Predicting postharvest weight loss and texture changes in table grapes using fruit color and machine learning

Accurately predicting postharvest quality is crucial for optimizing storage and reducing losses in table grapes. This study explores the potential of fruit color parameters as non-invasive indicators of postharvest weight loss and textural changes. Using convolutional neural networks (CNNs), we deve...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoyan Cheng, Yao Zhou, Zhengyang Huo, Ruiying Li, Shiqian Xu, Hao Qi, Jianyuan Zhu, Fei Wang, Yang Bi
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Future Foods
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666833525001613
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850111625062776832
author Xiaoyan Cheng
Yao Zhou
Zhengyang Huo
Ruiying Li
Shiqian Xu
Hao Qi
Jianyuan Zhu
Fei Wang
Yang Bi
author_facet Xiaoyan Cheng
Yao Zhou
Zhengyang Huo
Ruiying Li
Shiqian Xu
Hao Qi
Jianyuan Zhu
Fei Wang
Yang Bi
author_sort Xiaoyan Cheng
collection DOAJ
description Accurately predicting postharvest quality is crucial for optimizing storage and reducing losses in table grapes. This study explores the potential of fruit color parameters as non-invasive indicators of postharvest weight loss and textural changes. Using convolutional neural networks (CNNs), we developed predictive models based on colorimetric data, achieving high accuracy (R² > 0.80 for weight loss and R² > 0.97 for texture). Additionally, the effects of storage temperature on grape quality were examined, revealing that colder storage at 3°C significantly reduces weight loss and maintains texture better than storage at 10°C. Among tested cultivars, ‘Shine Muscat’ exhibited lower weight loss and superior textural stability compared to ‘Flame Seedless’. These findings highlight the potential of integrating color-based assessments and machine learning models into postharvest monitoring, offering a practical approach for improving quality control and storage management in the grape industry.
format Article
id doaj-art-9eb50a0fced7461b9fdf2be94ac172a5
institution OA Journals
issn 2666-8335
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Future Foods
spelling doaj-art-9eb50a0fced7461b9fdf2be94ac172a52025-08-20T02:37:35ZengElsevierFuture Foods2666-83352025-12-011210070310.1016/j.fufo.2025.100703Predicting postharvest weight loss and texture changes in table grapes using fruit color and machine learningXiaoyan Cheng0Yao Zhou1Zhengyang Huo2Ruiying Li3Shiqian Xu4Hao Qi5Jianyuan Zhu6Fei Wang7Yang Bi8College of Science, Gansu Agricultural University / State Key Laboratory of Aridland Crop Science, Co-Built by the Provincial and Ministerial Authorities, Lanzhou 730070, China; Corresponding authors.College of Science, Gansu Agricultural University / State Key Laboratory of Aridland Crop Science, Co-Built by the Provincial and Ministerial Authorities, Lanzhou 730070, ChinaCollege of Science, Gansu Agricultural University / State Key Laboratory of Aridland Crop Science, Co-Built by the Provincial and Ministerial Authorities, Lanzhou 730070, ChinaCollege of Science, Gansu Agricultural University / State Key Laboratory of Aridland Crop Science, Co-Built by the Provincial and Ministerial Authorities, Lanzhou 730070, ChinaCollege of Information Science and Technology, Gansu Agricultural University, Lanzhou 730070, ChinaCollege of Information Science and Technology, Gansu Agricultural University, Lanzhou 730070, ChinaCollege of Information Science and Technology, Gansu Agricultural University, Lanzhou 730070, ChinaCollege of Science, Gansu Agricultural University / State Key Laboratory of Aridland Crop Science, Co-Built by the Provincial and Ministerial Authorities, Lanzhou 730070, ChinaCollege of Food Science and Engineering, Gansu Agricultural University, Lanzhou 730070, China; Corresponding authors.Accurately predicting postharvest quality is crucial for optimizing storage and reducing losses in table grapes. This study explores the potential of fruit color parameters as non-invasive indicators of postharvest weight loss and textural changes. Using convolutional neural networks (CNNs), we developed predictive models based on colorimetric data, achieving high accuracy (R² > 0.80 for weight loss and R² > 0.97 for texture). Additionally, the effects of storage temperature on grape quality were examined, revealing that colder storage at 3°C significantly reduces weight loss and maintains texture better than storage at 10°C. Among tested cultivars, ‘Shine Muscat’ exhibited lower weight loss and superior textural stability compared to ‘Flame Seedless’. These findings highlight the potential of integrating color-based assessments and machine learning models into postharvest monitoring, offering a practical approach for improving quality control and storage management in the grape industry.http://www.sciencedirect.com/science/article/pii/S2666833525001613Postharvest deteriorationNon-destructive evaluationPredictive analyticsStorage stabilityMachine learning applications
spellingShingle Xiaoyan Cheng
Yao Zhou
Zhengyang Huo
Ruiying Li
Shiqian Xu
Hao Qi
Jianyuan Zhu
Fei Wang
Yang Bi
Predicting postharvest weight loss and texture changes in table grapes using fruit color and machine learning
Future Foods
Postharvest deterioration
Non-destructive evaluation
Predictive analytics
Storage stability
Machine learning applications
title Predicting postharvest weight loss and texture changes in table grapes using fruit color and machine learning
title_full Predicting postharvest weight loss and texture changes in table grapes using fruit color and machine learning
title_fullStr Predicting postharvest weight loss and texture changes in table grapes using fruit color and machine learning
title_full_unstemmed Predicting postharvest weight loss and texture changes in table grapes using fruit color and machine learning
title_short Predicting postharvest weight loss and texture changes in table grapes using fruit color and machine learning
title_sort predicting postharvest weight loss and texture changes in table grapes using fruit color and machine learning
topic Postharvest deterioration
Non-destructive evaluation
Predictive analytics
Storage stability
Machine learning applications
url http://www.sciencedirect.com/science/article/pii/S2666833525001613
work_keys_str_mv AT xiaoyancheng predictingpostharvestweightlossandtexturechangesintablegrapesusingfruitcolorandmachinelearning
AT yaozhou predictingpostharvestweightlossandtexturechangesintablegrapesusingfruitcolorandmachinelearning
AT zhengyanghuo predictingpostharvestweightlossandtexturechangesintablegrapesusingfruitcolorandmachinelearning
AT ruiyingli predictingpostharvestweightlossandtexturechangesintablegrapesusingfruitcolorandmachinelearning
AT shiqianxu predictingpostharvestweightlossandtexturechangesintablegrapesusingfruitcolorandmachinelearning
AT haoqi predictingpostharvestweightlossandtexturechangesintablegrapesusingfruitcolorandmachinelearning
AT jianyuanzhu predictingpostharvestweightlossandtexturechangesintablegrapesusingfruitcolorandmachinelearning
AT feiwang predictingpostharvestweightlossandtexturechangesintablegrapesusingfruitcolorandmachinelearning
AT yangbi predictingpostharvestweightlossandtexturechangesintablegrapesusingfruitcolorandmachinelearning