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 »
- Authors:
-
- Subsurface Insights, Hanover, NH (United States)
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Publication Date:
- 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
Citation Formats
Meyal, Alireza Yekta, Versteeg, Roelof, Alper, Erek, Johnson, Doug, Rodzianko, Anastasia, Franklin, Maya, and Wainwright, Haruko. Automated Cloud Based Long Short-Term Memory Neural Network Based SWE Prediction. United States: N. p., 2020.
Web. doi:10.3389/frwa.2020.574917.
Meyal, Alireza Yekta, Versteeg, Roelof, Alper, Erek, Johnson, Doug, Rodzianko, Anastasia, Franklin, Maya, & Wainwright, Haruko. Automated Cloud Based Long Short-Term Memory Neural Network Based SWE Prediction. United States. https://doi.org/10.3389/frwa.2020.574917
Meyal, Alireza Yekta, Versteeg, Roelof, Alper, Erek, Johnson, Doug, Rodzianko, Anastasia, Franklin, Maya, and Wainwright, Haruko. Thu .
"Automated Cloud Based Long Short-Term Memory Neural Network Based SWE Prediction". United States. https://doi.org/10.3389/frwa.2020.574917. https://www.osti.gov/servlets/purl/1720153.
@article{osti_1720153,
title = {Automated Cloud Based Long Short-Term Memory Neural Network Based SWE Prediction},
author = {Meyal, Alireza Yekta and Versteeg, Roelof and Alper, Erek and Johnson, Doug and Rodzianko, Anastasia and Franklin, Maya and Wainwright, Haruko},
abstractNote = {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.},
doi = {10.3389/frwa.2020.574917},
journal = {Frontiers in Water},
number = ,
volume = 2,
place = {United States},
year = {Thu Nov 19 00:00:00 EST 2020},
month = {Thu Nov 19 00:00:00 EST 2020}
}
Works referenced in this record:
SWAT: Model Use, Calibration, and Validation
journal, January 2012
- J. G. Arnold,
- Transactions of the ASABE, Vol. 55, Issue 4
Using machine learning for real-time estimates of snow water equivalent in the watersheds of Afghanistan
journal, January 2018
- Bair, Edward H.; Abreu Calfa, Andre; Rittger, Karl
- The Cryosphere, Vol. 12, Issue 5
Mountain hydrology of the western United States: MOUNTAIN HYDROLOGY OF THE WESTERN US
journal, August 2006
- Bales, Roger C.; Molotch, Noah P.; Painter, Thomas H.
- Water Resources Research, Vol. 42, Issue 8
Learning long-term dependencies with gradient descent is difficult
journal, March 1994
- Bengio, Y.; Simard, P.; Frasconi, P.
- IEEE Transactions on Neural Networks, Vol. 5, Issue 2
Factors controlling seasonal groundwater and solute flux from snow-dominated basins
journal, June 2018
- Carroll, Rosemary W. H.; Bearup, Lindsay A.; Brown, Wendy
- Hydrological Processes, Vol. 32, Issue 14
Combined impacts of current and future dust deposition and regional warming on Colorado River Basin snow dynamics and hydrology
journal, January 2013
- Deems, J. S.; Painter, T. H.; Barsugli, J. J.
- Hydrology and Earth System Sciences, Vol. 17, Issue 11
Comparison of Long Short Term Memory Networks and the Hydrological Model in Runoff Simulation
journal, January 2020
- Fan, Hongxiang; Jiang, Mingliang; Xu, Ligang
- Water, Vol. 12, Issue 1
Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental U.S. Using a Deep Learning Neural Network
journal, November 2017
- Fang, Kuai; Shen, Chaopeng; Kifer, Daniel
- Geophysical Research Letters, Vol. 44, Issue 21
Snow water equivalent interpolation for the Colorado River Basin from snow telemetry (SNOTEL) data: SNOW WATER EQUIVALENT FROM SNOTEL DATA
journal, August 2003
- Fassnacht, S. R.; Dressler, K. A.; Bales, R. C.
- Water Resources Research, Vol. 39, Issue 8
Deep learning for time series classification: a review
journal, March 2019
- Ismail Fawaz, Hassan; Forestier, Germain; Weber, Jonathan
- Data Mining and Knowledge Discovery, Vol. 33, Issue 4
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
- Guan, Bin; Molotch, Noah P.; Waliser, Duane E.
