Publicação

A smart approach to harvest date forecasting

Ver documento

Detalhes bibliográficos
Resumo:The concept of grape ripeness depends not only on the degree of enrichment of the chemical compounds in the grape and the volume of the berries, but also on the possible production purposes. The different types of maturation in individual cases are not sufficient for the decision on the harvest date. Taken together, however, they define oenological maturation times and help to harvest them. However, there are no consistent studies that correlate the chemical parameters obtained from must analysis and oenological maturation due to the nonlinearity of these two types of variables. Therefore, this work seeks to create a self-explanatory model that allows for the prediction of ideal harvest time, based on eneological parameters related to practices in new developments in knowledge acquisition and management in relational databases.
Autores principais:Charneca, Beatriz
Outros Autores:Santos, Vanda; Crespo, Ana; Vicente, Henrique; Ribeiro, Jorge; Alves, Victor; Neves, José; Chaves, Humberto
Assunto:Analysis of the Must Date of the Harvest Knowledge Discovery in Databases Data Mining Decision Trees Indexação Scopus Maturação da uva Mosto de uva
Ano:2019
País:Portugal
Tipo de documento:documento de conferência
Tipo de acesso:acesso aberto
Instituição associada:Instituto Politécnico de Beja
Idioma:inglês
Origem:Repositório Institucional do IPBeja
Descrição
Resumo:The concept of grape ripeness depends not only on the degree of enrichment of the chemical compounds in the grape and the volume of the berries, but also on the possible production purposes. The different types of maturation in individual cases are not sufficient for the decision on the harvest date. Taken together, however, they define oenological maturation times and help to harvest them. However, there are no consistent studies that correlate the chemical parameters obtained from must analysis and oenological maturation due to the nonlinearity of these two types of variables. Therefore, this work seeks to create a self-explanatory model that allows for the prediction of ideal harvest time, based on eneological parameters related to practices in new developments in knowledge acquisition and management in relational databases.