The water looks inviting, the kids are already running for the shore, and there’s a calm patch between the breaking waves that looks like the perfect place to swim. It could be the most dangerous spot on the beach.
Rip currents remain one of Australia’s deadliest coastal hazards. They contributed to 47% of the 66 beach drowning deaths recorded in the 2026 National Drowning Report. Most of us know rips are dangerous, but Surf Life Saving Australia (SLSA) research shows a worrying gap between confidence and ability: 45% of Australians think they can spot a rip, yet only 16% can correctly identify one.
Meet RipEye
UNSW researchers, working with SLSA, have developed RipEye. It’s an AI-powered mobile tool that can analyse a photo of the surf and, within seconds, show where rip currents may be.
RipEye has two parts. AI Live Scan identifies potential rips in beach images. Spot the Rip is an interactive game that teaches people to find rips for themselves.
The tool will be trialled with selected Surf Life Saving clubs this summer. The longer-term aim is to use it in public beach safety education and patrol operations, and eventually to release it to the public. It’s part of an Australian Research Council Linkage Project led by UNSW.
Dr Mandana Ghanavati, Senior Researcher at UNSW’s School of Civil and Environmental Engineering, led RipEye’s development. Her focus was making it fast, accessible and practical on a real beach.
“Rip currents are dynamic coastal hazards, and beach conditions can change rapidly,” she says. For the tool to be useful, she adds, “accuracy alone isn’t enough. The system has to process information efficiently and deliver results while those conditions are still relevant.
“We wanted to make advanced AI simple and accessible. By combining AI-assisted detection with interactive learning, we want to give people the knowledge and tools to make safer decisions before entering the water – without replacing human judgement.”
Can you beat AI at spotting a rip?
In Spot the Rip, players work through levels, picking out rip currents in beach images and then comparing their answers with the AI’s. Feedback and tips along the way help them sharpen their eye.
“Rather than simply relying on technology to identify the rips, we wanted to use AI to help people develop the skills to recognise one for themselves,” Dr Ghanavati says.
The game was designed with the groups most at risk of drowning in mind. These include young men, international visitors and culturally and linguistically diverse communities. It works on mobile devices and comes in 11 languages, and SLSA will test it with these groups this summer.
“Gamification makes learning more engaging, particularly for younger audiences,” Dr Ghanavati says. “We hope to break down the barrier to beach safety education no matter where people may be.”
Teaching AI to see a rip
Rips are strong, narrow currents that flow away from the shore and can quickly carry swimmers into deeper water. They’re notoriously hard to identify.
RipEye draws on more than 25 years of beach monitoring at UNSW’s Water Research Laboratory (WRL) in Manly Vale, which holds one of the world’s largest databases of beach imagery. SLSA members added their own rip current images, along with expert and local knowledge.
PhD candidate Shenyang Qian, from UNSW’s School of Computer Science and Engineering, used those images to train the model.
“I spent the first 12 months of my research mining and annotating through more than 10,000 images of rip currents at different beaches to develop and train the model,” he says. “Through this enormous and laborious task, RipEye has learnt to detect rip currents and to adapt its knowledge to changing conditions.”
RipEye correctly detects a rip around 80% of the time. Scientia Associate Professor Mitchell Harley, a coastal monitoring expert at WRL, stresses that no detection system is right every time. The technology doesn’t guarantee that an area of water is safe.
“Australia is a massive island and depending on where you are, the coastline can be very different,” he says. “Rips do not always look the same, so to be able to recognise them across different beaches and conditions can be challenging.”
The model was built mainly on Australian beach data, but early tests on beaches in Vietnam and California have been promising.
The wider UNSW team includes:
- Scientia Professor Toby Walsh and Associate Professor Yang Song (School of Computer Science and Engineering)
- Associate Professor Amy Peden (School of Population Health)
- Professor Rob Brander, better known as Dr Rip, and Dr Jaz Lawes (School of Biological, Earth and Environmental Sciences)
Could AI make us overconfident?
SLSA members are already testing RipEye at selected locations. They want to see how it could complement existing patrol procedures, such as helping lifesavers decide where to put the red and yellow flags. SLSA plans to use it to train members and inform patrol operations.
The researchers are also asking a harder question: could AI help make people too confident, or too reliant on technology?
“How people interpret, trust and interact with AI is equally important, yet often overlooked in early warning systems,” Dr Ghanavati says. “A key part of our research is understanding how AI assistance influences people’s decisions and behaviour, including whether it improves hazard awareness or creates a false sense of confidence.”
Why it matters
Australia has around 11,000 mainland beaches, far too many to patrol all year round. The project has a particular focus on unpatrolled beaches. It supports the Australian Water Safety Strategy 2030 goal of cutting drowning deaths by 50% by 2030.
“You can’t avoid a hazard if you can’t see it,” says Dr Jaz Lawes, SLSA’s National Research Manager and an Adjunct Senior Lecturer at UNSW. “Rip currents are the number one coastal hazard globally … but they can be extremely difficult to identify.
“That’s why RipEye is so important. It can help Surf Life Saving turn something that is often difficult to see into tangible information people can understand and use to educate, inform and make safer choices for themselves and their loved ones.”
A/Prof Harley agrees. “If AI can help people and professionals better identify the danger in hazards right in front of them – while encouraging them to learn what to look for themselves – it could become another tool in helping beachgoers make safer choices before entering the water.”
How to spot a rip
Before you get in the water, Surf Life Saving Australia’s advice is to STOP to check for rips, LOOK for other dangers and PLAN how to stay safe. The key signs of a rip are:
- Deeper and/or darker water
- Fewer breaking waves
- Sandy-coloured water extending beyond the surf zone
- Debris or seaweed
- Significant water movement
It can be easier to look for where the waves are breaking consistently, then look to either side, where they don’t. Those areas are rip currents.
If you’re caught in a rip
- Stay calm and conserve your energy.
- Seek help. Raise your arm and call out.
- Float with the current. It may return you to a shallow sandbank.
- Swim parallel to the beach or towards the breaking waves.
Always swim at a patrolled beach, between the red and yellow flags.
About Surf Life Saving Australia
Surf Life Saving Australia is the nation’s peak coastal water safety, drowning prevention and rescue authority. With more than 200,000 members and 316 affiliated clubs, it’s the largest volunteer movement of its kind in the world. Since the first clubs formed on Sydney’s ocean beaches in 1907, surf lifesavers have rescued more than 715,000 people.
Surf Life Saving is a not-for-profit, funded by community donations, fundraising, corporate sponsorship and government grants. Its vision is zero preventable deaths in Australian waters.
- Check your beach: Look up beaches and rip safety advice at beachsafe.org.au, or download the Beachsafe app for iOS and Android.
- Volunteer: Join your local surf club at sls.com.au/join.
- Donate: As little as $20 can help save a life. Give through the Surf Life Saving Foundation.
- Find out more: sls.com.au
