AI for Earth Observation

Recent increases in the spatial coverage and temporal resolution of satellite imagery, is opening new opportunities to rapidly detect environmental objects of interest e.g. iceberg position, ice floes, sea ice extent and wildlife from space, with greater positional accuracy.

Our team are developing supervised and semi-supervised multimodal machine learning techniques to automatically detect these features. We use a wealth of satellite data sources, primarily Synthetic Aperture Radar (SAR) and multispectral imagery from the the Copernicus, MODIS and Planet datastores as well as Worldview 3 and other commercial products.

This detection work is closely linked to downstream application projects, from aiding in-ice navigation of the Sir David Attenborough research vessel, iceberg tracking and validation of the passive microwave-derived sea ice concentration record. We closely collaborate with a range of national and internation partners, including the Alan Turing Institute, European Space Agency, National Snow and Ice Centre (US) and the Norwegian Ice Service.

Recent publications:

Rogers, M.S., Fox, M., Fleming, A., van Zeeland, L., Wilkinson, J. and Hosking, J.S., 2024. Sea ice detection using concurrent multispectral and synthetic aperture radar imagery. Remote Sensing of Environment, 305, p.114073. https://doi.org/10.1016/j.rse.2024.114073 

Evans, B., Faul, A., Fleming, A., Vaughan, D.G. and Hosking, J.S., 2023. Unsupervised machine learning detection of iceberg populations within sea ice from dual-polarisation SAR imagery. Remote Sensing of Environment, 297, p.113780. https://doi.org/10.1016/j.rse.2023.113780