Shifts Project Launches to Study Distributional Shift for Decarbonization
DeepSea Technologies, an Al-led maritime technology company and energy efficiency expert, has partnered with other entities in the field of AI to launch the Shifts Project. The international collaboration of academic and industrial researchers is dedicated to studying and solving problems associated with distributional shift for real-world impact.
An example of distributional shift is found in maritime, where an entire ship data set moves over time as a result of biofouling. Marine fouling occurs when organisms attach themselves to underwater objects such as hulls, rope, pipes and building structures. This can lead to various operational inefficiencies, and vessel data can be used to calculate how to counter these.
Understanding how an entire ship data set shifts over time is crucial to accurately modeling vessels, which is the key to unlocking shipping’s decarbonization potential and minimizing fuel waste. The development of robust models is essential to enable the effective deployment of AI-based technology to reduce the carbon footprint of global supply chains.
Alongside DeepSea, the Shifts Project’s partners include the universities of Cambridge, Basel, Lausanne and HES-SO Valais-Wallis. The initiative brings together core machine learning (ML) researchers studying distributional shift with applied ML researchers, who work on tasks affected by distributional shift in the real world.
Maritime has been chosen as one of two case study challenges, the other being distributional shift in relation to the treatment of multiple sclerosis.
Learn more here.