- Water Resources Research, Vol. 49, Issue 8
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
- Harte, John; Saleska, Scott R.; Levy, Charlotte
- Global Change Biology, Vol. 21, Issue 6
Long Short-Term Memory
journal, November 1997
- Hochreiter, Sepp; Schmidhuber, Jürgen
- Neural Computation, Vol. 9, Issue 8
Observations Data Model 2: A community information model for spatially discrete Earth observations
journal, May 2016
- Horsburgh, Jeffery S.; Aufdenkampe, Anthony K.; Mayorga, Emilio
- Environmental Modelling & Software, Vol. 79
Deep Learning with a Long Short-Term Memory Networks Approach for Rainfall-Runoff Simulation
journal, October 2018
- Hu, Caihong; Wu, Qiang; Li, Hui
- Water, Vol. 10, Issue 11
Spatio-temporal prediction of snow water equivalent using the Kalman filter
journal, July 1996
- Huang, Hsin-Cheng; Cressie, Noel
- Computational Statistics & Data Analysis, Vol. 22, Issue 2
The East River, Colorado, Watershed: A Mountainous Community Testbed for Improving Predictive Understanding of Multiscale Hydrological–Biogeochemical Dynamics
journal, January 2018
- Hubbard, Susan S.; Williams, Kenneth Hurst; Agarwal, Deb
- Vadose Zone Journal, Vol. 17, Issue 1
Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks
journal, January 2018
- Kratzert, Frederik; Klotz, Daniel; Brenner, Claire
- Hydrology and Earth System Sciences, Vol. 22, Issue 11
Comparison of different efficiency criteria for hydrological model assessment
journal, January 2005
- Krause, P.; Boyle, D. P.; Bäse, F.
- Advances in Geosciences, Vol. 5
River Flow Forecasting using Recurrent Neural Networks
journal, April 2004
- Nagesh Kumar, D.; Srinivasa Raju, K.; Sathish, T.
- Water Resources Management, Vol. 18, Issue 2
Application of Long Short-Term Memory (LSTM) Neural Network for Flood Forecasting
journal, July 2019
- Le, Xuan-Hien; Ho, Hung Viet; Lee, Giha
- Water, Vol. 11, Issue 7, p. 1387
Snow water equivalent prediction using Bayesian data assimilation methods
journal, December 2010
- Leisenring, Marc; Moradkhani, Hamid
- Stochastic Environmental Research and Risk Assessment, Vol. 25, Issue 2
Improving hydropower inflow forecasts by assimilating snow data
journal, March 2020
- Magnusson, Jan; Nævdal, Geir; Matt, Felix
- Hydrology Research, Vol. 51, Issue 2
River flow forecasting through conceptual models part I — A discussion of principles
journal, April 1970
- Nash, J. E.; Sutcliffe, J. V.
- Journal of Hydrology, Vol. 10, Issue 3
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
- Painter, Thomas H.; Berisford, Daniel F.; Boardman, Joseph W.
- Remote Sensing of Environment, Vol. 184
Long short-term memory (LSTM) recurrent neural network for low-flow hydrological time series forecasting
journal, July 2019
- Sahoo, Bibhuti Bhusan; Jha, Ramakar; Singh, Anshuman
- Acta Geophysica, Vol. 67, Issue 5
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
- Schneider, Dominik; Molotch, Noah P.
- Water Resources Research, Vol. 52, Issue 10
The Effect of the Foresummer Drought on Carbon Exchange in Subalpine Meadows
journal, February 2015
- Sloat, Lindsey L.; Henderson, Amanda N.; Lamanna, Christine
- Ecosystems, Vol. 18, Issue 3
Satellite-derived foresummer drought sensitivity of plant productivity in Rocky Mountain headwater catchments: spatial heterogeneity and geological-geomorphological control
journal, July 2020
- Wainwright, Haruko M.; Steefel, Christoph; Trutner, Sarah D.
- Environmental Research Letters, Vol. 15, Issue 8
The Bias‐Detecting Ensemble: A New and Efficient Technique for Dynamically Incorporating Observations Into Physics‐Based, Multilayer Snow Models
journal, January 2019
- Winstral, A.; Magnusson, J.; Schirmer, M.
- Water Resources Research, Vol. 55, Issue 1
A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning
journal, January 2020
- Xiang, Zhongrun; Yan, Jun; Demir, Ibrahim
- Water Resources Research, Vol. 56, Issue 1
Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas
journal, June 2018
- Zhang, Jianfeng; Zhu, Yan; Zhang, Xiaoping
- Journal of Hydrology, Vol. 561