Use of low cost near‑infrared spectroscopy, to predict pasting properties of high quality cassava flour

Determination of pasting properties of high quality cassava flour using rapid visco analyzer is expensive and time consuming. The use of mobile near infrared spectroscopy (SCiO™) is an alternative high throughput phenotyping technology for predicting pasting properties of high quality cassava flour...

Descripción completa

Detalles Bibliográficos
Autores principales: Abubakar, M., Wasswa, P., Masumba, E., Ongom, P., Mkamilo, G., Kanju, E., Abincha, W., Edema, R., Sichalwe, K., Tukamuhabwa, P., Kayondo, S., Rabbi, I., Kulembeka, H.
Formato: Journal Article
Lenguaje:Inglés
Publicado: Springer 2024
Materias:
Acceso en línea:https://hdl.handle.net/10568/155266
_version_ 1855537881099010048
author Abubakar, M.
Wasswa, P.
Masumba, E.
Ongom, P.
Mkamilo, G.
Kanju, E.
Abincha, W.
Edema, R.
Sichalwe, K.
Tukamuhabwa, P.
Kayondo, S.
Rabbi, I.
Kulembeka, H.
author_browse Abincha, W.
Abubakar, M.
Edema, R.
Kanju, E.
Kayondo, S.
Kulembeka, H.
Masumba, E.
Mkamilo, G.
Ongom, P.
Rabbi, I.
Sichalwe, K.
Tukamuhabwa, P.
Wasswa, P.
author_facet Abubakar, M.
Wasswa, P.
Masumba, E.
Ongom, P.
Mkamilo, G.
Kanju, E.
Abincha, W.
Edema, R.
Sichalwe, K.
Tukamuhabwa, P.
Kayondo, S.
Rabbi, I.
Kulembeka, H.
author_sort Abubakar, M.
collection Repository of Agricultural Research Outputs (CGSpace)
description Determination of pasting properties of high quality cassava flour using rapid visco analyzer is expensive and time consuming. The use of mobile near infrared spectroscopy (SCiO™) is an alternative high throughput phenotyping technology for predicting pasting properties of high quality cassava flour traits. However, model development and validation are necessary to verify that reasonable expectations are established for the accuracy of a prediction model. In the context of an ongoing breeding effort, we investigated the use of an inexpensive, portable spectrometer that only records a portion (740–1070 nm) of the whole NIR spectrum to predict cassava pasting properties. Three machine-learning models, namely glmnet, lm, and gbm, implemented in the Caret package in R statistical program, were solely evaluated. Based on calibration statistics (R2, RMSE and MAE), we found that model calibrations using glmnet provided the best model for breakdown viscosity, peak viscosity and pasting temperature. The glmnet model using the first derivative, peak viscosity had calibration and validation accuracy of R2 = 0.56 and R2 = 0.51 respectively while breakdown had calibration and validation accuracy of R2 = 0.66 and R2 = 0.66 respectively. We also found out that stacking of pre-treatments with Moving Average, Savitzky Golay, First Derivative, Second derivative and Standard Normal variate using glmnet model resulted in calibration and validation accuracy of R2 = 0.65 and R2 = 0.64 respectively for pasting temperature. The developed calibration model predicted the pasting properties of HQCF with sufficient accuracy for screening purposes. Therefore, SCiO™ can be reliably deployed in screening early-generation breeding materials for pasting properties.
format Journal Article
id CGSpace155266
institution CGIAR Consortium
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Springer
publisherStr Springer
record_format dspace
spelling CGSpace1552662025-12-08T10:11:39Z Use of low cost near‑infrared spectroscopy, to predict pasting properties of high quality cassava flour Abubakar, M. Wasswa, P. Masumba, E. Ongom, P. Mkamilo, G. Kanju, E. Abincha, W. Edema, R. Sichalwe, K. Tukamuhabwa, P. Kayondo, S. Rabbi, I. Kulembeka, H. temperature viscosity forecasting phenotypes cassava calibration tanzania Determination of pasting properties of high quality cassava flour using rapid visco analyzer is expensive and time consuming. The use of mobile near infrared spectroscopy (SCiO™) is an alternative high throughput phenotyping technology for predicting pasting properties of high quality cassava flour traits. However, model development and validation are necessary to verify that reasonable expectations are established for the accuracy of a prediction model. In the context of an ongoing breeding effort, we investigated the use of an inexpensive, portable spectrometer that only records a portion (740–1070 nm) of the whole NIR spectrum to predict cassava pasting properties. Three machine-learning models, namely glmnet, lm, and gbm, implemented in the Caret package in R statistical program, were solely evaluated. Based on calibration statistics (R2, RMSE and MAE), we found that model calibrations using glmnet provided the best model for breakdown viscosity, peak viscosity and pasting temperature. The glmnet model using the first derivative, peak viscosity had calibration and validation accuracy of R2 = 0.56 and R2 = 0.51 respectively while breakdown had calibration and validation accuracy of R2 = 0.66 and R2 = 0.66 respectively. We also found out that stacking of pre-treatments with Moving Average, Savitzky Golay, First Derivative, Second derivative and Standard Normal variate using glmnet model resulted in calibration and validation accuracy of R2 = 0.65 and R2 = 0.64 respectively for pasting temperature. The developed calibration model predicted the pasting properties of HQCF with sufficient accuracy for screening purposes. Therefore, SCiO™ can be reliably deployed in screening early-generation breeding materials for pasting properties. 2024 2024-10-09T09:30:45Z 2024-10-09T09:30:45Z Journal Article https://hdl.handle.net/10568/155266 en Open Access application/pdf Springer Abubakar, M., Wasswa, P., Masumba, E., Ongom, P., Mkamilo, G., Kanju, E., ... & Kulembeka, H. (2024). Use of low cost near-infrared spectroscopy, to predict pasting properties of high quality cassava flour. Scientific Reports, 14(1): 17130, 1-8.
spellingShingle temperature
viscosity
forecasting
phenotypes
cassava
calibration
tanzania
Abubakar, M.
Wasswa, P.
Masumba, E.
Ongom, P.
Mkamilo, G.
Kanju, E.
Abincha, W.
Edema, R.
Sichalwe, K.
Tukamuhabwa, P.
Kayondo, S.
Rabbi, I.
Kulembeka, H.
Use of low cost near‑infrared spectroscopy, to predict pasting properties of high quality cassava flour
title Use of low cost near‑infrared spectroscopy, to predict pasting properties of high quality cassava flour
title_full Use of low cost near‑infrared spectroscopy, to predict pasting properties of high quality cassava flour
title_fullStr Use of low cost near‑infrared spectroscopy, to predict pasting properties of high quality cassava flour
title_full_unstemmed Use of low cost near‑infrared spectroscopy, to predict pasting properties of high quality cassava flour
title_short Use of low cost near‑infrared spectroscopy, to predict pasting properties of high quality cassava flour
title_sort use of low cost near infrared spectroscopy to predict pasting properties of high quality cassava flour
topic temperature
viscosity
forecasting
phenotypes
cassava
calibration
tanzania
url https://hdl.handle.net/10568/155266
work_keys_str_mv AT abubakarm useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT wasswap useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT masumbae useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT ongomp useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT mkamilog useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT kanjue useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT abinchaw useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT edemar useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT sichalwek useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT tukamuhabwap useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT kayondos useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT rabbii useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour
AT kulembekah useoflowcostnearinfraredspectroscopytopredictpastingpropertiesofhighqualitycassavaflour