Rapid and Accurate Measurement of Major Soybean Components Using Near-Infrared Spectroscopy

This study addresses the urgent need for the rapid, non-destructive assessment of key soybean components, including moisture, fat, and protein, using near-infrared (NIR) spectroscopy. This study provides technical and theoretical support for achieving the efficient and accurate detection of major so...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenxiao Li, Jiatong Yu, Sheng Wang, Qinglong Zhao, Qian Song, Yanlei Xu
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/15/7/1505
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849304245367472128
author Chenxiao Li
Jiatong Yu
Sheng Wang
Qinglong Zhao
Qian Song
Yanlei Xu
author_facet Chenxiao Li
Jiatong Yu
Sheng Wang
Qinglong Zhao
Qian Song
Yanlei Xu
author_sort Chenxiao Li
collection DOAJ
description This study addresses the urgent need for the rapid, non-destructive assessment of key soybean components, including moisture, fat, and protein, using near-infrared (NIR) spectroscopy. This study provides technical and theoretical support for achieving the efficient and accurate detection of major soybean components and for the development of portable near-infrared (NIR) instruments. Thirty soybean samples from diverse sources were collected, and 360 spectral measurements were acquired using a 900–1700 nm NIR spectrometer after grinding and standardized sampling. To improve model robustness, preprocessing strategies such as standard normal variate (SNV), multiplicative scatter correction (MSC), and Savitzky–Golay derivatives were applied. Feature selection was conducted using competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE), followed by model construction with partial least squares regression (PLSR), support vector regression (SVR), and random forest (RF). Comparative analysis revealed that the RF model consistently outperformed the others across most combinations. Specifically, the SPASNV + D<sub>1</sub>–RF combination achieved an RPD of 14.7 for moisture, CARS–SNV + D<sub>1</sub>–RF reached 5.9 for protein, and CARS–SG + D<sub>2</sub>–RF attained 12.0 for fat, all significantly surpassing alternative methods and demonstrating a strong nonlinear learning capacity and predictive precision. These findings show that integrating optimal preprocessing and feature selection strategies can markedly enhance the predictive accuracy in NIR-based soybean analyses. The RF model offers exceptional stability and performance, providing both technical reference and theoretical support for the development of portable NIR devices and practical rapid-quality assessment systems for soybeans in industrial applications.
format Article
id doaj-art-090ff9a7030d4823a8e4b1771b98a047
institution Kabale University
issn 2073-4395
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-090ff9a7030d4823a8e4b1771b98a0472025-08-20T03:55:48ZengMDPI AGAgronomy2073-43952025-06-01157150510.3390/agronomy15071505Rapid and Accurate Measurement of Major Soybean Components Using Near-Infrared SpectroscopyChenxiao Li0Jiatong Yu1Sheng Wang2Qinglong Zhao3Qian Song4Yanlei Xu5College of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Physics, Jilin University, Changchun 130012, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaThis study addresses the urgent need for the rapid, non-destructive assessment of key soybean components, including moisture, fat, and protein, using near-infrared (NIR) spectroscopy. This study provides technical and theoretical support for achieving the efficient and accurate detection of major soybean components and for the development of portable near-infrared (NIR) instruments. Thirty soybean samples from diverse sources were collected, and 360 spectral measurements were acquired using a 900–1700 nm NIR spectrometer after grinding and standardized sampling. To improve model robustness, preprocessing strategies such as standard normal variate (SNV), multiplicative scatter correction (MSC), and Savitzky–Golay derivatives were applied. Feature selection was conducted using competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE), followed by model construction with partial least squares regression (PLSR), support vector regression (SVR), and random forest (RF). Comparative analysis revealed that the RF model consistently outperformed the others across most combinations. Specifically, the SPASNV + D<sub>1</sub>–RF combination achieved an RPD of 14.7 for moisture, CARS–SNV + D<sub>1</sub>–RF reached 5.9 for protein, and CARS–SG + D<sub>2</sub>–RF attained 12.0 for fat, all significantly surpassing alternative methods and demonstrating a strong nonlinear learning capacity and predictive precision. These findings show that integrating optimal preprocessing and feature selection strategies can markedly enhance the predictive accuracy in NIR-based soybean analyses. The RF model offers exceptional stability and performance, providing both technical reference and theoretical support for the development of portable NIR devices and practical rapid-quality assessment systems for soybeans in industrial applications.https://www.mdpi.com/2073-4395/15/7/1505near-infrared spectroscopysoybeanchemometricsvariable selectionprediction model
spellingShingle Chenxiao Li
Jiatong Yu
Sheng Wang
Qinglong Zhao
Qian Song
Yanlei Xu
Rapid and Accurate Measurement of Major Soybean Components Using Near-Infrared Spectroscopy
Agronomy
near-infrared spectroscopy
soybean
chemometrics
variable selection
prediction model
title Rapid and Accurate Measurement of Major Soybean Components Using Near-Infrared Spectroscopy
title_full Rapid and Accurate Measurement of Major Soybean Components Using Near-Infrared Spectroscopy
title_fullStr Rapid and Accurate Measurement of Major Soybean Components Using Near-Infrared Spectroscopy
title_full_unstemmed Rapid and Accurate Measurement of Major Soybean Components Using Near-Infrared Spectroscopy
title_short Rapid and Accurate Measurement of Major Soybean Components Using Near-Infrared Spectroscopy
title_sort rapid and accurate measurement of major soybean components using near infrared spectroscopy
topic near-infrared spectroscopy
soybean
chemometrics
variable selection
prediction model
url https://www.mdpi.com/2073-4395/15/7/1505
work_keys_str_mv AT chenxiaoli rapidandaccuratemeasurementofmajorsoybeancomponentsusingnearinfraredspectroscopy
AT jiatongyu rapidandaccuratemeasurementofmajorsoybeancomponentsusingnearinfraredspectroscopy
AT shengwang rapidandaccuratemeasurementofmajorsoybeancomponentsusingnearinfraredspectroscopy
AT qinglongzhao rapidandaccuratemeasurementofmajorsoybeancomponentsusingnearinfraredspectroscopy
AT qiansong rapidandaccuratemeasurementofmajorsoybeancomponentsusingnearinfraredspectroscopy
AT yanleixu rapidandaccuratemeasurementofmajorsoybeancomponentsusingnearinfraredspectroscopy