Title: Automated Cloud Based Long Short-Term Memory Neural Network Based SWE Prediction

Abstract

Snow derived water is a critical component 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 an integrated framework for real-time data ingestion, estimation, prediction and visualization of SWE based on daily snow datasets. In particular, we 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.more » In addition, 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.« less

Authors:

Meyal, Alireza Yekta  ^[1];

• Search DOE PAGES for author "Meyal, Alireza Yekta"
• Search DOE PAGES for ORCID "0000-0003-3608-8799"

Versteeg, Roelof  ^[1];

• Search DOE PAGES for author "Versteeg, Roelof"
• Search DOE PAGES for ORCID "0000-0002-6767-1082"

Alper, Erek  ^[1];

• Search DOE PAGES for author "Alper, Erek"
• Search DOE PAGES for ORCID "0000-0002-2923-7840"

Johnson, Doug  ^[1];

• Search DOE PAGES for author "Johnson, Doug"
• Search DOE PAGES for ORCID "0000-0002-4023-2709"

Rodzianko, Anastasia  ^[1];

• Search DOE PAGES for author "Rodzianko, Anastasia"
• Search DOE PAGES for ORCID "0000-0003-4081-5100"

Franklin, Maya  ^[2];

• Search DOE PAGES for author "Franklin, Maya"
• Search DOE PAGES for ORCID "0000-0002-4804-3267"

Wainwright, Haruko  ^[2]

• Search DOE PAGES for author "Wainwright, Haruko"
• Search DOE PAGES for ORCID "0000-0002-2140-6072"

---

+ Show Author Affiliations

1. Subsurface Insights, Hanover, NH (United States)
2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

Publication Date:

Thu Nov 19 00:00:00 EST 2020

Research Org.:

Subsurface Insights, Hanover, NH (United States)

Sponsoring Org.:

USDOE Office of Science (SC), Biological and Environmental Research (BER). Earth and Environmental Systems Science Division

OSTI Identifier:

1720153

Grant/Contract Number:  

SC0018447; AC02-05CH11231

Resource Type:

Accepted Manuscript

Journal Name:

Frontiers in Water

Additional Journal Information:

Journal Volume: 2; Journal ID: ISSN 2624-9375

Publisher:

Frontiers

Country of Publication:

United States

Language:

English

Subject:

54 ENVIRONMENTAL SCIENCES; 58 GEOSCIENCES; Neural networks; prediction, SWE; LSTM; real-time web based interface; forecasting; model-data integration