Machine learning-enhanced near-infrared spectroscopy for high-throughput phenotyping of sweetpotato sugars across raw and cooked states

Sweetpotato is a major root crop with high yield and nutritional benefits. However, existing methods for evaluating sugars level are inefficient, limiting the breeding and processing of high-quality varieties. This study utilized near-infrared spectroscopy (NIRS) coupled with machine learning algori...

Full description

Saved in:
Bibliographic Details
Main Authors: Chaochen Tang, Xueying Mo, Zhimin Ma, Zhangying Wang
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Journal of Agriculture and Food Research
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666154325003059
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725567152160768
author Chaochen Tang
Xueying Mo
Zhimin Ma
Zhangying Wang
author_facet Chaochen Tang
Xueying Mo
Zhimin Ma
Zhangying Wang
author_sort Chaochen Tang
collection DOAJ
description Sweetpotato is a major root crop with high yield and nutritional benefits. However, existing methods for evaluating sugars level are inefficient, limiting the breeding and processing of high-quality varieties. This study utilized near-infrared spectroscopy (NIRS) coupled with machine learning algorithms to develop a high-throughput assay for fructose, glucose, sucrose, and maltose in sweetpotatoes across their raw, steamed, and baked states. Leveraging representative samples, characteristic spectral variables, and advanced learning algorithms, twelve optimal models were established for the four sugar indicators under three processing states. These models exhibited outstanding performance in calibration (R2C: 0.941–0.984), cross-validation (R2CV: 0.926–0.976), external validation (R2V: 0.898–0.971), and the ratio of prediction to deviation (RPD: 5.83–10.3), confirming their robust predictive capacity. The findings suggest that these machine learning-enhanced NIRS models enable rapid, high-throughput analysis of sweetpotato sugars, significantly benefiting both breeding programs and food processing applications.
format Article
id doaj-art-bc2ff844dffa41bab803f4ff02a02fc6
institution DOAJ
issn 2666-1543
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Journal of Agriculture and Food Research
spelling doaj-art-bc2ff844dffa41bab803f4ff02a02fc62025-08-20T03:10:25ZengElsevierJournal of Agriculture and Food Research2666-15432025-06-012110193410.1016/j.jafr.2025.101934Machine learning-enhanced near-infrared spectroscopy for high-throughput phenotyping of sweetpotato sugars across raw and cooked statesChaochen Tang0Xueying Mo1Zhimin Ma2Zhangying Wang3Crops Research Institute, Guangdong Academy of Agricultural Sciences & Key Laboratory of Crop Genetic Improvement of Guangdong Province, Guangzhou, 510640, ChinaCrops Research Institute, Guangdong Academy of Agricultural Sciences & Key Laboratory of Crop Genetic Improvement of Guangdong Province, Guangzhou, 510640, ChinaInstitution of Cereal and Oil Crops, Hebei Academy of Agriculture and Forestry Sciences, Shijiazhuang, 050035, China; Institute of Cereal and Oil Crops, HAAFS/Hebei Key Laboratory of Crop Genetics and Breeding, Shijiazhuang, China; Corresponding author. Institution of Cereal and Oil Crops, Hebei Academy of Agriculture and Forestry Sciences, Shijiazhuang, 050035, China.Crops Research Institute, Guangdong Academy of Agricultural Sciences & Key Laboratory of Crop Genetic Improvement of Guangdong Province, Guangzhou, 510640, China; Corresponding author.Sweetpotato is a major root crop with high yield and nutritional benefits. However, existing methods for evaluating sugars level are inefficient, limiting the breeding and processing of high-quality varieties. This study utilized near-infrared spectroscopy (NIRS) coupled with machine learning algorithms to develop a high-throughput assay for fructose, glucose, sucrose, and maltose in sweetpotatoes across their raw, steamed, and baked states. Leveraging representative samples, characteristic spectral variables, and advanced learning algorithms, twelve optimal models were established for the four sugar indicators under three processing states. These models exhibited outstanding performance in calibration (R2C: 0.941–0.984), cross-validation (R2CV: 0.926–0.976), external validation (R2V: 0.898–0.971), and the ratio of prediction to deviation (RPD: 5.83–10.3), confirming their robust predictive capacity. The findings suggest that these machine learning-enhanced NIRS models enable rapid, high-throughput analysis of sweetpotato sugars, significantly benefiting both breeding programs and food processing applications.http://www.sciencedirect.com/science/article/pii/S2666154325003059Sugar contentChemometric algorithmsModeling methodCrop breedingFood processing
spellingShingle Chaochen Tang
Xueying Mo
Zhimin Ma
Zhangying Wang
Machine learning-enhanced near-infrared spectroscopy for high-throughput phenotyping of sweetpotato sugars across raw and cooked states
Journal of Agriculture and Food Research
Sugar content
Chemometric algorithms
Modeling method
Crop breeding
Food processing
title Machine learning-enhanced near-infrared spectroscopy for high-throughput phenotyping of sweetpotato sugars across raw and cooked states
title_full Machine learning-enhanced near-infrared spectroscopy for high-throughput phenotyping of sweetpotato sugars across raw and cooked states
title_fullStr Machine learning-enhanced near-infrared spectroscopy for high-throughput phenotyping of sweetpotato sugars across raw and cooked states
title_full_unstemmed Machine learning-enhanced near-infrared spectroscopy for high-throughput phenotyping of sweetpotato sugars across raw and cooked states
title_short Machine learning-enhanced near-infrared spectroscopy for high-throughput phenotyping of sweetpotato sugars across raw and cooked states
title_sort machine learning enhanced near infrared spectroscopy for high throughput phenotyping of sweetpotato sugars across raw and cooked states
topic Sugar content
Chemometric algorithms
Modeling method
Crop breeding
Food processing
url http://www.sciencedirect.com/science/article/pii/S2666154325003059
work_keys_str_mv AT chaochentang machinelearningenhancednearinfraredspectroscopyforhighthroughputphenotypingofsweetpotatosugarsacrossrawandcookedstates
AT xueyingmo machinelearningenhancednearinfraredspectroscopyforhighthroughputphenotypingofsweetpotatosugarsacrossrawandcookedstates
AT zhiminma machinelearningenhancednearinfraredspectroscopyforhighthroughputphenotypingofsweetpotatosugarsacrossrawandcookedstates
AT zhangyingwang machinelearningenhancednearinfraredspectroscopyforhighthroughputphenotypingofsweetpotatosugarsacrossrawandcookedstates