📣 Help Shape the Future of UKRI's Gateway to Research (GtR)

We're improving UKRI's Gateway to Research and are seeking your input! If you would be interested in being interviewed about the improvements we're making and to have your say about how we can make GtR more user-friendly, impactful, and effective for the Research and Innovation community, please email gateway@ukri.org.

Commercialising a system to improve maritime safety with artificially intelligent iceberg and sea ice detection

Lead Research Organisation: Lancaster University
Department Name: Physics

Abstract

By lowering the quantity of ice in the Arctic Circle, climate change is creating additional shipping routes. However, these routes present risk due to the prevalence of icebergs and first-year sea ice.

There are approximately 2-3 iceberg-ship incidents a year in the Northern Hemisphere, despite the modern radar technology onboard ships (B. Hill, Institute for Ocean Technology). Several relatively recent incidents have involved tourist cruises having to abandon ship e.g. MS Explorer which sank (2007), and MS Fram (2007), or severe damage to fishing vessels (e.g. Sparta, 2011). Avoiding icebergs by travelling hundreds of miles is also potentially costly and so it is important to have an up-to-date map of their locations. In addition to this, false alarms of icebergs detected on radar, which are actually ships with no/inactive transponders are also a problem. We are therefore motivated to provide an additional safety measure by tracking icebergs on satellite imaging.

The vision of this grant is to further develop and apply our system which uses artificial intelligence combined with satellite imaging to detect and track icebergs and sea ice in shipping routes, in any cloud condition. The ultimate goal is to improve maritime safety by turning this into a commercial product.

Publications

10 25 50
 
Description Lancaster's Impact Acceleration Account (an institutional award from UKRI): Tech Catalyst
Amount £8,800 (GBP)
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 03/2025 
End 05/2025
 
Title A tool for the automatic detection of icebergs using machine learning 
Description The iceberg detection system works by training a convolutional neural network (CNN) on icebergs in ESA (European Space Agency) Sentinel 1 polarised synthetic aperture radar (SAR) satellite images, using ESA Sentinel 2 visual images for the ground truth. The CNN can then be run on SAR data only, to detect icebergs in any cloud cover or lighting conditions. It is highly successful providing 80-90% accuracy. This was based on a system we previously used for astrophysics research funded by STFC. The details of this system will be published in a journal within 2025. 
Type Of Material Improvements to research infrastructure 
Year Produced 2024 
Provided To Others? No  
Impact While do not yet have tangible impacts, we expect these to come as we work with potential stakeholders. We are participating in the Innovate UK ICURe journey, having already completed the Engage and Discover programmes. The purpose of this is to commercialise the iceberg detection project. For this we adopted the name IceHunter and created a website, professionally designed by Brilliant Red Digital and funded by InnovateUK https://icehunter.co/ . During this training we were tasked with speaking to 30 potential stakeholders. We achieved this and more through attending trade fairs, sending cold emails, and taking advice from our mentor who is an officer on the Sir David Attenborough research vessel. We hope to perform live Antarctic tests of our algorithm using this ship. Example potential stakeholders we have had discussions with are: the Royal Navy; US Coast Guard; the ice monitoring services for the US, Canada, Norway, and Denmark/Greenland; British Antarctic Survey; and Digital Earth Solutions (Spanish company). At the Oceanology2024 trade fair we spoke with representatives from Rutter (Canadian ship radar manufacturer), we are in discussions about a collaboration with them. 
URL https://icehunter.co/
 
Description Discussions with over 30 potential stakeholders 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact I am participating in the Innovate UK ICURe journey, having already completed the Engage and Discover programmes. The purpose of this is to commercialise the iceberg detection project. For this we adopted the name IceHunter and created a website, professionally designed by Brilliant Red Digital and funded by InnovateUK https://icehunter.co/ . During this training we were tasked with speaking to 30 potential stakeholders. We achieved this and more through attending trade fairs, sending cold emails, and taking advice from our mentor who is an officer on the Sir David Attenborough research vessel. We hope to perform live Antarctic tests of our algorithm using this ship.

Example potential stakeholders we have had discussions with are: the Royal Navy; US Coast Guard; the ice monitoring services for the US, Canada, Norway, and Denmark/Greenland; British Antarctic Survey; and Digital Earth Solutions (Spanish company). At the Oceanology2024 trade fair we spoke with representatives from Rutter (Canadian ship radar manufacturer), we are in discussions about a collaboration with them.
Year(s) Of Engagement Activity 2024
URL https://icehunter.co/
 
Description Magazine article for Ship Technology Global 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact We made the front cover of Ship Technology Global who wrote an article about our iceberg detection system.
Year(s) Of Engagement Activity 2024
URL https://ship.nridigital.com/ship_dec24/issue_92
 
Description PI gave a talk to the Nautical Institute about iceberg detection with AI 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact PI gave an online talk to the Nautical Institute about iceberg detection with AI. This was viewed by an international audience of ships' officers etc, including a number of those working in the polar regions. This sparked a lively discussion and emails that followed and we discovered more information about the problems ice navigators face and how we could solve them. It has also put us in touch with potential funding opportunities in AI.
Year(s) Of Engagement Activity 2024