Never miss a story

Get subscribed to our newsletter


×
Photo by Annie Spratt on Unsplash

A novel Artificial Intelligence (AI) tool that can help accurately forecast Arctic sea ice conditions has been developed.

A novel Artificial Intelligence (AI) tool that can help accurately forecast Arctic sea ice conditions has been developed. The AI system, IceNet, addresses the challenge of producing accurate Arctic sea ice forecasts for the season ahead -- something that has eluded scientists for decades. A team of researchers led by British Antarctic Survey (BAS) and The Alan Turing Institute have described IceNet in the journal Nature Communications. Sea ice, a vast layer of frozen sea water that appears at the North and South poles, is notoriously difficult to forecast because of its complex relationship with the atmosphere above and ocean below.

These accelerating changes have dramatic consequences for our climate, for Arctic ecosystems, and indigenous and local communities whose livelihoods are tied to the seasonal sea ice cycle.

IceNet -- the AI predictive tool -- is almost 95 per cent accurate in predicting whether sea ice will be present two months ahead.

IceNet has been designed based on a concept called deep learning. Photo by Willian Justen de Vasconcellos on Unsplash



"The Arctic is a region on the frontline of climate change and has seen substantial warming over the last 40 years. IceNet has the potential to fill an urgent gap in forecasting sea ice for Arctic sustainability efforts and runs thousands of times faster than traditional methods," said lead author Tom Andersson, Data Scientist at the BAS AI Lab. "Our new sea ice forecasting framework fuses data from satellite sensors with the output of climate models in ways traditional systems simply couldn't achieve," said Dr Scott Hosking, senior Research Fellow at The Alan Turing Institute.

Unlike conventional forecasting systems that attempt to model the laws of physics directly, IceNet has been designed based on a concept called deep learning. Through this approach, the model 'learns' how sea ice changes from thousands of years of climate simulation data, along with decades of observational data to predict the extent of Arctic sea ice months into the future.

"Now we've demonstrated that AI can accurately forecast sea ice, our next goal is to develop a daily version of the model and have it running publicly in real-time, just like weather forecasts. This could operate as an early warning system for risks associated with rapid sea ice loss," Andersson said.(Article originally published at IANSlife) IANS/SS


Keywords: arctic, arctic sea, AI, Arctic ecosystems, ice loss


Popular

Photo by Tingey Injury Law Firm on Unsplash

The plea asked the Election Commission to ensure that every political party publishes each candidate's criminal records.

The Supreme Court on Tuesday agreed to examine a seeking direction to the Election Commission to de-register a political party, which fails to comply with the court's direction to disclose criminal antecedents of candidates fielded in polls. Advocate Ashwini Upadhyay requested a bench headed by Chief Justice N.V. Ramana and comprising Justices A.S. Bopanna and Hima Kohli to list the petition urgently, against the backdrop of the ongoing election process. He contended that nomination for the first phase of the Uttar Pradesh Assembly election has started, and the political parties and candidates are brazenly violating the top court judgments.

After briefly hearing Upadhyay, the bench said: "We will consider it... will give a date".

Keep Reading Show less
Unsplash

In 2018, state heads of ASEAN countries graced the occasion with their presence.

There will be no chief guest at the Republic Day parade this year also as the plan to host state heads of five Central Asian countries -- Kazakhstan, Kyrgyzstan, Tajikistan, Turkmenistan and Uzbekistan -- seems to have been cancelled due to the Covid situation in India as well as in the respective nations. Though the Ministry of External Affairs is yet to confirm this officially.

Also Read : Republic Day 2021: Significance of the Day and highlights of the Parade

Keep Reading Show less
Unsplash

Infection with antibiotic-resistant bacteria and biofilm formation halt healing progress.

A team of scientists from the Banaras Hindu University (BHU) have found a cure for those suffering from chronic wounds, particularly with diabetic foot ulcers. The team led by Prof Gopal Nath of the department of Microbiology, Institute of Medical Sciences, said that wounds that took months and years to heal, could now be cured in days or months. The findings of study have been published in the National Centre for Biotechnology Information, National Institutes of Health, US.

Also Read : Researchers develop Hydrogel to treat infections in wound

Keep reading... Show less