Biography

I am an ML Research Scientist at the BAS AI Lab, funded by The Alan Turing Institute. My research focuses on using ML algorithms that leverage large datasets from climate models, satellites, and in-situ stations to develop tools for monitoring and adapting to climate change. In my previous work, I have used deep learning with methods from uncertainty quantification, interpretability, and active learning to drive scientific progress and support decision-making.

I currently specialise in the use of neural processes (NPs) in environmental sciences. NPs are versatile meta-learning models that can be applied to tasks such as downscaling, imputing missing satellite data, forecasting, and sensor placement. To accelerate research in this area, I am leading the development of DeepSensor, an open-source Python package. My latest journal paper applies active learning with NPs using DeepSensor to find optimal sensor locations for monitoring weather in Antarctica.

Another significant area of my research involves the development of IceNet, a deep learning system for sea ice forecasting, for which I was awarded the World Meteorological Organization (WMO)’s Young Scientist of the Year Award. Building upon the initial IceNet study published in Nature Communications, I am now PI on a WWF-funded project that explores the use of IceNet’s forecasts to inform decision-making in wildlife conservation.

Prior to joining BAS, I studied Information & Computer Engineering at Cambridge University. For my Master’s project at the Computational & Biological Learning Lab, I designed a machine learning algorithm for automatically dating ice cores. My thesis, ‘GPCore: A Gaussian Process Approach for Inferring Ice Core Chronologies’, is available on my GitHub.

Supervisory positions:

• Co-supervisor of Jonas Scholz’s Cambridge University MPhil project (2023), ‘Sim2Real with Neural Processes’
• Co-supervisor of Ellie Krige’s Cambridge University MSci project (2021), ‘Using IceNet to predict and understand the freeze-up and break-up dates of sea ice in Hudson Bay, Canada’

Research interests

• Neural processes in environmental sciences
• Active learning for sensor placement
• Deep learning for sea ice forecasting
• Open-source scientific software development
• Explainability in environmental ML
• AI for smart wildlife conservation

Collaborations

Alan Turing Institute (ATI) | Computational and Biological Learning Lab (CBL), University of Cambridge | UCL Centre for Artificial Intelligence | WWF | Government of Nunavut