindong t10slreanovelensemblelearningapproachforrapidandnondestructivepredictionofbreadloafvolumeinwheatusingnirspectroscopy
AT velugovindan t10slreanovelensemblelearningapproachforrapidandnondestructivepredictionofbreadloafvolumeinwheatusingnirspectroscopy
AT zhonghuhe t10slreanovelensemblelearningapproachforrapidandnondestructivepredictionofbreadloafvolumeinwheatusingnirspectroscopy
AT ibbamariaitria t10slreanovelensemblelearningapproachforrapidandnondestructivepredictionofbreadloafvolumeinwheatusingnirspectroscopy