Using Bayesian growth models to predict grape yield

Type of content
Theses / Dissertations
Publisher's DOI/URI
Thesis discipline
Statistics
Degree name
Doctor of Philosophy
Publisher
University of Canterbury
Journal Title
Journal ISSN
Volume Title
Language
English
Date
2021
Authors
Ellis, Rory
Abstract

Seasonal differences in in vine yield need to be managed to ensure appropriate fruit composition at harvest. Differences in yield are the result of changes in vine management (e.g. the number of notes retained after harvest) and weather conditions (in particular, temperature) at key vine development stages. Early yield prediction enables growers to manage vines to achieve target yields and prepare the required infrastructure for harvest.

This thesis explores Bayesian modelling approaches in three case studies, building on an underlying understanding of grape growth processes. In doing so, the algorithm developed during this thesis evolves from estimating grape bunch masses for a solitary vineyard, to estimating bunch masses using the Dirichlet distribution, to finally being used in a Bayesian hierarchical modelling framework to estimate bunch masses for multiple vineyards. Each model is described in detail, with results discussed in depth. Further insights are given to how the model can be utilised in other parts of grape bunch mass prediction, highlighting considerations for the industry.

Description
Citation
Keywords
Ngā upoko tukutuku/Māori subject headings
ANZSRC fields of research
Rights
All Right Reserved