Improving gridded snow water equivalent products in British Columbia, Canada: Multi-source data fusion by neural networkmodels

Simple item page
dc.contributor.authorSnauffer, Andrew
dc.contributor.authorHsieh, William W.
dc.contributor.authorCannon, Alex J.
dc.contributor.authorSchnorbus, Markus A.
dc.date.accessioned2025-04-10T20:27:28Z
dc.date.available2025-04-10T20:27:28Z
dc.date.issued2017
dc.description.abstractEstimates 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.
dc.description.reviewstatusReviewed
dc.description.scholarlevelFaculty
dc.description.sponsorshipFunding for this work was provided by the Canadian Sea Ice and Snow Evolution (CanSISE) Network awarded through the Climate Change and Atmospheric Research (CCAR) initiative of Canada’s Natural Sciences and Engineering Research Council (NSERC).
dc.identifier.citationSnauffer, A., Hsieh, W. W., Cannon, A. J., & Schnorbus, M. A. (2017). Improving gridded snow water equivalent products in British Columbia, Canada: Multi-source data fusion by neural networkmodels. The Cryosphere, 12, 891–905. https://doi.org/10.5194/tc-2017-56
dc.identifier.urihttps://doi.org/10.5194/tc-2017-56
dc.identifier.urihttps://hdl.handle.net/1828/21814
dc.language.isoen
dc.publisherThe Cryosphere
dc.rightsCC BY 3.0
dc.rights.urihttps://creativecommons.org/licenses/by/3.0/
dc.subjectUN SDG 13: Climate Action
dc.subject#journal article
dc.subjectPacific Climate Impacts Consortium (PCIC)
dc.titleImproving gridded snow water equivalent products in British Columbia, Canada: Multi-source data fusion by neural networkmodels
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
snauffer_andrew_tc_2017.pdf
Size:
3.16 MB
Format:
Adobe Portable Document Format
Download

Collections

PCIC Publications
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.