Researchers have developed a new artificial intelligence method that reveals ocean surface currents in far greater detail than ever before, using thermal images from weather satellites already orbiting Earth. The breakthrough, called GOFLOW (Geostationary Ocean Flow), applies deep learning to satellite data to track how temperature patterns shift across the ocean, revealing currents that were previously invisible to traditional measurement methods .

Why Can't We Just Measure Ocean Currents the Old Way?

Ocean currents are fundamental to Earth's climate system. They transport heat around the globe, move carbon between the atmosphere and ocean depths, and redistribute nutrients that sustain marine life. Yet measuring currents over large ocean areas has remained stubbornly difficult .

Traditional satellite methods estimate currents indirectly by measuring variations in sea-surface height, but they typically image the same location only every 10 days or so, which is far too infrequent to track currents that can appear and disappear within hours. Ship-based measurements and coastal radar systems can capture rapid changes, but only for limited areas. This left a critical gap in observations at the scales where most of the ocean's vertical mixing occurs, when shallower waters are mixed deeper or vice versa .

The phenomena that drive vertical mixing can be less than 10 kilometers wide and transform in hours. Understanding vertical mixing matters because it powers key processes such as bringing nutrients up from depth to sustain marine ecosystems and pumping carbon dioxide from the surface to deeper waters where it can be stored long-term .

How Does GOFLOW Actually Work?

The method emerged when Luc Lenain, an oceanographer at UC San Diego's Scripps Institution of Oceanography, was examining thermal imagery from the geostationary satellite GOES-East in 2023. The satellite, primarily used for weather observation, produces images as frequently as every five minutes, showing swirls of warm and cool water evolving on the sea surface. Lenain noticed he could see the imprint of major currents like the Gulf Stream in these temperature patterns .

To convert visual observation into measurable data, the research team trained a neural network, a type of AI system inspired by how brains process information, to recognize how ocean surface temperature patterns shift and deform when pushed by underlying currents. The network learned from a high-resolution computer simulation of ocean circulation, which provided examples of temperature patterns and the water velocities that created them. By tracking how complex temperature patterns moved across consecutive satellite images, the trained network could infer the currents responsible for those changes .

"Weather satellites have been observing the ocean surface for years. The breakthrough was learning how to turn that time-lapse into hourly maps of currents by tracking how temperature patterns bend, stretch and move from one hour to the next," said Luc Lenain.

Luc Lenain, Oceanographer at UC San Diego's Scripps Institution of Oceanography

What Makes GOFLOW Different From Existing Methods?

The researchers tested GOFLOW's accuracy by comparing its output to velocities recorded by shipboard instruments in the Gulf Stream region in 2023, as well as standard satellite methods using ocean topography. GOFLOW's measurements agreed with the data collected with ships and traditional satellite techniques, and revealed much greater detail for smaller, faster-moving eddies and boundary layers where existing methods showed only blurred averages .

This newfound detail allowed the researchers to measure for the first time key statistical signatures of small, intense currents that drive vertical mixing in the ocean, patterns that previously had been documented only in computer simulations. The method works with existing geostationary satellites and does not require new instruments to be launched into space, making it immediately practical .

• Frequency of observation: GOFLOW produces hourly maps of currents, compared to traditional satellite methods that image the same location only every 10 days.
• Detail resolution: The AI method reveals much greater detail for smaller, faster-moving eddies and boundary layers where existing methods showed only blurred averages.
• Infrastructure requirements: GOFLOW works with existing weather satellites already in orbit, eliminating the need for expensive new space hardware.
• Measurement capability: For the first time, researchers can measure key signatures of small, intense currents using real observations rather than relying almost entirely on computer simulations.

How Could GOFLOW Change Climate Science?

Over time, GOFLOW could be incorporated directly into weather forecasts and climate models, potentially improving forecasts by resolving rapidly evolving currents that influence air-sea exchange, marine debris transport, and ocean ecosystems. The method could also help improve search-and-rescue operations and tracking of oil spills, which depend on accurate current predictions .

"This opens a range of exciting possibilities in physical oceanography that, until now, were largely accessible only through simulations. Using GOFLOW, we can now measure key signatures of these small, intense currents using real observations rather than relying almost entirely on simulations. This opens the door to testing long-standing ideas about how the ocean takes up heat and carbon," explained Luc Lenain.

Luc Lenain, Oceanographer at UC San Diego's Scripps Institution of Oceanography

The study was co-led by Lenain and Kaushik Srinivasan, a Scripps alumnus now at UCLA, and published in the journal Nature Geoscience. The project's two other co-authors, Roy Barkan of Tel Aviv University and Nick Pizzo of the University of Rhode Island, are also Scripps alumni. The work was supported by grants from the Office of Naval Research, NASA, and the European Research Council .

What Are the Current Limitations?

Cloud cover remains a significant limitation, since clouds block the thermal imagery GOFLOW relies on. Future work will incorporate other types of satellite data to fill in the gaps when clouds block satellites' views and achieve continuous coverage. The team is currently working to extend the method globally, and the study's data products and computer code are being made publicly available to support further research and applications .

This AI-driven approach to ocean observation represents a shift in how climate scientists can study one of Earth's most critical systems, turning decades of existing satellite data into actionable insights about the currents that regulate our planet's climate.