Research Thesis Topic
Predictive Analytics with Big Data: Heatwave and Drought Modelling with Nature-Inspired Machine Learning
Drought and heatwaves are challenging events that are catastrophic and cause significant harm to crops, human health, ecosystem and economy. Advanced modelling of drought and heatwaves is challenging, so new models that are smart enough to accurately represent their behaviour is very important. Such models can be used in decision systems by farmers, resource managers, water quality management and government.
In this project, the students will model big data (of environmental origin such as rainfall, temperature and streamflow) for drought and heatwave prediction. Often, the agricultural industry fails to utilise relevant input features from atmospheric and hydrological data when developing a drought or a heatwave model. In this project students will use machine learning that offers advanced solutions for high-precision modelling, as an emerging technology to discover the patterns in natural (geographic & hydro-physical) data to design prototypical models for prediction of heatwaves and drought.
The nature-inspired models will analyse patterns in hydro-meteorological variables to model drought and heat indices over daily and seasonal scales. Local-scale models are useful for real applications, yet challenging since they require large (atmospheric & ground) inputs from physical and statistical sources. This project will develop models for feature selection to find optimal features in inputs, reduce model complexity and improve its efficiency. Students will apply bio-inspired algorithms to predict heatwaves or drought and will learn about their application in agriculture, climate risk management and environment.
The project will suit students with background in environmental science, agriculture, mathematics, computing and climate/atmospheric physics. 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. Students will learn artificial neural network models, machine learning in agriculture, expert system development with smart predictive tools and evaluation of such models in real-time forecasting of drought or heatwaves.
- Institute for Agriculture and the Environment
- National Centre for Engineering in Agriculture
- School of Agricultural, Computational and Environmental Sciences
- Artificial Intelligence and Image Processing
- Atmospheric Sciences
- Civil Engineering
- Environmental Science and Management
Please review the admission requirements for the academic program associated with this Thesis Topic
Suits students interested with background in civil engineering (hydrology), atmospheric science, environmental physics, climate science, computing and water science.