Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

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

Journal Article · · Frontiers in Water
 [1];  [2];  [2];  [2];  [2];  [3];  [3]
  1. Subsurface Insights, Hanover, NH (United States); Subsurface Insights LLC
  2. Subsurface Insights, Hanover, NH (United States)
  3. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
+ Show Author Affiliations
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. 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.
Research Organization:
Subsurface Insights, Hanover, NH (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Biological and Environmental Research (BER). Earth and Environmental Systems Science Division
Grant/Contract Number:
AC02-05CH11231; SC0018447
OSTI ID:
1720153
Journal Information:
Frontiers in Water, Journal Name: Frontiers in Water Vol. 2; ISSN 2624-9375
Publisher:
FrontiersCopyright Statement
Country of Publication:
United States
Language:
English

References (32)

Real-time estimation of snow water equivalent in the Upper Colorado River Basin using MODIS-based SWE Reconstructions and SNOTEL data: REAL-TIME SNOW WATER EQUIVALENT FROM SWE RECONSTRUCTIONS journal October 2016
Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental U.S. Using a Deep Learning Neural Network journal November 2017
Factors controlling seasonal groundwater and solute flux from snow-dominated basins journal June 2018
Snow water equivalent in the Sierra Nevada: Blending snow sensor observations with snowmelt model simulations: SNOW WATER EQUIVALENT IN THE SIERRA NEVADA journal August 2013
Snow water equivalent prediction using Bayesian data assimilation methods journal December 2010
The Effect of the Foresummer Drought on Carbon Exchange in Subalpine Meadows journal February 2015
Deep learning for time series classification: a review journal March 2019
Long short-term memory (LSTM) recurrent neural network for low-flow hydrological time series forecasting journal July 2019
River flow forecasting through conceptual models part I — A discussion of principles journal April 1970
Spatio-temporal prediction of snow water equivalent using the Kalman filter journal July 1996
Observations Data Model 2: A community information model for spatially discrete Earth observations journal May 2016
Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas journal June 2018
The Airborne Snow Observatory: Fusion of scanning lidar, imaging spectrometer, and physically-based modeling for mapping snow water equivalent and snow albedo journal October 2016
River Flow Forecasting using Recurrent Neural Networks journal April 2004
Snow water equivalent interpolation for the Colorado River Basin from snow telemetry (SNOTEL) data: SNOW WATER EQUIVALENT FROM SNOTEL DATA journal August 2003
Mountain hydrology of the western United States: MOUNTAIN HYDROLOGY OF THE WESTERN US journal August 2006
The Bias‐Detecting Ensemble: A New and Efficient Technique for Dynamically Incorporating Observations Into Physics‐Based, Multilayer Snow Models journal January 2019
A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning journal January 2020
Satellite-derived foresummer drought sensitivity of plant productivity in Rocky Mountain headwater catchments: spatial heterogeneity and geological-geomorphological control journal July 2020
Learning long-term dependencies with gradient descent is difficult journal March 1994
Convergent ecosystem responses to 23-year ambient and manipulated warming link advancing snowmelt and shrub encroachment to transient and long-term climate-soil carbon feedback journal January 2015
Long Short-Term Memory journal November 1997
SWAT: Model Use, Calibration, and Validation journal January 2012
The East River, Colorado, Watershed: A Mountainous Community Testbed for Improving Predictive Understanding of Multiscale Hydrological–Biogeochemical Dynamics journal January 2018
Improving hydropower inflow forecasts by assimilating snow data journal March 2020
Deep Learning with a Long Short-Term Memory Networks Approach for Rainfall-Runoff Simulation journal October 2018
Application of Long Short-Term Memory (LSTM) Neural Network for Flood Forecasting journal July 2019
Comparison of Long Short Term Memory Networks and the Hydrological Model in Runoff Simulation journal January 2020
Comparison of different efficiency criteria for hydrological model assessment journal January 2005
Combined impacts of current and future dust deposition and regional warming on Colorado River Basin snow dynamics and hydrology journal January 2013
Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks journal January 2018
Using machine learning for real-time estimates of snow water equivalent in the watersheds of Afghanistan journal January 2018

Similar Records

Using Temporal Deep Learning Models to Estimate Daily Snow Water Equivalent Over the Rocky Mountains
Journal Article · Tue Apr 16 20:00:00 EDT 2024 · Water Resources Research · OSTI ID:2337973

Related Subjects

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