Climate change is impacting snowpack dynamics such as timing of snow melt. Accurate prediction of snowmelt runoff will aid in water supply forecasting. Snow being an important water resource in the Western United States, accurate assessments of its availability are crucial for regional water managers. They need to make informed decisions on how to allocate water among diverse stakeholder needs (Schneider & Molotch, 2016). Precise estimation of SWE plays a pivotal role in determining the amount of spring and summer runoff. Thus, SWE estimates are a vital component of water resources prediction and forecasting, which can help water managers plan ahead and ensure sustainable water management practices for the long term (Meyal et al., 2020).
To leverage the application of a range of machine learning models, starting from simplistic regression models to more complex deep learning models such as long short-term memory network (LSTM) as utilized by researchers in the past. We plan to gain a comprehensive understanding of different models by working with realistic datasets acquired from various Snow Telemetry (SNOTEL) sites. This would help us to obtain hands-on experiences that will aid our comprehension of automation and parameter prediction in the water resources sector. Through this we would go through the step-by-step process of data acquisition, pre -processing of raw datasets, exploratory data exploration, and model selection. We hope to gain the skills and knowledge necessary to improve our ability to predict and manage snow melt.
