<-- Back to schedule

Evaluating fire simulators using Docker, Dask and Jupyter notebooks!

Project: Bushfire predictive services

Bushfires are one of the most destructive forces in our environment. A major responsibility of the Bureau of Meteorology is to provide information on weather conditions that could make bushfires difficult to fight. Fire agencies then use simulators of fire behaviour to inform finer grained warnings to protect the Australian public. Objectively choosing the best performing simulators, or indeed the best versions of the same simulator, with respect to end-user requirements is a difficult task that requires a large amount of computation.

The introduction of new tools like Docker, Dask and Jupyter notebooks make the task of large scale computation much easier! The Bureau of Meteorology is looking at these technologies to help modernise its legacy workflows and processes, one example is our recent work in the area of fire simulators.

This talk will work through the approach developed for a reproducible environment (using Docker) and then how we form workflows (jupyter notebooks) that execute fire simulators on a small compute cluster of both windows and linux hosts (Dask, Distributed). Finally, we will work through an example of scaling up an experiment and demonstrate a process that is easy to replicate and follow for fellow scientists.

Nathan Faggian

Nathan Faggian's career started at Monash University, completing a PhD in computer vision under the supervision of Prof. Andrew Paplinski and Dr. Jamie Sherrah, working on the development of fast human face recognition algorithms. Nathans then shifted focus to work in medical imaging at the University of Melbourne and the Howard Florey Institute, working for Prof. Leigh Johnston and Prof. Gary Egan. Following a quick transition to the Centre for Neuroscience, Nathan was awarded an Australian Academy of Science grant to work in South Korea with Prof. Zhang-hee Cho on ultra-high field imaging. After the completion of his postdoc Nathan joined the Centre for Australian Weather and Climate Research (CAWCR) in the Australian Bureau of Meteorology to work on the development of a national forecasting system, the Graphical Forecast Editor (GFE). During this time Nathan developed tools that supported national fire weather forecast processes, which improved services to the Australian public. As a member of CAWCR Nathan also contributed to the development of "ensemble guidance", a post-processing of Numerical Weather Prediction (NWP) model output that underpins the public weather forecast. Nathan then briefly left the Bureau and transitioned into the corporate world, joining Microsoft as a data scientist. In this role he was responsible for delivering insights from large anti-malware datasets (using a huge volume of telemetry data) to support the continuous improvement of an entire research division. Following this transition Nathan re-joined the Bureau, division of weather services, to help with the development of bushfire predictive services.