Researchers speed up analysis of Arctic ice and snow data through artificial intelligence

Researchers at the University of Maryland, Baltimore County have developed a technique for quicker analysis of extensive data from Arctic ice sheets to gain knowledge of patterns and trends.

Researchers are speeding up analysis of Arctic ice and snow data through AI. Photo: NSF/UCAR

Over the years, vast amounts of data have been collected about Arctic and Antarctic ice. These data are essential for scientists and policymakers seeking to understand climate change and the current trend of melting.

Researchers Masoud Yari and Maryam Rahnemoonfar have utilized new AI technology to develop a fully automatic technique to analyze ice data. They describe the technology in the Journal of Glaciology. Their effort is part of the U.S. National Science Foundation's ongoing BigData project. The data build on new image-processing algorithms developed by John Paden at the University of Kansas.

For decades, researchers have kept close track of polar ice, snow and soil measurements, but processing the large volume of available data has proven challenging.

According to Rahnemoonfar, "Radar big data is very difficult to mine and understand just by using manual techniques." The AI techniques she and Yari are developing can be used to mine the data more quickly, to get useful information on trends related to the thickness of the ice sheets and the level of snow accumulation in a certain location.

The researchers developed an algorithm that learns how to identify objects and patterns in the Arctic and Antarctic data. An AI algorithm must be exposed to hundreds of thousands of examples to learn how to identify important elements and patterns.

Rahnemoonfar and her team used existing Arctic data labeled as incomplete to train the AI algorithm how to categorize and understand new data.

The algorithm's training is not yet complete, as it will need to be scaled up over multiple sensors and locations to create a more accurate tool. However, it has already successfully begun to automate a process that was previously inefficient and labor-intensive.

The rapid expansion of AI technology to understand ice and snow thickness in the Arctic is allowing scientists and researchers to make faster and more accurate climate predictions.

The rate at which Arctic ice is melting impacts sea level rise, and, if scientists are better able to predict the severity of the melting, society can better mitigate the harm caused by sea level rise, the researchers say. (National Science Foundation)

YOU MAY ALSO LIKE

Corralling Carrots' Microbial Allies Could Stymie Disease

Carrots, while in the ground, are home to a community of microorganisms, some members of which wage a kind of battle (...)

Ancient life may have thrived in acidic lakes billions of years ago

A new study suggests acidic lakes may have harbored life in Earth’s ancient past.

Rare lichen unique to Florida discovered in museum collection, may be extinct

Hunt is on to find the lichen in the wild -- if it still exists.

Asian butterfly populations show different mimicry patterns, thanks to genetic 'switch'

New study identifies genetic markers associated with female color pattern.

Warming Seas Are Accelerating Greenland’s Glacier Retreat

Scientists with NASA’s Oceans Melting Greenland mission are probing (...)

Toxic tiger rattlesnake venom advances genetic science techniques

Study of simplest yet most toxic venom will help explain array of genetic questions.