Optimization of NIRS-based models for predicting quality and gas production traits of fresh alfalfa silage via machine learning.

Near-infrared spectroscopy (NIRS) prediction models offer an expeditious method for assessing the nutritional value of feedstuffs, however, developing high-performance models using undried and unground samples remains challenging. This study aimed to explore strategies to improve NIRS models for predicting silage quality and gas production of fresh alfalfa using machine learning approaches. A total of 348 spectral samples were collected for modeling 15 parameters of alfalfa silage. The modeling performance of Partial Least Squares Regression (PLSR), Principal Component Regression (PCR), Ridge Regression (RR), and Linear Support Vector Regression (L-SVR) were first evaluated based on a ten-fold cross-validation. Then, three spectral preprocessing methods-Savitzky-Golay smoothing combined with Standard Normal Variate (SG+SNV), SG with Multiplicative Scatter Correction (SG+MSC), and SNV with detrending (SNV+D) were employed to facilitate the modeling process. Besides, Least Absolute Shrinkage and Selection Operator (LASSO) and Binary Particle Swarm Optimization (BPSO) techniques were applied for selecting feature wavelengths to further optimize model performance. The results indicated that PLSR and RR exhibited relatively superior modeling performance while both spectral preprocessing and feature wavelength selection procedures effectively enhanced the optimal parameters. Acceptable modeling results were achieved for dry matter (DM), water-soluble carbohydrates (WSC), lactic acid (LA), pH, acetic acid (AA), neutral detergent fiber (NDF), and relative feed value (RFV) with corresponding R2CV of 0.986, 0.943, 0.958, 0.958, 0.897, 0.793, and 0.777, respectively. The models for 24-h gas and 48-h CH4 production performed relatively well among the gas traits, with R2CV of 0.534 and 0.506, respectively. Overall, the PLSR-SG+SNV-BPSO modeling strategy demonstrated the best performance, and thus may be considered a preferred approach for future research on developing NIRS models for fresh forage samples.

• Publication year

  2025

• Venue

  Spectrochimica Acta Part A - Molecular and Biomolecular Spectroscopy

• Publication date

  2025-12-13

• Fields of study

  Agricultural and Food Sciences, Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.1016/j.saa.2025.127352PMID 41418701
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• NIRS-based fresh grape ripeness prediction with SPA-LASSO spectral feature selection.

  2025cited by this paper
• Enhancement of non-destructive chicken freshness prediction using Vis/NIR spectroscopy through wavelength selection and data augmentation

  2025cited by this paper
• Fused LassoNet: Sequential feature selection for spectral data with neural networks

  2025cited by this paper
• Predicting Forage Nutritional Quality With Near‐Infrared Spectroscopy

  2025cited by this paper
• Effects of temperature and lactic acid Bacteria additives on the quality and microbial community of wilted alfalfa silage

  2024cited by this paper
• The effect of replacing conventional alfalfa hay with lower-lignin alfalfa hay on feed intake, nutrient digestibility, and energy utilization in lactating Jersey cows.

  2024cited by this paper
• Forage quality and fermentation dynamics of silages of Italian ryegrass (Lolium multiflorum Lam.) wilted for varying periods

  2024cited by this paper
• Stacking and ridge regression-based spectral ensemble preprocessing method and its application in near-infrared spectral analysis.

  2024cited by this paper
• Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes.

  2024cited by this paper
• Comparative near Infrared (NIR) spectroscopy calibrations performance of dried and undried forage on dry and wet matter bases.

  2024cited by this paper
• Application of NIRS for hay evaluation at different degrees of sample preparation.

  2024cited by this paper
• Optimization of visible transmission and NIR reflection in multilayer via PSO: simulation and experimental validation

  2024cited by this paper
• Near-infrared spectroscopy for analysing livestock diet quality: A systematic review

  2024cited by this paper
• Variations in the milk lipidomic profile of lactating dairy cows fed the diets containing alfalfa hay versus alfalfa silage

  2024cited by this paper
• Near Infrared Spectroscopy for Prediction of Yeast and Mould Counts in Black Soldier Fly Larvae, Feed and Frass: A Proof of Concept

  2023cited by this paper
• Near-infrared spectroscopy and machine learning-based technique to predict quality-related parameters in instant tea

  2022cited by this paper
• A Review of Machine Learning for Near-Infrared Spectroscopy

  2022cited by this paper
• Effects of Different Additives on Fermentation Quality, Microbial Communities, and Rumen Degradation of Alfalfa Silage

  2022cited by this paper
• Comparative Accuracy of In Vitro Rumen Fermentation and Enzymatic Methodologies for Determination of Undigested Neutral Detergent Fiber in Forages and Development of Predictive Equations Using NIRS

  2022cited by this paper
• Nutritional Characterization of Hay Produced in Campania Region: Analysis by the near Infrared Spectroscopy (NIRS) Technology

  2022cited by this paper
• Effect of Sowing Date on Growth Characteristics and Dry Matter Yield of Alfalfa in a Dry Paddy Field

  2022cited by this paper
• Preprocessing NIR Spectra for Aquaphotomics

  2022cited by this paper
• Fast detection of volatile fatty acids in biogas slurry using NIR spectroscopy combined with feature wavelength selection.

