Monitoring icebergs in satellite images using artificial intelligence
The Arctic is a unique, but fragile ecosystem that is increasingly threatened by changes to our climate. The reduction in sea ice across the Arctic has driven an increase in navigating these waters, especially through the North West and North East Passages which promise large reductions in travel.
In this project, we will develop novel machine learning and computer vision techniques for identifying small icebergs in satellite radar images. Algorithms will be developed and provide a valuable aid to navigation in ice infested waters. Furthermore, the output results will allow climate and ocean circulation studies.
We will use freely available European Space Agency (ESA) data collected by the Synthetic Aperture Radar (SAR) onboard the Sentinel-1 satellites. The starting point is an image filter (the iDPolRAD) developed by Dr. Marino. The algorithm allows to increase the contrast between icebergs and sea ice, however it does not currently run automatically. The student will automate the detector designing an appropriate machine learning and artificial intelligence (computer vision) methodology able to identify icebergs in filtered images.
This PhD project is fully funded by NERC through the IAPETUS Doctoral Training Centre. We welcome applications form EU Students. This is a competition funded PhD.
A first or upper second class degree in Engineering, Geosciences, Mathematics or in closely related areas, and enthusiasm for innovation. It would be beneficial for applicants to have experience with a programming language (eg. Python, Matlab, C).
Applicants are welcome to contact Dr. Armando Marino for further information ([email protected]).
Interviews will be held between the 17th and 19th of July.
How to apply:
Please apply sending the following documents to Dr. Marino [email protected] :
A cover letter
Transcript of the degrees
Reference letters or contact details (email) of two referees