Abstract
Snow derived water is a critical component of a large part of the US water supply. Measurements of the Snow Water Equivalent (SWE) and associated predictions of peak SWE and snowmelt onset are essential inputs for water management efforts. This paper aims to develop a data-driven approach for estimating and predicting SWE dynamics using the Long Short-Term Memory neural network (LSTM) method. Our approach uses historical datasets (precipitation, air temperature, SWE and snow thickness) collected at NRCS Snow Telemetry (SNOTEL) stations to train the LSTM network and current year data to predict SWE behavior. The performance of our prediction was compared for different prediction dates and prediction training datasets. Our results suggest that the proposed LSTM network can be an efficient tool for forecasting the SWE timeseries, as well as Peak SWE and snowmelt timing. Results showed that the window size impacts the model performance (where the Nash Sutcliffe efficiency (NSE) ranged from 0.96 to 0.85 and the Rooted Mean Square Error (RMSE) ranged from 0.038 to 0.07) with an optimum number that should be calibrated for different stations and climate conditions. By implementing the LSTM prediction capability in a cloud based site-monitoring platform we automate model-data integration. By making the data accessible through a graphical web interface and an underlying API which exposes both training and prediction capabilities. the associated results can be made easily accessible to a broad range of stakeholders.
Highlights
Accurate estimation and prediction of snow water equivalent (SWE) in mountain watersheds has been a longstanding challenge (Bair et al, 2018), while, it is a key metric used by hydrologists and water managers to assess water resources in snow-dominated catchments or basins (Bales et al, 2006; Painter et al, 2016)
We evaluated Snow Water Equivalent (SWE) forecast performance, obtained from Long Short-Term Memory neural network (LSTM) model, by considering 3 month forecasting for different Snow Telemetry (SNOTEL) stations (Schofield Pass, Upper Taylor, and Park Cone)
We demonstrated that LSTM networks can be trained to accurately predict SWE behavior for different Natural Resource Conservation Service (NRCS) SNOTEL stations
Summary
Accurate estimation and prediction of snow water equivalent (SWE) in mountain watersheds has been a longstanding challenge (Bair et al, 2018), while, it is a key metric used by hydrologists and water managers to assess water resources in snow-dominated catchments or basins (Bales et al, 2006; Painter et al, 2016). Cloud Based LSTM SWE Prediction peak SWE and snowmelt timing onset (Odei et al, 2009). This snowmelt timing is critical for ecological processes in snow-dominated regions, controlling plant dynamics, net ecosystem exchanges, and soil carbon (Harte et al, 2015; Sloat et al, 2015; Wainwright et al, 2020). Stations are typically located in small clearings in evergreen forests Data from these stations is transferred multiple times a day to a central database, from where the data is publicly accessible through web interfaces and software APIs. Each SNOTEL station has a long record of historical data, often more than 30 years, encompassing a variety of metrological conditions at each site. Snow accumulation and melting is a highly heterogeneous process affected by a complex terrain or regional scale atmospheric forcing which support us to use deep learning method for SWE forecasting
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
