Predicting Forage Quality of Warm-Season Legumes by Near Infrared Spectroscopy Coupled with Machine Learning Techniques

Abstract

Warm-season legumes have been receiving increased attention as forage resources in the southern United States and other countries. However, the near infrared spectroscopy (NIRS) technique has not been widely explored for predicting the forage quality of many of these legumes. The objective of this research was to assess the performance of NIRS in predicting the forage quality parameters of five warm-season legumes—guar (Cyamopsis tetragonoloba), tepary bean (Phaseolus acutifolius), pigeon pea (Cajanus cajan), soybean (Glycine max), and mothbean (Vigna aconitifolia)—using three machine learning techniques: partial least square (PLS), support vector machine (SVM), and Gaussian processes (GP). Additionally, the efficacy of global models in predicting forage quality was investigated. A set of 70 forage samples was used to develop species-based models for concentrations of crude protein (CP), acid detergent fiber (ADF), neutral detergent fiber (NDF), and in vitro true digestibility (IVTD) of guar and tepary bean forages, and CP and IVTD in pigeon pea and soybean. All species-based models were tested through 10-fold cross-validations, followed by external validations using 20 samples of each species. The global models for CP and IVTD of warm-season legumes were developed using a set of 150 random samples, including 30 samples for each of the five species. The global models were tested through 10-fold cross-validation, and external validation using five individual sets of 20 samples each for different legume species. Among techniques, PLS consistently performed best at calibrating (R2c = 0.94–0.98) all forage quality parameters in both species-based and global models. The SVM provided the most accurate predictions for guar and soybean crops, and global models, and both SVM and PLS performed better for tepary bean and pigeon pea forages. The global modeling approach that developed a single model for all five crops yielded sufficient accuracy (R2cv/R2v = 0.92–0.99) in predicting CP of the different legumes. However, the accuracy of predictions of in vitro true digestibility (IVTD) for the different legumes was variable (R2cv/R2v = 0.42–0.98). Machine learning algorithms like SVM could help develop robust NIRS-based models for predicting forage quality with a relatively small number of samples, and thus needs further attention in different NIRS based applications.

Detecting Biophysical Characteristics and Nitrogen Status of Finger Millet at Hyperspectral and Multispectral Resolutions

“…It generates latent variables, also known as score vectors, to capture the variability related to the dependent variable(s). Technically, PLSR develops a model by deriving Xscores from latent variables to predict Y-scores (Baath et al, 2020). A redundancy analysis on the X-and Y-scores brings directionality in the factor space to obtain the most accurate prediction (Wu and Yu, 2016).…”

Near-infrared spectroscopy calibration strategies to predict multiple nutritional parameters of pasture species from different functional groups

“…Near-infrared reflectance spectroscopy has been shown to accurately predict forage nutritional quality, such as in studies involving mixed bulk samples of central European grasslands (Berauer et al, 2020), fresh samples from natural pastures in Italy (Parrini et al, 2019), warm-season legumes in the United States (Baath et al, 2020), and native and temporary grasses in the United Kingdom (Bell et al, 2018). However, few studies report on the establishment of NIRS calibration models for predicting multiple nutritional constituents, such as ash, crude protein, ether extract, neutral detergent fibre, acid detergent fibre and acid detergent lignin, and fewer still include calibrations using large sample sets comprised of multiple pasture species (Parrini et al, 2018;Parrini et al, 2019;cf.…”

In‐line characterization of dispersion uniformity evolution during a twin‐screw blending extrusion based on near‐infrared spectroscopy

“…Due to the above mentioned reasons, NIR spectroscopy has been widely used for nondestructive measurements in a variety of domains, such as food, [13,14] pharmacy, [15,16] petrochemical, [17,18] and chemical engineering. [19][20][21] Recently, chemometrics and machine learning methods further push forward the development of NIR spectroscopy, [22][23][24][25] which help to extract feature information from the spectra and serve as a basic tool for classification or regression. [26,27] A series of studies exist in the literatures that characterize the dispersion state using NIR spectroscopy.…”