Win half-a-million for measuring water in snowflakes

Image: Don Ross III

The US government is offering $500,000 to anyone in the world who can produce a better tool to measure how much water snowflakes contain.

This challenges comes as comes as Colorado and other western states in the US are experiencing a worryingly dry autumn and early winter.

Climate change has triggered decades-long megadroughts, and populations have soared, which means water is becoming an ever-increasingly scarce resource and consequently cities and farms across much of the west rely primarily on snow for their water supplies.

The snow acts as a natural reservoir by storing precipitation throughout the winter months and releasing it as snowmelt when temperatures rise during the spring and summer. This meltwater becomes runoff and serves as a primary freshwater source for major streams, rivers and reservoirs. As a result, snowpack accumulation on high-elevation mountains significantly influences the amount of water that is available for millions of people living in the region.

When it comes to snow forecasting, it is important to understand early how snowy a winter season is likely to be, and how much water is contained in the snow. For example, flakes that fall in ultra-cold weather often contain significantly less water than those that fall during warmer storms. Given the diverse landscape in the western US, and shifting climate, new and improved methods are needed to accurately measure snow water content.

In order to accurately forecast and therefore manage snow-based water supplies, the Bureau of Reclamation - a federal US agency which oversees water resource management - has partnered with three technology companies including NASA and DrivenData to challenge anyone aged 18+ to develop a tool that can accurately predict snow water content.

“Our technology must advance to meet the particular challenges of climate change and extreme weather.”

Greg Lipstein, DrivenData.

The competition is divided into two tracks. In track one, participants develop a model and calibrate it using historical information. The effectiveness and accuracy of the test model will be evaluated during the winter and spring using real-time snowpack measurements. For track two, models in the first track are eligible to submit a report that discusses their solution and approaches to solving the problem in track one.

The challenge will focus on using machine-learning methods that provide flexible and efficient algorithms for data-driven models and real-time prediction.

The Bureau of Reclamation conducts prize competitions to spur innovation by engaging a non-traditional, problem-solver community. In the past six years, it has awarded more than $4 million in prizes through 29 competitions. Please visit the Water Prize Competition Center to learn more.