From root to result: Portable NIRS-based non-destructive prediction of cassava quality traits
PLOS One · 2025
DOI: 10.1371/journal.pone.0337761 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Paulo Henrique Ramos Guimarães und 4 weiteren Autor:innen. Beteiligte Einrichtung: Embrapa Mandioca e Fruticultura, Cruz das Almas, Brazil. Hauptthemen laut MEDLINE: Manihot, Plant Roots. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 109 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Conselho Nacional de Desenvolvimento CientÃfico e Tecnológico, Embrapa Mandioca e Fruticultura, Coordenação de Aperfeiçoamento de Pessoal de NÃvel Superior.
Abstract (Originalsprache)
Cassava ( Manihot esculenta Crantz) is a staple food and a key industrial crop across tropical regions, but traditional phenotyping for critical quality traits like dry matter content (DMC) and starch content (StC) is a laborious and low-throughput process. This study investigates the efficacy of a handheld near-infrared spectrometer device (NIRS) for the non-destructive, rapid prediction of these traits. The research methodology involved collecting spectral data from 2,236 cassava clones from 19 field trials in Brazil, using two sample types: fresh roots and mashed roots. Six spectral pre-processing methods and three machine learning algorithms—Partial Least Squares (PLS), Support Vector Machines (SVM), and Extreme Gradient Boosting (XGB)—were evaluated to optimize predictive models. Model performance was assessed using the coefficient of determination in calibration ( R C ), the root mean squared error of calibration ( R M S E C ), and the Kappa index to quantify the consistency of clone selection. Results show that mashed samples consistently yielded superior predictive performance across all models. Specific preprocessing methods, such as Savitzky-Golay filtering combined with Standard Normal Variate (SG + SNV) and first-derivative transformations, significantly enhanced model accuracy. Among the algorithms, PLS demonstrated the best overall performance, with high predictive accuracy ( R C >0.96) and low prediction errors ( R M S E C
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Embrapa Mandioca e Fruticultura, Cruz das Almas, Brazil.
ORCID-Profile: Marcos de Souza Campos, Eder Jorge de Oliveira
Förderung
- Conselho Nacional de Desenvolvimento CientÃfico e Tecnológico
- Embrapa Mandioca e Fruticultura
- Coordenação de Aperfeiçoamento de Pessoal de NÃvel Superior
- Foreign, Commonwealth and Development Office
- Bill and Melinda Gates Foundation
Zitieren
APA
Guimarães, P. H. R., Morales, C. F. G., Cerqueira, T. S., Campos, M. S., & Oliveira, E. J. (2025). From root to result: Portable NIRS-based non-destructive prediction of cassava quality traits. PLOS One. https://doi.org/10.1371/journal.pone.0337761
Vancouver
Guimarães PHR, Morales CFG, Cerqueira TS, Campos MS, Oliveira EJ. From root to result: Portable NIRS-based non-destructive prediction of cassava quality traits. PLOS One. 2025. doi:10.1371/journal.pone.0337761
BibTeX
@article{Guimares2025,
author = {Guimarães, Paulo Henrique Ramos and Morales, Cinara Fernanda Garcia and Cerqueira, Tamires Sousa and Campos, Marcos de Souza and Oliveira, Eder Jorge de},
title = {From root to result: Portable NIRS-based non-destructive prediction of cassava quality traits},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0337761}
}
EUVIMED