  2022cited by this paper
• A Preliminary Study to Classify Corn Silage for High or Low Mycotoxin Contamination by Using near Infrared Spectroscopy

  2022cited by this paper
• Prediction of quality of total mixed ration for dairy cows by near infrared reflectance spectroscopy and empirical equations

  2022cited by this paper
• The rumen microbiome: balancing food security and environmental impacts

  2021cited by this paper
• Effects of formic acid and lactic acid bacteria inoculant on main summer crop silages in Korea

  2021cited by this paper
• In Vitro Screening of East Asian Plant Extracts for Potential Use in Reducing Ruminal Methane Production

  2021cited by this paper
• Effect of harvest dates on β-carotene content and forage quality of rye (Secale cereale L.) silage and hay

  2021cited by this paper
• Effects of Different Carbohydrate Sources on Alfalfa Silage Quality at Different Ensiling Days

  2021cited by this paper
• The Effect of Gaseous Ozone Generated by Surface Dielectric Barrier Discharge on the Decay and Quality of Stored Onion Bulbs

  2021cited by this paper
• Methane mitigating options with forages fed to ruminants

  2021cited by this paper
• Use of near-infrared spectroscopy and multivariate approach for estimating silage fermentation quality from freshly harvested maize

  2021cited by this paper
• The usefulness of NIRS calibrations based on feed and feces spectra to predict nutrient content, digestibility and net energy of pig feeds

  2021cited by this paper
• Near-infrared calibration models for estimating volatile fatty acids and methane production from in vitro rumen fermentation of different total mixed rations

  2021cited by this paper
• Metagenomic analysis reveals the linkages between bacteria and the functional enzymes responsible for potential ammonia and biogenic amine production in alfalfa silage

  2021cited by this paper
• A novel NIR spectral calibration method: Sparse coefficients wavelength selection and regression (SCWR).

  2020cited by this paper
• Transportation of maize silage to biogas plants

  2020cited by this paper
• Preprocessing methods for near‐infrared spectrum calibration

  2020cited by this paper
• A comprehensive review on the variants of support vector machines

  2019cited by this paper
• Near infrared spectroscopy: A mature analytical technique with new perspectives - A review.

  2018cited by this paper
• High-Resolution Remote Sensing Image Change Detection by Statistical-Object-Based Method

  2018cited by this paper
• Development and validation of near-infrared spectroscopy for the prediction of forage quality parameters in Lolium multiflorum

  2017cited by this paper
• A wavelength selection method based on random decision particle swarm optimization with attractor for near‐infrared spectral quantitative analysis

  2015cited by this paper
• Near Infrared Reflectance Spectroscopy (NIRS) for rapid determination of biochemical methane potential of plant biomass

  2014cited by this paper
• The Combined Optimization of Savitzky-Golay Smoothing and Multiplicative Scatter Correction for FT-NIR PLS Models

  2013cited by this paper
• Near infrared reflectance spectroscopy for determination of the geographical origin of wheat.

  2013cited by this paper
• Prediction of pork quality with near infrared spectroscopy (NIRS): 1. Feasibility and robustness of NIRS measurements at laboratory scale.

  2012cited by this paper
• Study on the Best Analysis Spectral Section of NIR to Detect Alcohol Concentration Based on SiPLS

  2012cited by this paper
• Removing the effect of soil moisture from NIR diffuse reflectance spectra for the prediction of soil organic carbon

  2011cited by this paper
• Variable selection in near-infrared spectroscopy: benchmarking of feature selection methods on biodiesel data.

  2011cited by this paper
• Ridge regression

  2009cited by this paper
• Ensemble preprocessing of near-infrared (NIR) spectra for multivariate calibration.

  2008cited by this paper
• Near infrared spectroscopy for determination of various physical, chemical and biochemical properties in Mediterranean soils.

  2008cited by this paper
• Applying spectral peak area analysis in near-infrared spectroscopy moisture assays.

  2007cited by this paper
• Prediction of gas production kinetic parameters of forages by chemical composition and near infrared reflectance spectroscopy

  2005cited by this paper
• NIR spectroscopy: a rapid-response analytical tool

  2002cited by this paper
• Determination of Research Octane Number using NIR Spectral Data and Ridge Regression

  2001cited by this paper
• The use of near infrared reflectance spectroscopy /NIRS on undried samples of grass silage to predict chemical composition and digestibility parameters

  1998cited by this paper
• Interpretive Spectroscopy for Near Infrared

  1996cited by this paper
• Regression Shrinkage and Selection via the Lasso

  1996cited by this paper
• Methods for dietary fiber, neutral detergent fiber, and nonstarch polysaccharides in relation to animal nutrition.

  1991cited by this paper
• Proposed Hay Grading Standards Based on Laboratory Analyses for Evaluating Quality

  1978cited by this paper
• Relationship between Fibrous Components and In vitro Dry Matter Digestibility of Autumn‐saved Grasses1

  1977cited by this paper
• The estimation of carbohydrates in plant extracts by anthrone.

  1954cited by this paper

• No citing papers are available for this paper.