Snowpack is an essential source of water for many urban communities in the United States, a kind of piggy bank that water providers withdrawal from each spring. As drought grips the southwest, that makes accurately estimating snowpack essential.

The job in part falls to the Bureau of Reclamation, which today announced its crowdsourcing innovative methods of estimating what's known in the water business as snow water equivalent (SWE). The competition is called "Snowcast Showdown" and it's being implemented by DrivenData, Ensemble, and HeroX. Competitors are challenged to provide spatially-distributed estimates of SWE over the western US during the 2022 winter season, with prizes at stake totaling$500,000.

"These kinds of Challenges channel the efforts of skilled experts around the world to push forward the tools available to our nation's public agencies and water managers," explains Greg Lipstein, Principal at DrivenData, one of the challenge partners. The company is a social enterprise dedicated to bringing the data tools and methods that are transforming industry to big global challenges, channeling the skills and passion of data scientists, researchers, and other quantitative experts to build solutions for social good.

This is a cool application for spatial problem solvers, and it's parts of an urgent effort to effectively manage dwindling water resources. The Bureau of Reclamation is the largest wholesaler of water in the western US and the second largest producer of hydropower in the US, serving 31 million people per year and irrigating 10 million acres of farmland that produce 60% of the nation's vegetables and 25% of fruit and nut crops. 

Much of that water comes from snowpack, particularly in the Rockies and the Sierra Nevada. During winter, snow accumulates in mountain headwaters. When temperatures rise in the spring and summer, snowpacks melt, serving as a freshwater source for major streams and rivers which feed Reclamation reservoirs. 

Reclamation has been relying on ground-based telemetry instruments to monitor snowpacks for decades, but these tools are spatially limited and challenging to maintain. Airborne methods to estimate SWE are highly accurate but espensive. Satellite remote sensing methods, likely the future of the science, are not ready for prime time. Thus new solutions are needed.

The Prediction Competition Track of the competition focuses on machine learning. Participants will train models to estimate SWE at 1km resolution across 17 states in the Western US. Most of the prize money ($440,000) will be awarded in this track, with separate prizes for overall performance and performance across geographies. The Model Report Competition is a model analysis competition, which will award a$60,000 prize purse to the top 3 teams. 

If this is up your alley and you're over 18, the challenge rule and instructions can be found here. Don't forget your snow shovel.

Innovation

I tried Apple Vision Pro and it's far ahead of where I expectedThis tiny satellite communicator is packed full of features and peace of mindHow to use ChatGPT: Everything you need to knowThese are my 5 favorite AI tools for work

• I tried Apple Vision Pro and it's far ahead of where I expected
• This tiny satellite communicator is packed full of features and peace of mind
• How to use ChatGPT: Everything you need to know
• These are my 5 favorite AI tools for work