Application of deep learning to leverage high-throughput phenotyping for crop breeding

Monica Furaste Danilevicz

Research output: ThesisDoctoral Thesis

38 Downloads (Pure)

Abstract

High-throughput plant phenotyping (HTPP) platforms can monitor phenotypic variation through multiple sensor types, generating valuable datasets for characterising the phenotype. However, the lack of appropriate analysis methods leads to the underutilisation of HTPP in crop breeding. This thesis has sought to investigate the advantage of using deep learning models to tackle unsolved challenges in using HTPP datasets for crop research by (i) implementing models for yield prediction of crops under breeding trial; (ii) assessing the advantages of integrating varied data types in the deep learning model; and (iii) building a model to identify weeds among a similar looking crop
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • The University of Western Australia
Supervisors/Advisors
  • Bennamoun, Mohammed, Supervisor
  • Bayer, Philipp, Supervisor
  • Edwards, Dave, Supervisor
  • Batley, Jacqueline, Supervisor
Thesis sponsors
Award date21 Aug 2023
DOIs
Publication statusUnpublished - 2023

Cite this