Predicting starch content in cassava fresh roots using near-infrared spectroscopy

Abstract

The cassava starch market is promising in sub-Saharan Africa and increasing rapidly due to the numerous uses of starch in food industries. More accurate, high-throughput, and cost-effective phenotyping approaches could hasten the development of cassava varieties with high starch content to meet the growing market demand. This study investigated the effectiveness of a pocket-sized SCiO™ molecular sensor (SCiO) (740−1070 nm) to predict starch content in freshly ground cassava roots. A set of 344 unique genotypes from 11 field trials were evaluated. The predictive ability of individual trials was compared using partial least squares regression (PLSR). The 11 trials were aggregated to capture more variability, and the performance of the combined data was evaluated using two additional algorithms, random forest (RF) and support vector machine (SVM). The effect of pretreatment on model performance was examined. The predictive ability of SCiO was compared to that of two commercially available near-infrared (NIR) spectrometers, the portable ASD QualitySpec® Trek (QST) (350−2500 nm) and the benchtop FOSS XDS Rapid Content™ Analyzer (BT) (400−2490 nm). The heritability of NIR spectra was investigated, and important spectral wavelengths were identified. Model performance varied across trials and was related to the amount of genetic diversity captured in the trial. Regardless of the chemometric approach, a satisfactory and consistent estimate of starch content was obtained across pretreatments with the SCiO (correlation between the predicted and the observed test set, (R2P): 0.84−0.90; ratio of performance deviation (RPD): 2.49−3.11, ratio of performance to interquartile distance (RPIQ): 3.24−4.08, concordance correlation coefficient (CCC): 0.91−0.94). While PLSR and SVM showed comparable prediction abilities, the RF model yielded the lowest performance. The heritability of the 331 NIRS spectra varied across trials and spectral regions but was highest (H2 > 0.5) between 871−1070 nm in most trials. Important wavelengths corresponding to absorption bands associated with starch and water were identified from 815 to 980 nm. Despite its limited spectral range, SCiO provided satisfactory prediction, as did BT, whereas QST showed less optimal calibration models. The SCiO spectrometer may be a cost-effective solution for phenotyping the starch content of fresh roots in resource-limited cassava breeding programs.

Rapid analysis of hydrogen cyanide in fresh cassava roots using NIRSand machine learning algorithms: Meeting end user demand for low cyanogenic cassava

“…Despite the overall superior performance of PLS‐DA to LR and SVM using the full spectrum, the two models—LR (75.72%) and SVM (78.64%)—outperformed PLS‐DA (67.81%) when SNV.d1 spectral pretreatment was applied, yet PLS‐DA achieved 99.38% accuracy with raw spectra (Table 3). Although spectra pretreatments correct for systemic noise and could highlight differences between samples (Freitas et al., 2020; Sampaio et al., 2020; Sohn et al., 2022), care should be taken to identify the best pretreatment for a given spectral dataset, else the pretreatments could disrupt the pattern in the spectra (Nkouaya Mbanjo et al., 2022).…”

“…The use of near‐infrared spectroscopy (NIRS) to predict essential cassava root quality traits is gaining prominence. Thus, NIRS has been deployed to predict cassava root dry matter content and total carotenoids (Abincha et al., 2020, 2021; Belalcazar et al., 2016; Sánchez et al., 2014), starch (Nkouaya Mbanjo et al., 2022), cassava boiled root cooking time (Namakula et al., 2023), and amylose (Nuwamanya, et al., 2022). This progress is hinged on the fact that NIRS offers fast, simultaneous, and accurate trait analyses with minimal sample preparation as compared to traditional laboratory wet chemistry methods (Alamu et al., 2020; Gaby et al., 2021).…”

Genetic Variation and Heritability for Hydrogen Cyanide in Fresh Cassava Roots

“…Near infrared spectroscopy (NIRS) is one such technologies that has been adopted by major cassava breeding programmes in Uganda and Nigeria for cassava root quality phenotyping (59)(60)(61) and has recently been shown to separate low and high HCN clones with high accuracy (62). Thus, cassava breeders targeting low HCN cassava varieties may find the concept of phenomic selection as recently described by (63) more appealing compared to genome based tools like marker assisted selection (MAS) given the phenotypic plasticity of the trait.…”

Use of Low Cost Near-Infrared Spectroscopy, to Predict Pasting Properties of High Quality Cassava Flour

“…For the quick estimate of important cassava traits, near infrared spectroscopy (NIRS) has shown promise (Ikegu et al,2017;Rittiron et al,2020;Abincha et al, 2021;Hershberger et al, 2022;Nkouaya Mbanjo et al, 2022). In addition, pasting properties of rice were predicted with su cient accuracy by NIRS based on our spectra (Bao et al, 2007).…”