Random forests as a tool to understand the snow depth distribution and its evolution in mountain areas

Revuelto, Jesús; Billecocq, Paul; Tuzet, François; Cluzet, Bertrand; Lamare, Maxim; Larue, Fanny; Dumont, Marie

doi:10.1002/hyp.13951

Cited by 26 publications

(29 citation statements)

References 77 publications

(143 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Broxton et al (2019) applied artificial neural networks 115 to estimate snow density, which was then combined with aerial lidar snow depth to predict SWE. Revuelto et al (2020) used random forests to predict lidar snow depth distribution from several topographic predictors. King et al (2020) used random forests for bias correction of a SWE data assimilation product.…”

Section: )mentioning

confidence: 99%

Spatial Patterns of Snow Distribution for Improved Earth System Modelling in the Arctic

Bennett

Miller

Busey

et al. 2021

Preprint

View full text Add to dashboard Cite

Abstract. The spatial distribution of snow plays a vital role in Arctic climate, hydrology, and ecology due to its fundamental influence on the water balance, thermal regimes, vegetation, and carbon flux. However, for earth system modelling, the spatial distribution of snow is not well understood, and therefore, it is not well modeled, which can lead to substantial uncertainties in snow cover representations. To capture key hydro-ecological controls on snow spatial distribution, we carried out intensive field studies over multiple years for two small (2017–2019, ~2.5 km2) sub-Arctic study sites located on the Seward Peninsula of Alaska. Using an intensive suite of field observations (> 22,000 data points), we developed simple models of spatial distribution of snow water equivalent (SWE) using factors such as topographic characteristics, vegetation characteristics based on greenness (normalized different vegetation index, NDVI), and a simple metric for approximating winds. The most successful model was the random forest using both study sites and all years, which was able to accurately capture the complexity and variability of snow characteristics across the sites. Approximately 86 % of the SWE distribution could be accounted for, on average, by the random forest model at the study sites. Factors that impacted year-to-year snow distribution included NDVI, elevation, and a metric to represent coarse microtopography (topographic position index, or TPI), while slope, wind, and fine microtopography factors were less important. The models were used to predict SWE at the locations through the study area and for all years. The characterization of the SWE spatial distribution patterns and the statistical relationships developed between SWE and its impacting factors will be used for the improvement of snow distribution modelling in the Department of Energy’s earth system model, and to improve understanding of hydrology, topography, and vegetation dynamics in the Arctic and sub-Arctic regions of the globe.

show abstract

Section: )mentioning

confidence: 99%

Spatial Patterns of Snow Distribution for Improved Earth System Modelling in the Arctic

Bennett

Miller

Busey

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Since tan 2 ζ is the same as 2µ 2 (e.g., Löwe and Helbig, 2012), we here derive sqS from 2µ 2 . Several other studies used σ z as terrain parameter (e.g., Roesch et al, 2001). Here, we were interested in finding dominant scaling variables that correlate consistently across scales with σ HS .…”

Section: Deriving a New Scale-independent Fractionalmentioning

confidence: 99%

“…A fSCA plays a key role in modeling physical processes for various applications such as weather forecasts (e.g., Douville et al, 1995;Doms et al, 2011), climate simula-N. Helbig et al: Fractional snow-covered area tions (e.g., Roesch et al, 2001;Mudryk et al, 2020) and avalanche forecasting (Bellaire and Jamieson, 2013;Horton and Jamieson, 2016;Vionnet et al, 2016). As climate warms, fSCA is an highly relevant indicator for spatial snow-cover changes in climate projections (e.g., Mudryk et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

“…Parametric SCD curves have disadvantages for practical applications such as numerical stability, computational efficiency and assuming an unimodal distribution which might be less appropriate for large grid cells covering heterogeneous surface such as mountainous terrain (e.g., Essery and Pomeroy, 2004;Swenson and Lawrence, 2012). Various closed functional forms for fSCAs are therefore applied in land surface and climate models (e.g., Douville et al, 1995;Roesch et al, 2001;Yang et al, 1997;Niu and Yang, 2007;Su et al, 2008;Swenson and Lawrence, 2012). Most of these parameterizations use simple relationships between fSCA and spatial mean HS or SWE.…”

