Steefan Contractor

Post-doctoral Research Associate (Research Data Scientist)

UNSW Data Science Hub, School of Mathematics and Statistics, The Univesrsity of New South Wales

I am a research data scientist with an honours in experimental quantum computing, a doctorate in climate science and nearly five years of post-doctorate experience as a trans-disciplinary statistical and deep learning research consultant at the University of New South Wales (UNSW).

In my spare time I like to ride bicycles, climb rocks and ferment food and drinks.

Interests

Probabilistic machine learning and generative artificial intelligence
Spatiotemporal modeling and timeseries forecasting in climate, remote sensing, energy, economics and finance
Reinforcement learning for optimization of complex systems
Techniques that combine AI, statistical modelling and physics
Bayesian modelling with stochastic variational inference
Quantum machine learning

Education

PhD in Climate Science, 2019
Climate Change Research Centre, The University of New South Wales
Honours in Physics, 2012
ARC Centre of Excellence for Quantum Computation and Communication Technology, The University of New South Wales
BSc (Adv.) in Physics, 2012
School of Physics, The University of New South Wales

Projects

Improving Antarctic Sea Ice Detection with CubeSat GNSS-R

A novel application of passive GPS signals (GNSS-R) picked up by cube satellites to detect the location and age of Antarctic sea ice. A simple Bayes rule based update strategy has been implemented to improve estimates of various sea ice types using both a gradient boosting machine learning model and a robust mixture discriminent analysis statistical model as the likelihood.

Education and Outreach

I am the lead academic on two key UNSW data science education and outreach initiatives. 1. The UNSW Data Science Hub Year 10 Work Experience Week, and 2. UNSW SciX Data Science Project. The work experience week is an intense five day annual workshop for year 10 students where they learn what it is like to be a data scientist. The SciX Data Science Project is a two week workshop and support program for year 12 students where they complete a science research project with a data science flavor over the course of a year as part of the HSC science extension curriculum.

Sea Ice Segmentation

We use deep learning and computer vision to detect individual ice floes in aerial imagery with the aim to understand the frequency distribution of sea ice by their area.

Photo by Cassie Matias on Unsplash

Is It Hot Right Now?

Are temperatures in Australia right now anomalously warm or cold compared to the past? - A website that aims to demystify climate change by answering this question with simple visualisations and statistics. A personal initiative with fellow PhD colleagues Mat Lipson and James Goldie at the Climate Change Research Centre, UNSW."

Gap-filling of Ocean Temperature Timeseries

Probabilistic deep learning (bidirectional LSTMs) with monte-carlo dropout for filling up to three month long gaps in daily temperature observations around the Sydney harbour and the East coast of Australia. As part of a postdoctoral role in the UNSW coastal oceanography group, part of the Integrated Marine Observing System Australia.

Open Politics

Leveraging large language models (BERT) for natural language processing of social media posts by Australian MPs to detect corruption. In collaboration with Sean Johnson of Openpolitics.

Photo by Aditya Joshi on Unsplash

Australian Legislation Amendment Frequency

An analysis of the frequency of amendments of the twenty largest Federal legislative bills since their inception. This project involved the automated acquisition of the documents and natural language processing of nearly twelve gigabytes of text data. The project was led by A/Prof Lisa Crawford of the Law School, University of Sydney.

Photo by Tingey Injury Law Firm on Unsplash

Australian Legislation Amendment Frequency

Kelvin Wake Detection

We use fluid dynamics to simulate realistic images of the ocean surface with the triangular wave patterns behind moving objects (kelvin wakes) in water overlayed on wind generated waves. A deep learning (u-net) algorithm was trained to detect the presence absence of the kelvin wakes in the images. The prediction skill is further improved with the use of diffusion models to improve the signal to noise ratio between the kelvin wakes and the wind generated waves. This project was in collaboration with Naval Group Australia.

Photo by Martin Adams on Unsplash

Contact

Feel free to get in touch via my socials or fill out the contact form below to send me an email.

UNSW Data Science Hub, Anita Lawrence Building H13, East Wing, Level 1, RC1050, UNSW Sydney, NSW 2052