CSIRO IPhD- Optimising solar farm usage utilising aerial images

The PhD will use historical and current ground-based data and observations to validate and train a machine learning model to obtain the same information from high resolution hyperspectral satellite images.

This project aims to leverage high resolution satellite images and artificial intelligence to enhance vegetation management and grazing efficiency in solar farms.

Key details

Reference number

20246658

For course

MRes Year 2 + PhD, PhD

Key dates

Applications close on 31 October 2024

Student type

Domestic

Area of study

Engineering

Stipend value
(Direct payment)

$47,000 p.a.

The potential benefits are enhanced solar operation and vegetation management efficiency, bush fire risk monitoring and solar grazing.

The main objectives are to:

  1. develop an algorithm using commercial satellite imagery to monitor and predict key factors including curing rates, vegetation growth, grazing patterns and effectiveness of land management.
  2. explore the use of free satellite imagery to achieve similar outcomes within an acceptable degree of accuracy and uncertainty.
  3. compare the algorithm with real-world data to improve vegetation management, optimise grazing patterns, prevent overgrazing, and automate the data required to determine the curing rating.

Availability

This scholarship is available to eligible candidates to undertake:

  • a direct entry three-year PhD program, or
  • a four-year MRes Year 2 + PhD program.

Components

The scholarships comprise:

  • a tuition fee offset/scholarship
  • a living allowance stipend.
  • supervision by the participating university, CSIRO and an industry partner
  • a project Expense and Development package of $13,000 per annum
  • a three month industry engagement component with the industry partner
  • a structured professional development and training program to develop your applied research skills.

The value of each stipend scholarship is $47,000 per annum (full-time, fixed rate) for four years.