Optimization of machine learning models for predicting glutinous rice quality stored under various conditions

The preservation of freshly harvested glutinous rice (GR) is essential for maintaining its nutritional and economic value. This study examines the impact of storage temperature and duration on key quality attributes, including moisture content (MC), germination growth rate (GGR), water absorption ca...

Full description

Bibliographic Details
Main Authors: Dasore, Abhishek, Hashim, Norhashila, Shamsudin, Rosnah, Che Man, Hasfalina, Mohd Ali, Maimunah, Ageh, Opeyemi Micheal
Format: Article
Language:English
Published: Elsevier Ltd 2025
Online Access:http://psasir.upm.edu.my/id/eprint/118909/
http://psasir.upm.edu.my/id/eprint/118909/1/118909.pdf
_version_ 1848867820751814656
author Dasore, Abhishek
Hashim, Norhashila
Shamsudin, Rosnah
Che Man, Hasfalina
Mohd Ali, Maimunah
Ageh, Opeyemi Micheal
author_facet Dasore, Abhishek
Hashim, Norhashila
Shamsudin, Rosnah
Che Man, Hasfalina
Mohd Ali, Maimunah
Ageh, Opeyemi Micheal
author_sort Dasore, Abhishek
building UPM Institutional Repository
collection Online Access
description The preservation of freshly harvested glutinous rice (GR) is essential for maintaining its nutritional and economic value. This study examines the impact of storage temperature and duration on key quality attributes, including moisture content (MC), germination growth rate (GGR), water absorption capacity (WAC) and head rice yield (HRY). GR samples were dried at 60 °C and stored under freeze (−10 °C), cold (6 °C), and ambient (∼26 °C) conditions for six months, with biweekly data collection. Statistical analysis using ANOVA revealed that storage duration significantly affected MC, GGR and HRY, while storage temperature primarily influenced MC. The Random Forest (RF) machine learning model demonstrated high predictive performance (R2 > 0.9) with low error values for predicting quality attributes. Hyperparameter tuning (HPT) through grid search optimization further improved the model's performance, as validated by parity plots showing strong alignment (regression slopes >0.8) between predicted and experimental results. SHapley Additive exPlanations (SHAP) and contour plots provided detailed insights into the influence of storage parameters on quality attributes. This comprehensive approach offers actionable guidance for optimizing GR storage conditions, contributing to food security, and supporting to the achievement of the United Nations Sustainable Development Goals (SDGs).
first_indexed 2025-11-15T14:42:35Z
format Article
id upm-118909
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T14:42:35Z
publishDate 2025
publisher Elsevier Ltd
recordtype eprints
repository_type Digital Repository
spelling upm-1189092025-07-29T06:52:58Z http://psasir.upm.edu.my/id/eprint/118909/ Optimization of machine learning models for predicting glutinous rice quality stored under various conditions Dasore, Abhishek Hashim, Norhashila Shamsudin, Rosnah Che Man, Hasfalina Mohd Ali, Maimunah Ageh, Opeyemi Micheal The preservation of freshly harvested glutinous rice (GR) is essential for maintaining its nutritional and economic value. This study examines the impact of storage temperature and duration on key quality attributes, including moisture content (MC), germination growth rate (GGR), water absorption capacity (WAC) and head rice yield (HRY). GR samples were dried at 60 °C and stored under freeze (−10 °C), cold (6 °C), and ambient (∼26 °C) conditions for six months, with biweekly data collection. Statistical analysis using ANOVA revealed that storage duration significantly affected MC, GGR and HRY, while storage temperature primarily influenced MC. The Random Forest (RF) machine learning model demonstrated high predictive performance (R2 > 0.9) with low error values for predicting quality attributes. Hyperparameter tuning (HPT) through grid search optimization further improved the model's performance, as validated by parity plots showing strong alignment (regression slopes >0.8) between predicted and experimental results. SHapley Additive exPlanations (SHAP) and contour plots provided detailed insights into the influence of storage parameters on quality attributes. This comprehensive approach offers actionable guidance for optimizing GR storage conditions, contributing to food security, and supporting to the achievement of the United Nations Sustainable Development Goals (SDGs). Elsevier Ltd 2025-05 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/118909/1/118909.pdf Dasore, Abhishek and Hashim, Norhashila and Shamsudin, Rosnah and Che Man, Hasfalina and Mohd Ali, Maimunah and Ageh, Opeyemi Micheal (2025) Optimization of machine learning models for predicting glutinous rice quality stored under various conditions. Journal of Stored Products Research, 111. art. no. 102550. pp. 1-11. ISSN 0022-474X; eISSN: 0022-474X https://linkinghub.elsevier.com/retrieve/pii/S0022474X25000098 10.1016/j.jspr.2025.102550
spellingShingle Dasore, Abhishek
Hashim, Norhashila
Shamsudin, Rosnah
Che Man, Hasfalina
Mohd Ali, Maimunah
Ageh, Opeyemi Micheal
Optimization of machine learning models for predicting glutinous rice quality stored under various conditions
title Optimization of machine learning models for predicting glutinous rice quality stored under various conditions
title_full Optimization of machine learning models for predicting glutinous rice quality stored under various conditions
title_fullStr Optimization of machine learning models for predicting glutinous rice quality stored under various conditions
title_full_unstemmed Optimization of machine learning models for predicting glutinous rice quality stored under various conditions
title_short Optimization of machine learning models for predicting glutinous rice quality stored under various conditions
title_sort optimization of machine learning models for predicting glutinous rice quality stored under various conditions
url http://psasir.upm.edu.my/id/eprint/118909/
http://psasir.upm.edu.my/id/eprint/118909/
http://psasir.upm.edu.my/id/eprint/118909/
http://psasir.upm.edu.my/id/eprint/118909/1/118909.pdf