Ensemble is very excited to be working with the Bureau of Reclamation on the Snowcast Showdown Competition along with DrivenData over the coming months!
Throughout much of the Western United States snowpack is an invaluable resource, acting as a water reservoir for the coming Spring and Summer seasons. The melt-off from snowpack is a major freshwater resource for the region’s streams, reservoirs, and rivers. Because of this chain of events, the mountaintop snowpack has a huge influence on water availability and allocation for millions of people throughout the region. Over the years, especially given the onset of significantly more climate change-related events such as droughts and wildfires in the Western U.S, being able to track and estimate the amount of snowpack on large peaks has become essential for the safety and wellbeing of communities in the region.
In order to analyze snowpack data;“Ground-based instruments including snow course and SNOwpack TELemetry (SNOTEL) stations have been used to monitor snowpacks. While ground measures can provide accurate SWE estimates, ground stations tend to be spatially limited and are not easily installed at high elevations. Recently, high-resolution satellite imagery has strengthened snow monitoring systems by providing data in otherwise inaccessible areas at frequent time intervals.”
Due to the ever-shifting climate in the region, it’s essential to more accurately measure Snow Water Equivalent (SWE), the most commonly used measure in water forecasting, which combines both snow density and depth data. Because of this, Ensemble and Driven Data are running the SnowCast Showdown competition, which is being hosted by the Bureau of Reclamation. As stated in the challenge description on the Driven Data crowdsourcing platform, “The goal of this challenge is to estimate Snow Water Equivalent (SWE) at a high spatiotemporal resolution over the Western U.S. using near-real-time data sources. Getting better SWE estimates for mountain watersheds and headwater catchments will help to improve runoff and water supply forecasts, which in turn will help reservoir operators manage limited water supplies. Improved SWE information will also help water managers respond to extreme weather events such as floods and droughts.”
Currently, the competition is in its 1st stage, model development. During this stage, participants are able to use available snowpack data from SNOTEL stations dispersed throughout the regions to build data pipelines and test modeling approaches.
To learn more about the competition and to see live results from participants be sure to check out Driven Data’s page here: https://www.drivendata.org/competitions/86/competition-reclamation-snow-water-dev/page/414/
Driven Data brings cutting-edge data science and crowdsourcing practices to large-scale challenges and the organizations that are tackling them. They host online challenges, “where a global community of data scientists competes to come up with the best statistical model for difficult predictive problems that make a difference.”