Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models
Estimates of surface snow water equivalent (SWE) in mixed alpine environments 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...
Published in: | The Cryosphere |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Publications
2018
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-12-891-2018 https://doaj.org/article/6c87ea785ebf49ef8025a20e4b617f5a |
id |
ftdoajarticles:oai:doaj.org/article:6c87ea785ebf49ef8025a20e4b617f5a |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:6c87ea785ebf49ef8025a20e4b617f5a 2023-05-15T18:32:26+02:00 Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models A. M. Snauffer W. W. Hsieh A. J. Cannon M. A. Schnorbus 2018-03-01T00:00:00Z https://doi.org/10.5194/tc-12-891-2018 https://doaj.org/article/6c87ea785ebf49ef8025a20e4b617f5a EN eng Copernicus Publications https://www.the-cryosphere.net/12/891/2018/tc-12-891-2018.pdf https://doaj.org/toc/1994-0416 https://doaj.org/toc/1994-0424 doi:10.5194/tc-12-891-2018 1994-0416 1994-0424 https://doaj.org/article/6c87ea785ebf49ef8025a20e4b617f5a The Cryosphere, Vol 12, Pp 891-905 (2018) Environmental sciences GE1-350 Geology QE1-996.5 article 2018 ftdoajarticles https://doi.org/10.5194/tc-12-891-2018 2022-12-31T01:04:52Z Estimates of surface snow water equivalent (SWE) in mixed alpine environments 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. Relevant spatiotemporal covariates 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 interannual 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 province. ANN3 outperformed each product as well as product means and multiple linear regression (MLR) models in all of BC's five physiographic regions except for the BC Plains. Subsequent comparisons with predictions generated by the Variable Infiltration Capacity (VIC) hydrologic model found ANN3 to better estimate SWE over the VIC domain and within most regions. The superior performance of ANN3 over the individual products, product means, MLR, and VIC was found to be statistically significant across the province. Article in Journal/Newspaper The Cryosphere Directory of Open Access Journals: DOAJ Articles Canada British Columbia ENVELOPE(-125.003,-125.003,54.000,54.000) The Cryosphere 12 3 891 905 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Environmental sciences GE1-350 Geology QE1-996.5 |
spellingShingle |
Environmental sciences GE1-350 Geology QE1-996.5 A. M. Snauffer W. W. Hsieh A. J. Cannon M. A. Schnorbus Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models |
topic_facet |
Environmental sciences GE1-350 Geology QE1-996.5 |
description |
Estimates of surface snow water equivalent (SWE) in mixed alpine environments 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. Relevant spatiotemporal covariates 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 interannual 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 province. ANN3 outperformed each product as well as product means and multiple linear regression (MLR) models in all of BC's five physiographic regions except for the BC Plains. Subsequent comparisons with predictions generated by the Variable Infiltration Capacity (VIC) hydrologic model found ANN3 to better estimate SWE over the VIC domain and within most regions. The superior performance of ANN3 over the individual products, product means, MLR, and VIC was found to be statistically significant across the province. |
format |
Article in Journal/Newspaper |
author |
A. M. Snauffer W. W. Hsieh A. J. Cannon M. A. Schnorbus |
author_facet |
A. M. Snauffer W. W. Hsieh A. J. Cannon M. A. Schnorbus |
author_sort |
A. M. Snauffer |
title |
Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models |
title_short |
Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models |
title_full |
Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models |
title_fullStr |
Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models |
title_full_unstemmed |
Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models |
title_sort |
improving gridded snow water equivalent products in british columbia, canada: multi-source data fusion by neural network models |
publisher |
Copernicus Publications |
publishDate |
2018 |
url |
https://doi.org/10.5194/tc-12-891-2018 https://doaj.org/article/6c87ea785ebf49ef8025a20e4b617f5a |
long_lat |
ENVELOPE(-125.003,-125.003,54.000,54.000) |
geographic |
Canada British Columbia |
geographic_facet |
Canada British Columbia |
genre |
The Cryosphere |
genre_facet |
The Cryosphere |
op_source |
The Cryosphere, Vol 12, Pp 891-905 (2018) |
op_relation |
https://www.the-cryosphere.net/12/891/2018/tc-12-891-2018.pdf https://doaj.org/toc/1994-0416 https://doaj.org/toc/1994-0424 doi:10.5194/tc-12-891-2018 1994-0416 1994-0424 https://doaj.org/article/6c87ea785ebf49ef8025a20e4b617f5a |
op_doi |
https://doi.org/10.5194/tc-12-891-2018 |
container_title |
The Cryosphere |
container_volume |
12 |
container_issue |
3 |
container_start_page |
891 |
op_container_end_page |
905 |
_version_ |
1766216547807789056 |