Researchers have recently developed artificial intelligence capable of reconstructing high-resolution ocean currents from satellite images, which were previously impossible to observe. This breakthrough could be invaluable for better understanding how the oceans function and anticipating extreme weather events.
An artificial intelligence system that provides invaluable assistance to scientists. It’s no secret that Earth is more than 70% covered in water, a characteristic that has earned it the nickname « Blue Planet. » This resource, essential to life, exists in several forms. The vast majority is saltwater, which represents nearly 97% of the water on the planet and is found primarily in the oceans and seas.
Conversely, freshwater represents only about 3% of this resource and is distributed among glaciers, groundwater, lakes, and rivers. A recent study published in the journal Nature Geoscience focused on the rapid currents found particularly in the oceans—movements that may seem invisible from space but nevertheless play a major role in regulating Earth’s climate.
This research has led to a significant breakthrough, offering researchers the ability to observe these phenomena with unprecedented precision. They developed GOFLOW, an AI system capable of reconstructing high-resolution ocean currents directly from satellite imagery. This allows them to study small-scale ocean dynamics that influence meteorology, climate change, and the exchange of heat and gases between the ocean and the atmosphere.
An AI system that reveals previously inaccessible data
The oceans play a major role in regulating Earth’s climate. They transport immense quantities of heat, carbon , and energy across the globe. Yet, many of these essential processes occur on scales of a few tens of kilometers, or even less, making them virtually impossible to observe with current technologies.
“The ocean is one of the most important components of Earth’s climate system, yet many of the processes that govern it occur on spatial and temporal scales that are extremely difficult to measure directly ,” explained Roy Barkan, a professor, physical oceanographer, and fluid dynamics specialist at Tel Aviv University. To try to overcome this limitation, the researchers developed an artificial intelligence system capable of analyzing sequences of infrared satellite images by capturing sea surface temperatures in order to reconstruct the horizontal movements of ocean waters.
This technology also makes it possible to identify subtle and particularly complex flow patterns that were previously impossible to detect. « Thanks to GOFLOW, we can now extract dynamic information from satellite observations that was previously inaccessible, thus revealing the mechanisms that govern ocean mixing, heat transport, and gas exchange with the atmosphere, » said the study’s lead author, before adding: « Faced with accelerating climate change, the ability to observe these processes at a fine scale is essential to understanding the phenomenon as a whole. »
A tool that could help to better anticipate extreme weather events
Thanks to this system, researchers have already been able to identify remarkably dynamic processes occurring on scales smaller than 30 kilometers within the Gulf Stream. It also provides information that was previously beyond the reach of oceanographers, including the first direct satellite measurements of horizontal ocean divergence, a key indicator of vertical water mass movements. Until now, researchers could only estimate it using computer simulations or limited observations.
These now observable phenomena play a crucial role in the functioning of Earth’s climate system. The mixing of ocean waters influences, in particular, the intensity of storms, the occurrence of marine heatwaves, the dispersion of pollutants, and the oceans’ capacity to absorb carbon dioxide from the atmosphere . This is why GOFLOW could significantly improve climate models and allow scientists to make more accurate forecasts of extreme weather and climate events.
