How AI is cleaning up our Oceans.
For some time, AI has been lauded as a game-changer for many industries. It has huge potential in a number of applications, but right now, every industry is grappling with how to become more sustainable. It’s here that AI may help reap the best rewards. Vaarst, a technology business driving the future of marine robotics is using 3D vision and machine learning to help improve efficiency and ease the transition to greener, renewable energy sources, and ways of working in offshore environments.
Offshore wind is a particular focus in governments’ energy strategies, given the plummeting costs and the fact turbines can now be placed ever further from coastlines. As a result, the GWEC predicts significant growth over the next five years, with an estimated compound annual growth rate of nearly 32 per cent, compared to just 0.3 per cent with land-based turbines.
However, in much the same way as energy companies survey and maintain oil and gas subsea assets, wind farm cables, foundations and all other components of the turbines also need continuous monitoring and maintenance.
Understanding the subsea environment
The wind turbines that we see are, in a sense, just the tip of the iceberg. While they do all the hard work harvesting the wind power, the subsea structures, cables and assets are also critical and require ongoing maintenance. An underwater ROV (remotely-operated vehicle) is used to regularly monitor these subsea assets, and this is carried from a large survey vessel, often crewed by up to 60 people from engineers and robot drivers to cooks and cleaners. These vessels can cost £1 million to £10 million per month to operate, depending on the job, and generate 275,000 tonnes of carbon emissions in their lifetime.
As asset data collected from the underwater ROVs is too large to be transmitted via satelites, it is then manually analysed aboard these vessels, to determine issues and potential threats, such as damage or marine growth, which can take many hours. Hours where the survey vessel remains at sea.
There are now far greener and more cost-effective ways of doing this – and they involve leveraging sophisticated robotics and AI.
The use of robotics in the energy industry isn’t new – as far as industries go, they were relatively early adopters – but the use of more advanced technologies, such as increasingly autonomous ROVs, machine learning, and simultaneous localisation and mapping (SLAM), present an opportunity that too few are seizing.
Automation and AI
By bringing SLAM technology to the subsea environment and coupling it with machine learning and autonomy, Vaarst is changing the way the energy industry works in a very real way. Integrating SubSLAM technology on an ROV can make them autonomous and enables operators to capture 3D point cloud data which can quickly be transmitted via a low bandwidth data-sharing platform to shore.
Enabling this work to be completed much more quickly and remotely on land, means energy companies require fewer people at sea, and they can operate on smaller, more carbon-efficient vessels. Not only does this speed the energy transition, it also reduces the adverse environmental impact of the transition itself.
There is an abundance of improvements and efficiencies to be found in the energy transition space by using AI. With the evolution of autonomous marine robotic systems, ROV supervisors can be almost entirely hands-off, with the vehicles operating themselves. Enabling significant wins from both a commercial and environmental perspective.
Vaarst’s focus is currently on marine operations, however, there are some clear opportunities to apply the company’s technology in other equally challenging environments.
The marine robotics industry is ripe for innovation and AI is undoubtedly going to change the landscape, ensuring that the transition to green energy involves greener processes. As we continue to build and innovate, there is no doubt that the lessons we learn on the seabed will drive innovation in AI into new and exciting territories.
Author:
You can read all insights from techUK's AI Week here