I’m a machine learning researcher based in the Artificial Intelligence (AI) lab at BAS. My research focuses on using machine learning to monitor and detect wildlife, particularly using satellite and drone imagery. I work closely with the Wildlife from Space research group, developing image algorithms to automatically count wildlife in very high resolution satellite imagery. For my PhD I developed a convolutional neural network to detect wandering albatrosses in 31-cm resolution WorldView-3 imagery – work which is being extended on in the Darwin Plus Albatrosses from Space project. Since joining BAS i have been involved with the Walrus from Space research, detecting walrus haulouts using lower resolution Sentinel-2 imagery. I am also involved with a WWF funded project using IceNet sea ice forecasts to predict risks to arctic wildlife. In this we are using GPS collar data to establish links between sea ice conditions and the timing and location of caribou migrations in the Coronation Gulf, to develop a Conservation Early Warning and Alert System which can inform local ecologists.

Research interests

Collaborations

Publications from NERC Open Research Archive

• Clarke, P., Cubaynes, H., Bowler, E., Jackson, J., Attard, M., Stockin, K., & Carlyon, K. (2025). Point annotation dataset of stranded whale and dolphin species identified in very high-resolution optical and SAR satellite imagery along offshore islands of New Zealand and Tasmania between 2018-2023 (Version 1.0) [Data set]. NERC EDS UK Polar Data Centre. https://doi.org/10.5285/b26c3a3d-73c8-4500-9a23-696011c20a45

• 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

• Panigada, V., Bowler, E., & Fretwell, P. (2024). Annotated dataset of wandering albatrosses detected in Very High Resolution (VHR) satellite imagery of South Georgia, Crozet Islands and Kerguelen Islands, from 2015-2017. (Version 1.0) [Data set]. NERC EDS UK Polar Data Centre. https://doi.org/10.5285/276367fa-03dd-4c80-9f7b-7652eb1664d9

1. AI for Earth Observation

   The AI for Earth Observation project develops machine learning tools to detect icebergs, sea ice, and wildlife from satellite imagery.

   Read more of: AI for Earth Observation

   

2. South Georgia seabirds from space

   This project tests whether satellite imagery can be used to monitor breeding seabirds across the island group.

   Read more of: South Georgia seabirds from space

   

3. 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

   

4. Digital Twins of the Polar Regions

   This project is developing digital twins of Antarctic and Arctic environments and resources. A digital twin makes it possible to test “what if” questions far more quickly than traditional computer models.

   Read more of: Digital Twins of the Polar Regions

   

5. Albatrosses from Space

   Albatrosses face multiple threats to their long-term survival. Using very high-resolution satellites, we are able to estimate the number of breeding pairs in remote locations.

   Read more of: Albatrosses from Space

   

7. Machine Learning for Sea Ice Forecasting

   IceNet is a deep learning system that forecasts Arctic sea ice. The system is trained on climate simulations and observational data. It outperforms state-of-the-art dynamical models, especially for extreme sea ice events.

   Read more of: Machine Learning for Sea Ice Forecasting