National Water Model
The National Water Model (NWM) is a hydrologic modeling framework that simulates observed and forecast streamflow over the entire continental United States (CONUS), southern Alaska (Cook Inlet, Copper River Basin, and Prince William Sound regions), Hawaii, Puerto Rico and the US Virgin Islands. Additionally, it produces total water level guidance for the coastlines of those same regions except Alaska. The NWM simulates the water cycle with mathematical representations of the different processes and how they fit together. This complex representation of physical processes such as snowmelt and infiltration and movement of water through the soil layers varies significantly with changing elevations, soils, vegetation types and a host of other variables. Additionally, extreme variability in precipitation over short distances and times can cause the response on rivers and streams to change very quickly. Overall, the process is so complex that to simulate it with a mathematical model means that it needs a very high powered computer or supercomputer in order to run in the time frame needed to support decision makers when flooding is threatened.
National Snow Model
The National Snow Model incorporates ground-based snow measuring sites, remotely-sensed snow cover information, and an artificial neural network to provide point estimations of snow water equivalent. The network was trained on historical data from NASA’s ASO missions, divided into regions, and then a LightGBM gradient boosting framework was used to preform recursive feature elimination to produce an efficient feature selection and region-specific model. The class contains the required functions for downloading data, pre-processing, running inference, and producing visualizations.