Abstract
Abstract. Canada's water cycle is driven mainly by snowmelt. Snow water equivalent (SWE) is the snow-related variable that is most commonly used in hydrology, as it expresses the total quantity of water (solid and liquid) stored in the snowpack. Measurements of SWE are, however, expensive and not continuously accessible in real time. This motivates a search for alternative ways of estimating SWE from measurements that are more widely available and continuous over time. SWE can be calculated by multiplying snow depth by the bulk density of the snowpack. Regression models proposed in the literature first estimate snow density and then calculate SWE. More recently, a novel approach to this problem has been developed and is based on an ensemble of multilayer perceptrons (MLPs). Although this approach compared favorably with existing regression models, snow density values at the lower and higher ends of the range remained inaccurate. Here, we improve upon this recent method for determining SWE from snow depth. We show the general applicability of the method through the use of a large data set of 234 779 snow depth–density–SWE records from 2878 nonuniformly distributed sites across Canada. These data cover almost 4 decades of snowfall. First, it is shown that the direct estimation of SWE produces better results than the estimation of snow density, followed by the calculation of SWE. Second, testing several artificial neural network (ANN) structural characteristics improves estimates of SWE. Optimizing MLP parameters separately for each snow climate class gives a greater representation of the geophysical diversity of snow. Furthermore, the uncertainty of snow depth measurements is included for a more realistic estimation. A comparison with commonly used regression models reveals that the ensemble of MLPs proposed here leads to noticeably more accurate estimates of SWE. This study thus shows that delving deeper into ANN theory helps improve SWE estimation.
Highlights
Snowmelt plays a major role in the hydrological cycle of many regions of the world. Casson et al (2018) determined that snow accumulation and melt are the main drivers of the spring freshet in the Canadian subarctic region, and Pomeroy et al (2011) demonstrated that over 80 % of the annual runoff in the Canadian Prairies is derived from snowmelt
In Sect. 4.1.3, we discuss the results used for the determination of the number of neurons and number of epoch, for single MLP ensemble model (SMLP) and MMLP models individually
The reliability part of the CRPS increases later when Snow water equivalent (SWE) is the target variable compared with when the target is variable density (Fig. 5b). This behavior is consistent with the ignorance score, which has its minimum at epoch 20 in Fig. 5f, whereas in Fig. 5c, the ignorance score for snow density increases from the beginning
Summary
Snowmelt plays a major role in the hydrological cycle of many regions of the world. Casson et al (2018) determined that snow accumulation and melt are the main drivers of the spring freshet in the Canadian subarctic region, and Pomeroy et al (2011) demonstrated that over 80 % of the annual runoff in the Canadian Prairies is derived from snowmelt. The following two studies uses ANNs to model the relationship between snow depth and snow density, which could be used to obtain estimates of SWE. Odry et al (2020) applied ANNs to estimate snow density from snow depth, but they focused on developing a method that would be applicable over a very large spatial extent In their study, they used almost 40 000 measurements from approximately 400 nonuniformly distributed sites across the province of Quebec, Canada. We build a model to estimate SWE from in situ snow depth measurements and several indicators derived from gridded meteorological time series.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
