AI Tool Maps Ocean Currents in Unprecedented Detail

Researchers developed an AI network that can track temperature changes in satellite imagery to infer ocean current patterns.

Apr. 15, 2026 at 9:27pm

Got story updates? Submit your updates here. ›

A highly textured, abstract painting in muted tones of blue, green, and gray, depicting sweeping geometric arcs, concentric circles, and precise spiral forms that conceptually represent the complex flows and patterns of ocean currents.An abstract visualization of the intricate, ever-shifting patterns of ocean currents, as mapped by a groundbreaking new AI tool.San Diego Today

Researchers at the University of California, San Diego have developed an AI tool called GOFlow that can map ocean currents across large areas with much greater detail than previous methods. The tool uses thermal satellite imagery to track temperature changes caused by underlying ocean currents, allowing it to infer current patterns. The researchers found that GOFlow's outputs aligned with data gathered by ships and other satellite observations, but provided even more granular detail on current movements.

Why it matters

Understanding ocean currents is crucial for a variety of applications, including weather forecasting, climate research, search-and-rescue operations, and oil spill response. This new AI-powered approach to mapping currents could significantly improve our ability to model and predict these important physical processes.

The details

The GOFlow neural network was trained on simulated ocean current data, then applied to real satellite imagery. By tracking temperature changes in the images, the AI was able to infer the underlying current patterns that caused those shifts. The researchers validated GOFlow's results against ship-based measurements and traditional satellite methods, finding that it provided greater detail than had previously been possible using only computer models.

  • The research was published in the journal Nature Geoscience on April 13, 2026.
  • The GOFlow tool was developed over the past few years by researchers at the University of California, San Diego.

The players

Luc Lenain

An oceanographer at UC San Diego's Scripps Institution of Oceanography and the first author of the study.

University of California, San Diego

The research institution where the GOFlow tool was developed.

Got photos? Submit your photos here. ›

What they’re saying

“We can now observe small, fast-changing ocean currents from space with much greater detail and frequency than before. Those currents are important because they help control how heat, carbon, nutrients and pollutants move through the ocean.”

— Luc Lenain, Oceanographer, UC San Diego

“These kinds of [AI] driven approaches are not replacing physics. Instead, AI is helping us extract physical information that is already present in satellite observations, but has been difficult to recover with traditional methods until now.”

— Luc Lenain, Oceanographer, UC San Diego

What’s next

The researchers say future work will incorporate additional satellite data to fill gaps caused by cloud cover, which can block a satellite's view of the ocean. The computer code for the GOFlow tool will also be made publicly available to help further research in this area.

The takeaway

This new AI-powered approach to mapping ocean currents represents a significant advancement in our ability to understand and model these critical physical processes. By extracting more detailed information from satellite imagery, GOFlow could lead to improved weather forecasting, climate modeling, and environmental monitoring capabilities.