DOI: 10.31220/agriRxiv.2022.00162

•  

  Abstract: Abstract Traditionally, wine producers perform early wine quality prediction on-site based on the berry morphological and sensory characteristics together with the measurement of basic chemical parameters. Incorporating analysis on grape and wine volatiles could potentially achieve accurate prediction of wine quality, but forming these models requires careful selection of grapes, controlled fermentations and standardised quality assessment. Here, we present 3 models for the prediction of quality in Shiraz wine. Modelling was done by general regression analysis with 4-fold cross-validation. Model 1 (R 2 = 99.97% and 4-fold R 2 = 97.61%) for prediction of wine quality from wine volatiles, Model 2 (R 2 = 99.89% and 4-fold R 2 = 98.42%) for early prediction of wine quality from free- and glycosidically- bound grape volatiles, and Model 3 (R 2 = 91.62% and 4-fold R 2 = 80.21%) for prediction of wine quality from free grape volatiles only. The accuracy of these models presents an advancement in the early prediction of wine quality and provide a valuable tool to assist grape growers and winemakers in understanding quality in the vineyard to better direct scarce resources.

  Key words: wine quality; prediction; fold; model; models; grap

  Submit time: 1 January 2022

  Copyright: The copyright holder for this preprint is the author/funder, who has granted agriXiv a license to display the preprint in perpetuity.
• html

• 图表

• Nuriel Shalom Mor, Tigabo Asras, Eli Gal, Tesfahon Demasia, Ezra Tarab, Nathaniel Ezekiel, Osher Nikapros, Oshri Semimufar, Eva Gladky, Maria Karpenko, Daniel Sason, Д. Н. Маслов, Omri Mo. Wine quality and type prediction from physicochemical properties using neural networks for machine learning: a free software for winemakers and customers.. 2022. doi: 10.31220/agriRxiv.2022.00125

  Viviane Costa Silva, Mateus Silva Rocha, Gláucia Amorim Faria, Sílvio Fernando Alves Xavier, Tiago Almeida de Oliveira, Ana Patrícia Bastos Peixot. Boosting algorithms for prediction in agriculture: an application of feature importance and feature selection boosting algorithms for prediction crop damage.. 2021. doi: 10.31220/agriRxiv.2021.00092

  Akhil Wilson, N. Hemalatha, Raji Sukuma. Computational prediction model for pepper yield prediction using support vector regression.. 2021. doi: 10.31220/agriRxiv.2021.00069

  Akhil Wilson, Raji Sukumar, N. Hemalath. Machine learning model for rice yield prediction using KNN regression.. 2021. doi: 10.31220/agriRxiv.2021.00070

  P. Sukhetha, N. Hemalatha, Raji Sukuma. Classification of fruits and vegetables using ResNet model.. 2021. doi: 10.31220/agriRxiv.2021.00075

  Yusuke Toda, Goshi Sasaki, Yoshihiro Omori, Yuji Yamasaki, Hirokazu Takahashi, Hideki Takanashi, Masayuki Tsuda, Hiromi Kajiya‐Kanegae, Raúl López-Lozano, Hisashi Tsujimoto, Akito Kaga, Mikio Nakazono, Toru Fujiwara, Frédéric Baret, Hiroyoshi Iwat. Genomic prediction of green fraction dynamics in soybean using UAV observations.. 2021. doi: 10.31220/agriRxiv.2021.00097

  Prosper Kamusasa, Eddington Gororo, Fungayi Primrose Chatiz. Effect of whole and clarified egg yolk based extenders on post-thaw semen quality in bulls.. 2021. doi: 10.31220/agriRxiv.2021.00050

  Tashin Ahmed, Chowdhury Rafeed Rahman, Md. Faysal Mahmud Abi. Rice grain disease identification using dual phase convolutional neural network based system aimed at small dataset.. 2021. doi: 10.31220/agriRxiv.2021.00062

  Richa Rajput, A. Arunachala. Plant residue quality index and ecological potential approach for selective reincorporation of crop residues in soil.. 2022. doi: 10.31220/agriRxiv.2022.00122

  M. Shanmugam, M. Niranjan, S.V. Rama Ra. Effect of dietary L-carnitine supplementation on semen quality parameters in Dahlem Red chicken.. 2022. doi: 10.31220/agriRxiv.2022.00129

• ID

  Submit time

  Number

  Download

• Public  Anonymous  To author only Submit Comments