Abstract. 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.
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 ERAInterim. Relevant spatiotemporal covariates including survey date, year, latitude, longitude, elevation and grid cell elevation 5 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 10 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.
Dissolved organic carbon (DOC) is a master variable in aquatic systems. Resolving DOC dynamics requires high‐temporal resolution data. However, DOC concentration cannot be directly measured in situ, and discrete sample collection and analysis becomes expensive as temporal resolution increases. To surmount this problem, an option is to predict site‐specific DOC concentration with linear modeling and optical data predictors collected from high‐cost, high‐maintenance in situ spectrophotometers. This study sought to improve upon the accuracy and field costs of linear predictive DOC methods by using machine learning modeling coupled to low‐to‐zero cost predictors. To do this, we collected 16 months of in situ data (e.g., spectrophotometer attenuation, salinity, temperature), assembled freely available predictors (e.g., point in year, rainfall), and collected samples for DOC analysis, all in a salt marsh creek. At seasonal timescales, machine learning (coefficient of determination [R2] = 0.90) modestly improved upon the accuracy of linear methods (R2 = 0.80) but offered substantial instrumentation cost reductions (~ 90%) by requiring only cost‐free predictors (online data) or cost‐free predictors paired with low‐cost in situ predictors (temperature, salinity, depth). At intertidal timescales, linear methods proved ill‐equipped to predict DOC concentration compared to machine learning, and again, machine learning offered a substantial instrumentation cost reduction (~ 90%). Although our models were developed for and applicable to a single site, the use of machine learning with low‐to‐zero cost predictors provides a blueprint for others trying to model DOC dynamics and other analytes in any complex aquatic system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.