Research Thesis Topic
Advanced Statistical and Computational Framework for Solar Energy Modelling with Satellite and Geophysical Data: Application for Renewable Energy Prospectivity Mapping with Machine Learning
Solar energy is a renewable resource to combat climate change with least environmental impact. In Australia, there is growing debate on the adoption of solar energy as a substitute for carbon-based fuels and solar energy is projected to increase from 7.0 PJ in 2007–08 to 24.0 PJ in 2029–30 with electricity generation from solar power projected to increase from 0.1 TWh in 2007–08 to 4.0 TWh in 2029–30. Due to the correlation between solar radiation and daytime electricity demand, it is envisaged that solar energy has good potential to supply electricity in peak demand time. As Renewable Energy Target advocates that 23.5% of electricity is to be derived from renewables by 2020, incentive to develop scientific techniques to harness solar energy must be explored.
This project will apply advanced data-driven models (neural networks, boot-strapping, wavelet transformations and Bayesian framework) combined with satellite and geophysical data to develop models for solar prospectivity mapping. Data from AVHRR, MODIS and other satellites and meteorological measurements will be used to design models for solar energy prediction and uncertainty assessment in models to help design new models for solar energy simulation.
The project is suitable for students interested in renewable energy, electrical or mechanical engineering, atmospheric science, mathematics, physics and data science. The project is scalable for further research, such as to a Masters or a PhD program to advance research careers, acquire programming skills and modelling. The project present opportunity to develop new modelling & computational skills and research-publications within the Environmental Modelling and Simulation Research Group.
- Institute for Agriculture and the Environment
- International Centre for Applied Climate Sciences
- National Centre for Engineering in Agriculture
- School of Agricultural, Computational and Environmental Sciences
- Artificial Intelligence and Image Processing
- Atmospheric Sciences
- Mechanical Engineering
Please review the admission requirements for the academic program associated with this Thesis Topic
Suits students interested with background in energy, atmospheric science, environmental physics, climate science, computing and electrical/mechanical backgrounds.