SnowML™, an open-data, machine learning–driven system for estimation of snow water equivalent (SWE) and seasonal water supply forecasting. The SnowML framework integrates satellite remote sensing, ground-based observations, and atmospheric model parameters to produce a spatially continuous, time-evolving SWE dataset. 

SnowQ®, patent pending, is our weather radar-based remote sensing solution for snow water equivalent (SWE). It enables delivery of  continuous data to snowmelt forecasters and water resource managers.

At the core of SnowQ is technology that integrates data streams from weather radar networks, ground sensor arrays, remote observations and other sources. Using proprietary algorithms to calibrate SWE-aloft to SWE on the ground, the system applies machine-learning techniques to generate accurate, basin-wide SWE maps.

Freshet™ is a cloud-native, physics-based, distributed hydrologic model engineered on a network-based framework rather than a traditional gridded system. It is purpose-built to capture snowmelt processes and the interplay between surface and subsurface runoff with greater fidelity. Driven by SnowML, Freshet produces daily, 10-day, and monthly forecasts of discharge and cumulative runoff volume, supporting both real-time water operations and longer-term planning.