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

点击翻译按钮获取中文摘要

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.