Examining spring wet slab and glide avalanche occurrence along the Going-to-the-Sun Road corridor, Glacier National Park, Montana, USA

Peitzsch, Erich H.; Hendrikx, Jordy; Fagre, Daniel B.; Reardon, Blase A.

doi:10.1016/j.coldregions.2012.01.012

Cited by 37 publications

(38 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…correlation analysis (Perla, 1970); multivariate discriminant function analysis (Bois et al, 1975;Föhn et al, 1977); nearest neighbors (Buser, 1983); expert systems (Schweizer and Föhn, 1996); classification and regression trees (Davis et al, 1999); and cross validated classification trees (Hendrikx et al, 2005;Peitzsch et al, 2012a). For this study we first reviewed the relationship between the meteorological data and avalanche days using a univariate analysis using the non-parametric Kolmogorov-Smirnov two-sample test.…”

Section: Methodsmentioning

confidence: 99%

“…For this study we first reviewed the relationship between the meteorological data and avalanche days using a univariate analysis using the non-parametric Kolmogorov-Smirnov two-sample test. Following this, we then elected to use cross validated classifications trees as used by Hendrikx et al (2005) and Peitzsch et al (2012a). This technique was used as it provides a clearer and often more easily understood interpretations of complex interactions than other model constructions (Davis et al, 1999;Hendrikx et al, 2005), which makes them ideal for operational forecasting.…”

Section: Methodsmentioning

confidence: 99%

“…Following this, we then elected to use cross validated classifications trees as used by Hendrikx et al (2005) and Peitzsch et al (2012a). This technique was used as it provides a clearer and often more easily understood interpretations of complex interactions than other model constructions (Davis et al, 1999;Hendrikx et al, 2005), which makes them ideal for operational forecasting. A full discussion of classification and regression trees is given by Breiman et al (1993) and for an avalanche application in Hendrikx et al (2005).…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Classification trees as a tool for operational avalanche forecasting on the Seward Highway, Alaska

Hendrikx

Murphy²,

Onslow³

2014

Cold Regions Science and Technology

Self Cite

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Classification trees as a tool for operational avalanche forecasting on the Seward Highway, Alaska

Hendrikx

Murphy²,

Onslow³

2014

Cold Regions Science and Technology

Self Cite

View full text Add to dashboard Cite

“…Cold events occur at the beginning of the winter season, for which the most important driving factors are air temperature, the sum of new snow and incoming shortwave radiation; warm events occur late in spring, for which the most important driving factors are snow surface temperature, air temperature and the change in snow depth. Another example is Peitzsch, Hendrikx, Fagre, and Reardon (2012), who found that air temperature and snowpack settlement appear to be the most important variables in glide avalanche occurrence.…”

Section: Resultsmentioning

confidence: 99%

Snow gliding susceptibility: the Monterosa Ski resort, NW Italian Alps

Maggioni¹,

Godone²,

Höller

et al. 2016

Journal of Maps

View full text Add to dashboard Cite

Snow gliding, though a slow process, should be considered as important as the faster snow avalanche flows, as it can similarly produce severe damage to buildings and infrastructure. Snow gliding depends on snowpack properties, land cover and terrain parameters. Among these driving factors, in this work, we focus on stationary factors, that is, those that are considered features related to terrain and land cover, in particular those that could be derived from a Digital Elevation Model or land use/cover maps: slope angle, aspect, roughness and land cover. We propose a geographical information system-based procedure to create a snow gliding susceptibility index and to produce a related snow gliding susceptibility map. We tested this procedure in the Aosta Valley (NW Italian Alps), where the Monterosa Ski resort is located. The map covers an area of about 338 km 2 at a scale of 1:50,000. The proposed procedure is seen as a valuable tool to help safety personnel at ski resorts as well as in other scenarios (e.g. road management) in the identification of areas most prone to snow gliding. ARTICLE HISTORY

show abstract

“…Classification trees are used for discrete, 5 categorical data while regression trees are used for continuous data. This technique has been used extensively on snow-related prediction, for example in snow mapping (Rosenthal and Dozier, 1996) and avalanche forecasting (Davis et al, 1999;Peitzsch et al, 2012), but it tends to overfit. Bagged (bootstrap-aggregated, Breiman, 1996) trees, with the most recent developments called random forests (Breiman, 2001), are ensemble methods whereby multiple trees are grown from random subsets of predictors, producing a weighted ensemble of trees.…”

Section: Bagged Treesmentioning

confidence: 99%

Using machine learning for real-time estimates of snow water equivalent in the watersheds of Afghanistan

Bair¹,

Calfa²,

Rittger³

et al. 2017

Preprint

View full text Add to dashboard Cite

10In many mountains, snowmelt provides most of the runoff. In Afghanistan, few ground-based measurements of the snow resource exist. Operational estimates use imagery from optical and passive microwave sensors, but with their limitations. An accurate approach reconstructs spatially distributed snow water equivalent (SWE) by calculating snowmelt backward from a remotely sensed date of disappearance, but reconstructed SWE estimates are available only retrospectively; they do not provide a forecast.To estimate SWE early in the snowmelt season, we consider physiographic and remotely-sensed information as predictors and 15 reconstructed SWE as the target. The period of analysis matches the AMSR-E radiometer's lifetime from 2003 to 2011, for the months of April through June. The spatial resolution of the predictions is 3.125 km, to match the resolution of a microwave brightness temperature product. Two machine learning techniques-bagged regression trees and feed-forward neural networksproduced similar mean results, with 0-14% bias and 46-48 mm RMSE on average. Daily SWE climatology and fractional snowcovered area are the most important predictors. We conclude that the methods can accurately estimate SWE during the snow season 20 in remote mountains.

show abstract

Examining spring wet slab and glide avalanche occurrence along the Going-to-the-Sun Road corridor, Glacier National Park, Montana, USA

Cited by 37 publications

References 12 publications

Classification trees as a tool for operational avalanche forecasting on the Seward Highway, Alaska

Classification trees as a tool for operational avalanche forecasting on the Seward Highway, Alaska

Snow gliding susceptibility: the Monterosa Ski resort, NW Italian Alps

Using machine learning for real-time estimates of snow water equivalent in the watersheds of Afghanistan

Contact Info

Product

Resources

About