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

• Bowler, E., Byrne, J., Leclerc, L., Roberto-Charron, A., Rogers, M., Cavanagh, R., Harasimo, J., Lancaster, M., Chan, R., Strickson, O., Wilkinson, J., Downie, R., Hosking, J., & Andersson, T. (2025). Pan-Arctic 93-day sea ice concentration forecasts from the IceNet model and mappings between sea ice concentration and Dolphin and Union caribou sea ice crossing-start times (Version 1.0) [Data set]. NERC EDS UK Polar Data Centre. https://doi.org/10.5285/8738b3cb-52c7-4b36-aa6d-6e15c0b46ba4

• Andersson, T., & Hosking, J. (2021). Forecasts, neural networks, and results from the paper: ‘Seasonal Arctic sea ice forecasting with probabilistic deep learning’ (Version 1.0) [Data set]. NERC EDS UK Polar Data Centre. https://doi.org/10.5285/71820e7d-c628-4e32-969f-464b7efb187c

1. AI for smart conservation

   The AI for smart conservation project combines sea ice forecasts, satellite data, and GPS tracking to create early-warning systems for Arctic wildlife.

   Read more of: AI for smart conservation

   

2. Tracking Antarctica’s Ice Fluctuations

   The recent extreme swings in Antarctic sea ice extent emphasise the need to increase our knowledge of the drivers and climate implications of Antarctic sea ice loss.

   Read more of: Tracking Antarctica’s Ice Fluctuations

   

1. Predicting September 2021 Arctic sea ice using artificial intelligence

   Tom Andersson, a data scientist at British Antarctic Survey Artificial Intelligence (AI) Lab, shares the latest predictions from a new Arctic sea ice forecasting AI tool as this year’s Arctic […]

   Read more of: Predicting September 2021 Arctic sea ice using artificial intelligence

   

1. Artificial intelligence to help predict Arctic sea ice loss

   A new AI (artificial intelligence) tool is set to enable scientists to more accurately forecast Arctic sea ice conditions months into the future. The improved predictions could underpin new early-warning […]

   Read more of: Artificial intelligence to help predict Arctic sea ice loss