A new system using artificial intelligence to accurately model how sound waves travel underwater could help reduce the impact of noise pollution on marine life.

Researchers from the University of Glasgow, alongside academics from the University of British Columbia in Canada, are behind the development of the technology.

The loud sounds created by manmade tech, including the propellers of cargo ships and the construction and operation of offshore wind farms, have been shown to have negative effects on a wide range of sea life.

For instance, the noise—which can reflect off the surface of the ocean, the seabed, and everything in between—can disrupt migration patterns or marine animals like dolphins and whales, and affect their ability to navigate by echolocation.

Accurately modelling the physics of the sound waves’ movements and interactions underwater is currently difficult without using a large amount of compute. Large-scale projects can take days of computing time to fully model the spread of noise through water.

The researchers investigated if deep neural networks could help tackle this challenge, and bring future systems closer to providing real-time feedback on the propagation of sound waves which could be used in the real world.

To do so, they built and tested their acoustic wave modelling system using neural network architecture, known as a convolutional recurrent autoencoder network, or “CRAN.”

The CRAN works by compressing complex modelling data into a more simplified form. An AI model known as a long short-term memory network then analyses the model based on what it has previously learned about underwater physics, creating predictions of how underwater sound waves spread over time.

According to the researchers, when the system was asked to predict how sound waves would behave in 15 new underwater scenarios that it hadn’t seen before, it was capable of accurately predicting wave propagation with less than 10% error.

Further, it was said that the system can provide results much faster than conventional modelling processes.

In the future, the system could be used to help industries such as shipping and renewables to make better-informed decisions about the effect of their activities on the undersea environment.

Recommended reading

• Scots Uni Playing Key Role in Autonomous Network Standards
• Glasgow Uni Researchers Build “Self-eating” Rocket Engine
• Glasgow Uni Research Aims to Boost New Voice Recognition Tech

Dr Wrik Mallik, of the University of Glasgow’s James Watt School of Engineering, is the corresponding author of the paper published on the research. He said: “These are really encouraging results, which clearly show the potential deep neural networks hold for predicting the complex physics of underwater ocean acoustic propagation.

“Waiting seconds instead of days to produce models of underwater acoustic scattering would be a significant breakthrough for this field of research, and this paper shows how we’ve taken one step closer to making that happen.

“Having real-time feedback on devices which could be used out on the ocean would allow much more effective planning to help mitigate the effects of noise pollution on marine animals.

“Although this early-stage study demonstrated the effectiveness of the CRAN on two-dimensional data, we’re confident that the technology can be scaled up to meet the challenge of dealing with fully 3D acoustic simulations.

“We’ve already begun work to further develop and refine the system, and we plan to test it in real-world situations in the months ahead.”

The team’s paper, Deep neural network for learning wave scattering and interference of underwater acoustics, is published in Physics of Fluids.