Section: Introductionmentioning

confidence: 99%

“…Most of these parameterizations use simple relationships between fSCA and spatial mean HS or SWE. Since topography strongly determines the spatial snow depth or snow water equivalent distribution (Clark et al, 2011), in the past, terrain characteristics were mostly heuristically introduced in closed form curves to account for subgrid terrain influences on fSCA (e.g., Douville et al, 1995;Roesch et al, 2001;Swenson and Lawrence, 2012). To verify the commonly applied closed forms of fSCA, Essery and Pomeroy (2004) integrated lognormal SWE distributions and fitted the parametric SCD curves.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fractional snow-covered area: scale-independent peak of winter parameterization

Helbig¹,

Bühler²,

Eberhard³

et al. 2021

The Cryosphere

Self Cite

View full text Add to dashboard Cite

Abstract. The spatial distribution of snow in the mountains is significantly influenced through interactions of topography with wind, precipitation, shortwave and longwave radiation, and avalanches that may relocate the accumulated snow. One of the most crucial model parameters for various applications such as weather forecasts, climate predictions and hydrological modeling is the fraction of the ground surface that is covered by snow, also called fractional snow-covered area (fSCA). While previous subgrid parameterizations for the spatial snow depth distribution and fSCA work well, performances were scale-dependent. Here, we were able to confirm a previously established empirical relationship of peak of winter parameterization for the standard deviation of snow depth σHS by evaluating it with 11 spatial snow depth data sets from 7 different geographic regions and snow climates with resolutions ranging from 0.1 to 3 m. An enhanced performance (mean percentage errors, MPE, decreased by 25 %) across all spatial scales ≥ 200 m was achieved by recalibrating and introducing a scale-dependency in the dominant scaling variables. Scale-dependent MPEs vary between −7 % and 3 % for σHS and between 0 % and 1 % for fSCA. We performed a scale- and region-dependent evaluation of the parameterizations to assess the potential performances with independent data sets. This evaluation revealed that for the majority of the regions, the MPEs mostly lie between ±10 % for σHS and between −1 % and 1.5 % for fSCA. This suggests that the new parameterizations perform similarly well in most geographical regions.

show abstract

Exploring the Potential of Long Short-Term Memory Networks for Improving Understanding of Continental- and Regional-Scale Snowpack Dynamics

Wang

Gupta

Zeng

et al. 2021

Preprint

View full text Add to dashboard Cite

Introduction The Problem of Continental-Scale Estimation of Snow Water EquivalentAccurate monitoring of the large-scale dynamics of snowpack is essential for understanding the details of climate dynamics and climate change (Robinson et al., 1993). Warming under a changing climate is expected to cause snowpack to melt earlier in the year (Xiao, 2021; and to reduce the amount of water stored as snow (Musselman et al., 2021;Nijssen et al., 2001). This is expected to have broad and potentially severe impacts to ecosystem productivity (Boisvenue & Running, 2006), winter flood risk (Musselman et al., 2018), groundwater recharge (Ford et al., 2020), agriculture and food security (Qin et al., 2020;Shindell et al., 2012), wildfire hazard (Westerling, 2016), and frequency and severity of drought (Arevalo et al., 2021). In western North America, snow is the primary source of water and streamflow (Li et al., 2017), while globally it supports the water supply needs for more than 1 billion people (Barnett et al., 2005). Therefore, having accurate estimates of the quantity of water stored in snowpack, called snow water equivalent (SWE), is critical for the forecasting and management of water supply and hydropower (Bales et al., 2006;Mankin et al., 2015).

show abstract

Random forests as a tool to understand the snow depth distribution and its evolution in mountain areas

Cited by 26 publications

References 77 publications

Spatial Patterns of Snow Distribution for Improved Earth System Modelling in the Arctic

Spatial Patterns of Snow Distribution for Improved Earth System Modelling in the Arctic

Fractional snow-covered area: scale-independent peak of winter parameterization

Exploring the Potential of Long Short-Term Memory Networks for Improving Understanding of Continental- and Regional-Scale Snowpack Dynamics

Contact Info

Product

Resources

About