Machine Learning Approaches to the Optimisation of Ensemble Based, Meteorological Hazard Predictions
Engineering, IT, Mathematics and Statistics
- This internship is able to cover project costs for domestic students only.
- The Industry Partner has implemented appropriate preparations to comply with Federal and State Government requirements regarding COVID-19 safety.
- If your skillset is aligned with this internship and you are located remotely, please enquire with the Internship Contact to discuss possible arrangements.
ABOUT THE INDUSTRY PARTNER
The Bureau of Meteorology is Australia’s national weather, climate and water agency. Its expertise and services assist Australians in dealing with the harsh realities of their natural environment, including drought, floods, fires, storms, tsunami and tropical cyclones. Through regular forecasts, warnings, monitoring and advice spanning the Australian region and Antarctic territory, the Bureau provides one of the most fundamental and widely used services of government.
The Bureau contributes to national social, economic, cultural and environmental goals by providing observational, meteorological, hydrological and oceanographic services and by undertaking research into science and environment related issues in support of its operations and services.
WHAT’S IN IT FOR YOU?
- Opportunity to work with a world-class Bureau of Meteorology
- Gain real-world insights into research methods within BOM
- To engage, interact and learn from a multidisciplinary team of exports
RESEARCH TO BE CONDUCTED
The Bureau of Meteorology is developing a state-of-the-art thunderstorm nowcasting capability to mitigate the impacts of convective weather on air traffic flow management. The first phase of the Collaborative Convective Forecasting Project has delivered thunderstorm nowcasts from competing forecast systems; our challenge now is to assess the quality of each system and generate a performance weighted forecast ensemble that optimises the quality of the ensemble consensus.
Satellite observations, radar, aircraft location data, ground reports and lightning observations will be used to assess the quality of each thunderstorm nowcast and inform the composition of the resulting forecast ensemble.
This project will extend on the existing body of research by applying machine learning techniques in concert with established heuristic approaches to optimise system performance in near real time.
The following highlights the research to be done:
- Develop forecast performance metrics
- Generate a performance weighted forecast ensemble
- Optimise the quality of the ensemble consensus
SKILLS WISH LIST
If you’re a PhD student and meet some or all the below we want to hear from you. We strongly encourage women, indigenous and disadvantaged candidates to apply:
- Programming skills in a commonly used programming language such as Python, C++, R.
- Familiarity working with gridded data structures such as NetCDF files
- Ability to communicate clearly and effectively through written reports and oral presentations
- Understanding of machine learning techniques, particularly supervised learning and reinforcement learning.
The outputs of the project will be:
- Characterisation of the ability of the forecasting systems to predict the evolution of thunderstorms.
- An ensemble optimisation strategy
- A presentation of the study results in oral and written reports
- Identification of follow on opportunities
The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.
It is expected that the intern will primarily undertake this research project during regular business hours and maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.
The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.
CONNECT WITH APR.INTERN