Artificial intelligence predicts the disappearance of ice in the Arctic
Scientists from the British Antarctic Survey (BAS) have developed a new artificial intelligence system. Its main task is to predict when the Arctic seas may lose their ice cover, according to Nature Communications.
A project called IceNet has been trained based on satellite data collected in the Arctic over the past four decades. Experiments have shown that he predicts the presence of sea ice two months in advance with an accuracy of 95%.
Sea ice at both the North and South Poles naturally expands in winter and contracts in summer. But its behavior is difficult to predict as it interacts with the atmosphere above and the ocean below.
The Arctic has experienced “unprecedented year-round sea ice reduction” due to human-induced global warming. Artificial intelligence could serve as the basis for new early warning systems that protect Arctic ecosystems from the effects of sea ice loss.
“The Arctic is a region at the forefront of climate change and has seen significant warming over the past 40 years,” study author Tom Andersson said.
IceNet is thousands of times faster than traditional methods and does not require supercomputers – it can be run on a regular laptop. It will allow you to assess in advance the risks associated with the loss of ice.
“Our next goal is to develop a daily version of the model and launch it publicly in real time, just like weather forecasts,” noted the authors of the development.
Previously, scientists have named the signs of a global climate catastrophe. One of them is rain in Greenland.
