Top of page

Student/Staff Portal
Global Site Navigation

School of Science

Local Section Navigation
You are here: Main Content

Related Contents

Machine Learning Approaches for Plant Phenotyping

Project Outline

This project focuses on developing high-throughput plant phenotyping methods using UAV-based multispectral and hyperspectral imaging combined with machine learning, graph neural networks, and large language models. The goal is to predict key agronomic traits in crops such as wheat and maize, integrating visual, textual, and omics datasets to accelerate breeding programs, enhance stress-resilience evaluation, and improve crop improvement strategies in a changing climate.

Essential Skills

  • Strong programming skills in Python and R
  • Machine learning and deep learning knowledge (CNNs, transformers, GNNs)
  • Data processing for UAV-based imaging
  • Knowledge of plant biology and phenotyping techniques

Desired Skills

  • (if applicable)Experience with large language models (LLMs) and multimodal data integration
  • UAV operation and remote sensing
  • High-performance computing experience

Project Area: Computer Science; Biological and Environmental Science; Digital Agriculture

Supervisor(s): Dr Leisa Armstrong

Project Level: Masters / PhD

Funding: Applicant should apply for ECU HDR or RTP Scholarship

Start date: Any

Skip to top of page