Prediction of forage chemical composition by NIR spectroscopy

Vranić, Marina; Bošnjak, Krešimir; Rukavina, Ivana; Glavanović, Siniša; Pukec, Nataša Pintić; Babić, Andreja; Vranić, Ivica

doi:10.5513/jcea01/21.3.2839

Cited by 8 publications

(7 citation statements)

References 1 publication

(2 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For assessing the application of scattering correction pre-treatments to NIR spectra, spectral and reference (chemical composition) data of animal feeds were used, a field where NIR technology has been extensively applied. [43][44][45][46] To evaluate the impact of using type II regression models when applying MSC to spectral data on the development of calibration equations, NIR spectra from 54 Lucerne (cv. Timbale) herbage samples were used (Data Set 3) from a study to investigate the effects of cultivation date and method on the establishment of Lucerne in the UK.…”

Section: Impact Of Regression Models On Calibration and Validationmentioning

confidence: 99%

Methodology adjusting for least squares regression slope in the application of multiplicative scatter correction to near‐infrared spectra of forage feed samples

Dhanoa

López

Sanderson

et al. 2023

Journal of Chemometrics

View full text Add to dashboard Cite

Scatter corrections are commonly applied to refine near‐infrared (NIR) spectra. The aim of this study is to assess the impact of measurement errors when using ordinary least squares (OLS) for multiplicative scatter correction (MSC). Any measurement errors attached to the set‐mean spectrum may attenuate the OLS slope and that in turn will affect the estimate of the intercept and the adjustment of the spectra when using MSC methods to mitigate scattering. A corrected least squares slope may be used instead to prevent this problem, although the impact of this approach on the final outcome will depend on the relative size of the measurement errors in the individual spectra and the set‐mean spectrum. The errors‐in‐variables or type II regression model (also known as Deming regression) and its special cases, major axis (MA) and reduced major axis (RMA), are discussed and illustrated. The extent of OLS slope bias or attenuation is demonstrated as is the resulting MSC spectral distortion. Further modification to the MSC transformation method is also suggested. The influence of scattering correction (by MSC, standard normal variate (SNV) and detrending) and of using the maximum likelihood estimate of the slope for MSC on the prediction of chemical composition of Lucerne herbage from NIR spectra was assessed. The predictive performance was slightly improved by the use of scattering corrections with fairly minor differences among methods. Nonetheless, it seems well worth considering the use of type II regression models for assessing MSC application aiming at improving the goodness of prediction from NIR spectra.

show abstract

Section: Impact Of Regression Models On Calibration and Validationmentioning

confidence: 99%

Methodology adjusting for least squares regression slope in the application of multiplicative scatter correction to near‐infrared spectra of forage feed samples

Dhanoa

López

Sanderson

et al. 2023

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…Infrared spectroscopy. Mid-and near-infrared (NIR) spectroscopy has recently been successfully used to predict complex food phenotypes and an extensive set of quality traits (Bresolin & Dorea, 2020;Pralle & White, 2020;Vranic et al, 2020). NIR uses both empirical techniques and machine learning, although the proportion of machine learning increases with increasingly massive output.…”

Section: Large Scope Analysis Techniquesmentioning

confidence: 99%

A primer on predictive techniques for food and bioresources transformation processes

Sicard

Barbe²,

Boutrou

et al. 2023

J Food Process Engineering

View full text Add to dashboard Cite

To meet current societal demand for more sustainable transformation processes and bioresources, these processes must be optimized and new ones developed. The evolution of various systems (raw material, food, or process attributes) can be predicted to optimize the uses of biomass for better quality, safety, economic benefit, and sustainability. Predictive modeling can guide the necessary changes and influence industrials, governmental policies and consumers decision-making. However, achieving good predictive capability requires reflection on the models and model validation, which can be difficult. This review aims to help scientists begin to predict by presenting the techniques currently used in predictive science for food and related bioproducts. First, a guideline helps readers initiate a prediction process along with final tips and a warning about the risks involved, with a particular focus on the crucial validation step. Three broad categories of techniques are then presented: empirical, mechanistic, and artificial intelligence (or "data-driven"). For each category, the advantages and limitations of current techniques for prediction are explained in light of their current domains of applications, illustrated with literature studies and a detailed example. Thus this article provides engineering researchers information about predictive modeling which is a recent relevant development in optimization of both food and nonfood bioresources processes. Practical applicationsPredictive modeling is a recent development of much relevance in the optimization of both food and nonfood bioresources processes. The goal of this article is to guide those in research or industry who would like to start predicting. Therefore, the article is intended as a primer on prediction concepts and predictive techniques for food and non-food bioresources processing. Three categories of techniques commonly used in these fields are illustrated by various examples of current applications and a more detailed example helps to understand the implementation process. An increased ability of the global scientific body to predict the outcome of various decisions, often linked or sequential, will open new avenues for designing food products with circularity in mind: maintaining value and not creating waste in the process.

show abstract

“…The nutritive value of MS is mostly defined by the content of DM, ash, CP, NDF, ADF, ADL, and starch (Garcia et al 2003;Hoffman et al 2015;Vranić et al, 2020). The results of previous studies regarding the effect of maize crop differing in cutting height at harvest on the chemical composition of MS are presented in table 1.…”

Section: Effect Of Cutting Height Of Maize Crop On Chemical Compositi...mentioning

confidence: 99%

The effect of maize crop cutting height and the maturity at harvest on maize silage chemical composition and fermentation quality in silo

Kolar¹,

Vranić²,

Božić³

et al. 2022

JCEA

View full text Add to dashboard Cite

Maize silage (MS) has become one of the major energy components in ruminant nutrition. The maize crop is suitable for ensiling and is of high dry matter (DM) yield and nutritive value. The aim of this review is to provide a comprehensive overview of the effect of cutting height and maize crop maturity at harvest on the chemical composition of MS and fermentation quality in a silo. With an increase in cutting height and maize crop maturity, the content of dry matter (DM) in MS increases to about 400 g DM/kg of fresh crop, after which it does not change, crude protein (CP) CP content increases or remains the same, the ash content decreases or remains the same, starch content increases, and the content of neutral detergent fibre (NDF), acid detergent fibre (ADF) and acid detergent lignin (ADL) decreases or remains the same. The cutting height and maize crop maturity at harvest have no effect on pH value, lactic, acetic neither butyric acid but increases the amount of ethanol and decreases the ammonium nitrogen (NH 3 -N) in MS.

show abstract

Prediction of forage chemical composition by NIR spectroscopy

Cited by 8 publications

References 1 publication

Methodology adjusting for least squares regression slope in the application of multiplicative scatter correction to near‐infrared spectra of forage feed samples

Methodology adjusting for least squares regression slope in the application of multiplicative scatter correction to near‐infrared spectra of forage feed samples

A primer on predictive techniques for food and bioresources transformation processes

The effect of maize crop cutting height and the maturity at harvest on maize silage chemical composition and fermentation quality in silo

Contact Info

Product

Resources

About