Skip to main content
  • Home
  • Thesis Topics 
  • Future Climate Projection: Downscaling Global Climate Model with Artificial Intelligence for Agriculture and Renewable Energy Applications

Research Thesis Topic

Future Climate Projection: Downscaling Global Climate Model with Artificial Intelligence for Agriculture and Renewable Energy Applications


Topic ID
323

Thesis Topic/Title
Future Climate Projection: Downscaling Global Climate Model with Artificial Intelligence for Agriculture and Renewable Energy Applications

Description

In agriculture and renewable energy models, the future projected solar radiation, rainfall, stream-flow, temperature and wind speeds is essential. Warming scenarios are considered when projecting such variables with different CO2 through global climate models (GCM), but the coarse resolution of GCM (in order of 100 km) makes it difficult to interpret and apply projected information at local (e.g. farm or city) level.

In this exciting project, the students will address the challenge by designing artificial intelligence models for future climate projections and downscaling global climate model variables (e.g. drought, heatwave, solar radiation). The project will use machine learning approach, a relatively new, yet a powerful tool to accurately downscale GCM data at high resolution local scales.

This will be done by a two-step process (i) the development of statistical relationships between local climate variables (e.g., air temperature and precipitation) and large-scale predictors (e.g., pressure fields), and (ii) the application of such relationships to the output of global climate model experiments to simulate local climate characteristics in the future. Students will learn advanced statistical skills, extract and model Intergovernmental Panel of Climate Change (IPCC) approved CMIP-5 (coupled model inter-comparison phase 5) datasets.

Students will apply downscaled models in perspective of renewable energy modelling, water resource prediction, streamflow simulation and agricultural applications (e.g. rainfall prediction). Smart level machine learning models such as extreme learning machines, deep learning neural networks, wavelet transformations, empirical mode decomposition and several other learning algorithms will be used.

The project will suit students with background in engineering, mathematics, computing, climate, hydrology, water management, renewable energy and environment. Students will explore deep learning to enhance the performance accuracy of downscaled models. 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.


Principal Supervisor


Research Affiliations
  • Institute for Agriculture and the Environment
  • Institute for Resilient Regions
  • International Centre for Applied Climate Sciences
  • School of Agricultural, Computational and Environmental Sciences

Field of Research
  • Agriculture, Land and Farm Management
  • Applied Mathematics
  • Atmospheric Sciences
  • Civil Engineering
  • Ecological Applications
  • Other Earth Sciences
  • Statistics


Application Open Date
11/02/2018

Application Close Date
31/12/2019

USQ Scholarship Applications

Other Scholarship Funding Details
Australia Awards (Country-Specific Closing Dates), and Australian Endeavor Scholarships (Close June 2018)

Pre-approved for Ethics
Not Applicable

Admission Requirements

Please review the admission requirements for the academic program associated with this Thesis Topic

The project will suit students with background in engineering, mathematics, computing, climate, hydrology, water management, renewable energy and environment. Students will explore deep learning to enhance the performance accuracy of downscaled models. 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.




Back to List