Journal cover Journal topic
The Cryosphere An interactive open-access journal of the European Geosciences Union
https://doi.org/10.5194/tc-2017-56
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 3.0 License.
Research article
02 Jun 2017
Review status
This discussion paper is under review for the journal The Cryosphere (TC).
Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models
Andrew Snauffer1, William Hsieh1, Alex Cannon2, and Markus Schnorbus3 1Department of Earth, Ocean and Atmospheric Sciences, The University of British Columbia, Vancouver, BC V6T 1Z4, Canada
2Climate Research Division, Environment and Climate Change Canada, PO Box 1700 STN CSC, Victoria, BC V8W 2Y2, Canada
3Pacific Climate Impacts Consortium, University House 1, 2489 Sinclair Road, University of Victoria, Victoria, BC V8N 6M2, Canada
Abstract. Estimates of surface snow water equivalent (SWE) in alpine regions with seasonal melts are particularly difficult in areas of high vegetation density, topographic relief and snow accumulations. These three confounding factors dominate much of the province of British Columbia (BC), Canada. An artificial neural network (ANN) was created using as predictors six gridded SWE products previously evaluated for BC: ERA-Interim/Land, GLDAS-2, MERRA, MERRA-Land, GlobSnow and ERA-Interim. Relevant spatiotemporal covariates including survey date, year, latitude, longitude, elevation and grid cell elevation differences were also included as predictors, and observations from manual snow surveys at stations located throughout BC were used as target data. Mean absolute errors (MAEs) and correlations for April surveys were found using cross validation. The ANN using the three best performing SWE products (ANN3) had the lowest mean station MAE across the entire province, improving on the performance of individual products by an average of 53 %. Mean station MAEs and April survey correlations were also found for each of BC’s five physiographic regions. ANN3 outperformed each product as well as product means and multiple linear regression (MLR) models in all regions except for the BC Plains, which has relatively few stations and much lower accumulations than other regions. Subsequent comparisons of the ANN results with predictions generated by the Variable Infiltration Capacity (VIC) hydrologic model found ANN3 to be superior over the entire VIC domain and within most physiographic regions. The superior performance of the ANN over individual products, product means, MLR and VIC was found to be statistically significant across the province.

Citation: Snauffer, A., Hsieh, W., Cannon, A., and Schnorbus, M.: Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models, The Cryosphere Discuss., https://doi.org/10.5194/tc-2017-56, in review, 2017.
Andrew Snauffer et al.
Andrew Snauffer et al.
Andrew Snauffer et al.

Viewed

Total article views: 338 (including HTML, PDF, and XML)

HTML PDF XML Total BibTeX EndNote
255 65 18 338 2 22

Views and downloads (calculated since 02 Jun 2017)

Cumulative views and downloads (calculated since 02 Jun 2017)

Viewed (geographical distribution)

Total article views: 338 (including HTML, PDF, and XML)

Thereof 334 with geography defined and 4 with unknown origin.

Country # Views %
  • 1

Saved

Discussed

Latest update: 20 Jul 2017
Publications Copernicus
Download
Short summary
Estimating winter snowpack throughout British Columbia is challenging due to the complex terrain, thick forests and high snow accumulations present. This paper describes a way to make better snow estimates by combining publicly available data using machine learning, a branch of artificial intelligence research. These improved estimates will help water resources managers better plan for changes in rivers and lakes fed by springtime snowmelt and will aid other research that supports such planning.
Estimating winter snowpack throughout British Columbia is challenging due to the complex...
Share