Scientists have developed an artificial intelligence (AI) that can predict the melting of polar sea ice. According to experts, thanks to these predictions, early warning systems could improve significantly.
In a study published this week in the journal Nature Communications, an international research team led by the British Antarctic Survey (BAS) and The Alan Turing Institute introduced IceNet, an artificial intelligence system that can predict the probability of melting Arctic sea ice.
According to experts, this system will significantly improve early warning systems by providing more precise predictions of sea ice melt due to climate change.
Glacier melted 25 times the size of GREAT BRITAIN
Predicting the melting of sea ice, the frozen sea layers at the North and South poles, is difficult because of the complex relationship between the atmosphere and the ocean. But researchers have found that the area of Arctic sea ice has halved over the past 40 years, due to the increased sensitivity of sea ice to temperatures. This corresponds to an area loss of approximately 25 times the size of Great Britain. The biggest reason for this event is the climate changes on the planet.
SWEDEN’S HIGHEST MOUNT IS SHORTENING DUE TO GLOBAL WARMING
The artificial intelligence system IceNet is expected to be able to predict future meltdowns and play an important role in taking the necessary precautions.
According to the researchers, IceNet is 95% successful in predicting sea ice melt likely to occur two months from now. This ratio is much better than many leading models at the moment.
THOUSAND TIMES FASTER THAN CONVENTIONAL METHODS
Tom Anderrson, one of the authors of the study, used the following statements about the research:
“The Arctic is one of the regions affected by climate change. The melting of sea ice in the last 40 years is a very good example of this. IceNet, on the other hand, has great potential to predict these meltdowns. This system works thousands of times faster and delivers better results than traditional methods.”
Another researcher, Dr. Scott Hosting, on the other hand, said about the artificial intelligence system, “IceNet examines decades of satellite data by combining thousands of years of climate simulation data to predict glacier meltdowns, and comes to conclusions that cannot be achieved with traditional methods.”
According to Tom Anderrson, the next goal for the system is to develop a daily version of the model to develop a real-time and publicly available early warning system such as weather systems.
The opinions expressed herein are the author’s and not necessarily those of News2Sea.
#Artificial #intelligence #predict #polar #ice #melt