An innovative solution to revolutionise the speed and ease of seabed mapping in real-time utilising Artificial Intelligence (AI) has been developed thanks to a partnership between the University of East Anglia’s (UEA) School of Computing Sciences and GeoAcoustics Ltd.
Seabed mapping is used to produce a bathymetric (or water depth) profile of a given area of seabed using sonar technology. Sonar works by sending sound pulses into the water and measuring the echoes reflected from the seabed and any underwater structures that may be present. However, many unwanted data points are also generated and these need to be filtered out after the survey to produce a true representation of the seabed profile. This is a resource-intensive, expensive, and time-consuming task, often taking an experienced surveyor days or even weeks to complete. Which is why, as of this year, over three-quarters of the planet’s seabed remains unmapped.
GeoAcoustics Ltd, based in Great Yarmouth and a manufacturer of high-quality sonar equipment for seabed mapping, approached UEA’s Research and Innovation Team, who put them in contact with academics from the School of Computing Sciences. A feasibility study was first undertaken to see if AI technology could automatically remove unwanted noise from sonar data, which was carried out by two MSc Computing Science students, supervised by Dr Wenjia Wang and Dr Ben Milner, and a team from GeoAcoustics.
Following encouraging results, further research and development grants were awarded - one an Enabling Innovation: Research to Application (EIRA) award and one an Innovate UK Knowledge Transfer Partnership (KTP). These enabled an AI module to be developed which was then evaluated using various benchmark data sets and sea trials.
These trials established that the AI was able to produce accurate and consistent results comparable to that of an experienced surveyor, without needing any human intervention and operating at a fraction of the time. The AI module was integrated into the company’s existing software and is capable of processing survey data in real-time, saving days or weeks of post-processing by trained human users.
Dr Wenjia Wang, Associate Professor of Artificial Intelligence and the KTP project lead at UEA, said:
“This successful project represents an acknowledgment not only of the cutting-edge knowledge and skills of staff and students within UEA’s School of Computing Science in being approached by the company initially, but also the ways in which we can further develop relationships with businesses to produce innovative real-world solutions that are recognised nationally and internationally as sector leading.”
“As the project leader, I would like to thank all the team members from UEA, GeoAcoustics, and our Research Assistant, Dr Danny Websdale, for their hard work during the project, as well as the UEA Research and Innovation team and the Knowledge Transfer Network at Innovate UK for their valuable support. Without all these, we wouldn’t have been able to complete this project successfully.”
The new system has since been released by GeoAcoustics Ltd to their customers and has put the company into a world-leading position in their industry.
Dr Danny Websdale, the KTP Senior Research Associate at UEA for the duration of the AI development project, and now an AI/ML Research Scientist at GeoAcoustics Ltd, said:
“Designing an AI system that can process and quality control sonar data was a challenging process over the course of two and a half years, but together with the project team we were able to meet the project’s intended goals and even exceed them by developing a system that provides real-time data on board the survey vessel, which is a unique capability that improves data quality while saving GeoAcoustics’ customers time and money.”
In light of the success of this project, which was graded ‘Outstanding’ by Innovate UK, a non-departmental public body sponsored by the Department for Science, Innovation and Technology (DSIT), UEA has been named as one of three finalists in the Technical Excellence category at the national KTP Awards, with winners announced on Wednesday 18 October.
UEA’s industrial partner, GeoAcoustics, have also met with global recognition having been awarded with the first ever King’s Award for Enterprise in the International Trade category.
Dr Richard Dowdeswell, Chief Operating Officer at GeoAcoustics Ltd, said:
“The AI system was integrated in our flagship seabed mapping product and provided to our customers as a free update. So far, the feedback has been positive, and we are delighted with how the Knowledge Transfer Partnership turned out, as well as the excellent collaboration with Dr Danny Websdale and the School of Computing Sciences at UEA.”
As well as being a potential source of revenue generation, the School of Computing Science’s work on the seabed mapping project has brought their expertise to the attention of other businesses. This includes a partnership with a London based company to develop an AI solution to monitor and predict the conditions of babies during their birth, for which they have been awarded a grant totalling more than £500k from Innovate UK, and a collaboration with a Norwich business to develop an AI technique to rapidly check the legitimacy of identification papers.
The School remains in the process of dealing with discussions and applications from several other interested companies for future projects.
Prof Beatriz de la Iglesia, Head of the School of Computing Sciences at UEA, said:
“Our MSc Computing Science students aren’t just here to learn theory, they are encouraged and supported throughout their study to work on projects that use the latest knowledge to find innovative solutions across disciplines and industries.
“This latest success with AI follows on from our recent announcement of a partnership with Google to integrate knowledge and skills associated with their TensorFLow.JS system into the modules relating to AI and Machine Learning across our Computing Science courses from September 2023. In practice, this means students graduating from UEA will stand out from the crowd, equipped with cutting-edge skills and knowledge that are only going to grow in importance as businesses adapt to a changing world.”
Computing Science students will be among the first in the country to be taught skills in artificial intelligence based on TensorFlow.js, as part of a new collaboration between the University and Google.Read more
The University's School of Computing Sciences has had its MSc in Cyber Security officially recognised with full certification by the UK National Cyber Security Centre (NCSC).Read more
UEAnonymous, a talented team of CMP students, made it to the finals of the Cyber 9/12 Strategy competition one of just 17 teams selected of more than 120 applicants.Read more