If this is the year artificial intelligence and machine learning are everywhere, soon they may help you come down that mountain safely.

For the 2023 International Day for Disaster Risk Reduction, we talked to Scott Chamberlin who started The Open Avalanche Project. Launched in 2017, it aims to reduce avalanche-related deaths worldwide.

The avalanche forecasting community is trying to develop open-source artificial intelligence models to improve the accuracy of avalanche forecasts. However, there are two main challenges to this: the input labels (historical forecasts) are not always accurate and the input data source (GFS forecast model) is also not the most accurate available. One upside: much of that data comes from municipalities or governments, often in the public domain. There have been some good advances in making some of this data available, too.

Open-source advancements in AI/ML are advancing at tremendous speed. When those general advancements are done in open source it’s easier for people working on domain-specific problems to try them out and adopt them. “My hope is that we can provide something valuable and trustworthy to the community and that the open nature of it helps those aspects,” Chamberlin says.

A backcountry skier himself, he understands the importance of evaluating risks from the top of the slope. The avalanche forecast plays a vital role in this decision-making process by providing additional information on local conditions. He hopes that open-source contributions will provide those who enjoy the most remote mountains with tools to keep them safe.

Learn more about how Chamberlin got started, what community contributions he’s looking for and just how “open” the avalanche forecasting field is.

Catch the full interview over on opensource.net.