VesselAI: Enabling Maritime Digitalization by Extreme-scale Analytics, AI and Digital Twins
MarineTraffic has joined a new EU-funded project that aims to leverage the enormous footprint of data generated by shipping to help unlock new possibilities for the maritime industry.
VesselAI kicked off on January 21, through a two-day virtual meeting that brought together the project’s consortium, consisting of 13 academic and industrial partners, an assembly of renowned actors in maritime and ICT domains.
By harnessing the power of data generated by shipping, VesselAI aims to explore new possibilities in a diverse range of current maritime applications for vessel traffic monitoring, ship energy system design and operation, autonomous shipping, fleet intelligence and route optimisation.
The ambitions envisaged by the project call for a number of challenges to be tackled; the targeted goals require intricate models for capturing the sophistication of modern vessel design and operation, and extreme-scale analytics for digesting vast amounts of heterogeneous data generated ceaselessly and under dynamic conditions in the maritime world. Recent progress in the fields of AI, HPC and Big Data processing will be exploited and further advanced to cater for the needs of the project. Digital twins, i.e., replicas of physical objects in the digital world, will serve as the core technology of the VesselAI solution, where data pertinent to maritime physical assets will be directly linked to their digital counterparts, producing highly accurate representations of unprecedented detail.
The potential of the VesselAI approach will be tested through four pilots in the maritime industry, tackling practical challenges for 1) global vessel traffic monitoring and management, 2) globally optimal ship energy system design, 3) short-sea autonomous shipping and 4) global fleet intelligence. MarineTraffic will oversee the execution of all pilots and will lead the developments in the first pilot which aims to demonstrate novel solutions for overcoming current limitations in scalability, speed and accuracy of vessel traffic prediction.
The VesselAI partners anticipate that the foreseen R&D activities will promote innovation beyond the scope of maritime digitalization. It is aspired that the outcomes of the project will serve as a paradigm to any domain that requires the efficient processing of distributed, extreme-scale streaming and batch data for building accurate data-driven models.
The project is funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 957237 and will last 36 months.