Tom Andersson
Data Scientist
Contact
Team
Links/Websites
General enquiries
For general enquiries please see our contact page.
Tom Andersson
Data Scientist
Biography
I am a Data Scientist at the BAS Artificial Intelligence Lab (AI Lab), supervised by Dr Scott Hosking and funded by the Alan Turing Institute’s AI for Science programme. In my work, I aim to enable scientific progress through the application of machine learning algorithms to large datasets from climate models, satellites, and in-situ stations. I am currently developing a deep learning-based Arctic sea ice forecasting AI, IceNet (pre-print available on EarthArXiV and more information on the project web page). I’m also co-supervising Ellie Krige (Cambridge University) for the MSci project: ‘Using IceNet to predict and understand the freeze-up and break-up dates of sea ice in Hudson Bay, Canada’.
Before BAS, I studied Information & Computer Engineering at Cambridge University, graduating with a double-first. My Master’s research at the Computational & Biological Learning Lab involved the development of a machine learning algorithm for automatically dating ice cores based on seasonally-dependent ice core chemicals. My thesis, ‘GPCore: A Gaussian Process Approach for Inferring Ice Core Chronologies’, was awarded a Distinction and is available on my GitHub.
Research interests
- Explainable deep learning for climate prediction
- Arctic sea ice forecasts for conservation and ecosystem management
- Combining gridded climate data with off-grid surface station observations
Collaborations
Alan Turing Institute (ATI) | Computational and Biological Learning Lab (CBL), University of Cambridge | UCL Centre for Artificial Intelligence | WWF
2021
- Pre-print. Tom R. Andersson, J. Scott Hosking, Maria Pérez-Ortiz, Brooks Paige, Andrew Elliott, Chris Russell, Stephen Law, Daniel C. Jones, Jeremy Wilkinson, Tony Phillips, Steffen Tietsche, Beena Sarojini, Eduardo Blanchard-Wrigglesworth, Yevgeny Aksenov, Rod Downie, Emily Shuckburgh (2021). Seasonal Arctic sea ice forecasting with probabilistic deep learning. EarthArXiV. https://doi.org/10.31223/X5430P
2020
- Peer-reviewed article. J. Turner, M. V. Guarino, J. Arnatt, B. Jena, G. J. Marshall, T. Phillips, C. C. Bajish, K. Clem, Z. Wang, T. Andersson, E. J. Murphy, R. Cavanagh (2020). Recent Decrease of Summer Sea Ice in the Weddell Sea, Antarctica, Geophysical Research Letters, doi:10.1029/2020GL087127
- Conference poster. T. Andersson, J. S. Hosking, M. Pérez-Ortiz, B. Paige, C. Russell, A. Elliott, S. Law, F. Agocs, J. Wilkinson, W. Tebbutt, E. Shuckburgh (2020). Deep learning for monthly Arctic sea ice concentration prediction presented at EGU General Assembly, 4-8 May 2020, doi:10.5194/egusphere-egu2020-15481
Publications from NERC Open Research Archive
2020
Turner, John ORCID record for John Turner, Guarino, Maria Vittoria ORCID record for Maria Vittoria Guarino, Arnatt, Jack, Jena, Babula, Marshall, Gareth J. ORCID record for Gareth J. Marshall, Phillips, Tony ORCID record for Tony Phillips, Bajish, C.C., Clem, Kyle, Wang, Zhaomin, Andersson, Tom ORCID record for Tom Andersson, Murphy, Eugene J. ORCID record for Eugene J. Murphy, Cavanagh, Rachel ORCID record for Rachel Cavanagh. (2020) Recent decrease of summer sea ice in the Weddell Sea, Antarctica. Geophysical Research Letters, 47. 10.1029/2020GL087127