Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes

It has been established that near infrared (NIR) spectroscopy has the potential of estimating sensory traits given the direct spectral responses that these properties have in the near infrared (NIR) region. In sweetpotato, sensory traits are key for improving acceptability of the crop for food secur...

Descripción completa

Detalles Bibliográficos
Autores principales: Nantongo, J.S., Serunkuma, E., Burgos, C., Nakitto, M., Davrieux, F., Ssali, R.T.
Formato: Journal Article
Lenguaje:Inglés
Publicado: Elsevier 2024
Materias:
Acceso en línea:https://hdl.handle.net/10568/141737
_version_ 1855528003823468544
author Nantongo, J.S.
Serunkuma, E.
Burgos, C.
Nakitto, M.
Davrieux, F.
Ssali, R.T.
author_browse Burgos, C.
Davrieux, F.
Nakitto, M.
Nantongo, J.S.
Serunkuma, E.
Ssali, R.T.
author_facet Nantongo, J.S.
Serunkuma, E.
Burgos, C.
Nakitto, M.
Davrieux, F.
Ssali, R.T.
author_sort Nantongo, J.S.
collection Repository of Agricultural Research Outputs (CGSpace)
description It has been established that near infrared (NIR) spectroscopy has the potential of estimating sensory traits given the direct spectral responses that these properties have in the near infrared (NIR) region. In sweetpotato, sensory traits are key for improving acceptability of the crop for food security and nutrition. Studies have statistically modelled the levels of near infrared (NIR) spectroscopy sensory characteristics using Partial Least Squares (PLS) regression methods. To improve prediction accuracy, there are many advanced modelling techniques, particularly, which could be helpful when handling fresh (wet and un-processed) samples or where modelling may involve nonlinear dependence relationships. Performance of different quantitative prediction models for sensory traits developed using different machine learning methods were compared. Overall, results show that linear methods; linear support vector machine (L-SVM), principal component regression (PCR) and PLS performed better than other statistical methods. For all the 27 sensory traits, calibration models using L-SVM and PCR has slightly higher overall R2 (x = 0.33) compared to PLS (x̄ ̅= 0.32) and radial based SVM (NL-SVM; x ̅= 0.30). The levels of orange color intensity were the best predicted by all the calibration models (R2 = 0.87 – 0.89). The elastic net linear regression (ENR) and tree-based methods; extreme gradient boost (XGBoost) and random forest (RF) performed worse than would be expected but could possibly be improved with increased sample size. Lower average R2 were observed for calibration models of ENR (x ̅ = 0.26), XGBOOST (x ̅ = 0.26) and RF (x ̅ = 0.22). The overall RMSE in calibration, models was lower in PCR models (X = 0.82) compared to L-SVM (x= 0.86) and PLS (x= 0.90). ENR, XGboost and RF also had higher RMSE (0.90 -0.92). Effective wavelengths selection using the interval partial least-squares regression (iPLS), improved the robustness of the models but did not perform as good as the PLS. SNV pre-treatment was useful in improving model robustness.
format Journal Article
id CGSpace141737
institution CGIAR Consortium
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1417372025-10-26T12:52:53Z Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes Nantongo, J.S. Serunkuma, E. Burgos, C. Nakitto, M. Davrieux, F. Ssali, R.T. phenotyping breeding consumer behaviour food security sweet potatoes machine learning crop improvement It has been established that near infrared (NIR) spectroscopy has the potential of estimating sensory traits given the direct spectral responses that these properties have in the near infrared (NIR) region. In sweetpotato, sensory traits are key for improving acceptability of the crop for food security and nutrition. Studies have statistically modelled the levels of near infrared (NIR) spectroscopy sensory characteristics using Partial Least Squares (PLS) regression methods. To improve prediction accuracy, there are many advanced modelling techniques, particularly, which could be helpful when handling fresh (wet and un-processed) samples or where modelling may involve nonlinear dependence relationships. Performance of different quantitative prediction models for sensory traits developed using different machine learning methods were compared. Overall, results show that linear methods; linear support vector machine (L-SVM), principal component regression (PCR) and PLS performed better than other statistical methods. For all the 27 sensory traits, calibration models using L-SVM and PCR has slightly higher overall R2 (x = 0.33) compared to PLS (x̄ ̅= 0.32) and radial based SVM (NL-SVM; x ̅= 0.30). The levels of orange color intensity were the best predicted by all the calibration models (R2 = 0.87 – 0.89). The elastic net linear regression (ENR) and tree-based methods; extreme gradient boost (XGBoost) and random forest (RF) performed worse than would be expected but could possibly be improved with increased sample size. Lower average R2 were observed for calibration models of ENR (x ̅ = 0.26), XGBOOST (x ̅ = 0.26) and RF (x ̅ = 0.22). The overall RMSE in calibration, models was lower in PCR models (X = 0.82) compared to L-SVM (x= 0.86) and PLS (x= 0.90). ENR, XGboost and RF also had higher RMSE (0.90 -0.92). Effective wavelengths selection using the interval partial least-squares regression (iPLS), improved the robustness of the models but did not perform as good as the PLS. SNV pre-treatment was useful in improving model robustness. 2024-10 2024-05-06T19:51:35Z 2024-05-06T19:51:35Z Journal Article https://hdl.handle.net/10568/141737 en Limited Access Elsevier Nantongo, J.; Serunkuma, E.; Burgos, C.; Nakitto, M.; Davrieux, F.; Ssali, R. 2024. Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. ISSN 1873-3557. https://doi.org/10.1016/j.saa.2024.124406
spellingShingle phenotyping
breeding
consumer behaviour
food security
sweet potatoes
machine learning
crop improvement
Nantongo, J.S.
Serunkuma, E.
Burgos, C.
Nakitto, M.
Davrieux, F.
Ssali, R.T.
Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes
title Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes
title_full Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes
title_fullStr Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes
title_full_unstemmed Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes
title_short Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes
title_sort machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes
topic phenotyping
breeding
consumer behaviour
food security
sweet potatoes
machine learning
crop improvement
url https://hdl.handle.net/10568/141737
work_keys_str_mv AT nantongojs machinelearningmethodsinnearinfraredspectroscopyforpredictingsensorytraitsinsweetpotatoes
AT serunkumae machinelearningmethodsinnearinfraredspectroscopyforpredictingsensorytraitsinsweetpotatoes
AT burgosc machinelearningmethodsinnearinfraredspectroscopyforpredictingsensorytraitsinsweetpotatoes
AT nakittom machinelearningmethodsinnearinfraredspectroscopyforpredictingsensorytraitsinsweetpotatoes
AT davrieuxf machinelearningmethodsinnearinfraredspectroscopyforpredictingsensorytraitsinsweetpotatoes
AT ssalirt machinelearningmethodsinnearinfraredspectroscopyforpredictingsensorytraitsinsweetpotatoes