Open Access
Operational Decision Tree Avalanche Forecasting
Walter Rosenthal,Kelly Elder,Robert E. Davis +2 more
- 01 Jan 2002
pp 152-158
TL;DR: In this article, decision tree models of maximum avalanche size class run daily at Mammoth Mountain, California, and a complete 19-year data set yields a pair of decision trees forecasting both maximum size class and maximum crown size over the entire mountain.
read more
Abstract: Decision tree models ofmaximum avalanche size class run daily at Mammoth Mountain, California. A classification tree grown on an eight-year subset of all weather and avalanche records shows an absolute accuracy on avalanche control days of from about 60-70% in a given year; accepting overestimates increases this to 70-80%. Errors arise from the rarity of large events, exclusion ofthe smallest most frequent events, and tree sensitivity to small changes in key predictor variables. A complete 19-year data set yields a pair of decision trees forecasting both maximum size class and maximum crown size over the entire mountain. Tested against a twentieth year, the size class tree may be more accurate for extreme events but performed slightly worse overall than the original tree. Coupling the size class and crown trees identified both class 5 avalanches during the test year. A third set oftrees, driven by hourly data from a remote instrument network, distributes maximum class and crown sizes over geographic sub-regions ofthe mountain. These are striking for both small size and low misclassification rate. Ifa major source oferror is chaotic avalanche behavior, decision trees may prove most valuable for providing probability estimates from given sets of initial conditions.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Classification trees as a tool for operational avalanche forecasting on the Seward Highway, Alaska
TL;DR: In this paper, the authors used a classification tree with both equal and unequal misclassifications costs to train a model for days with significant avalanche activity on the Seward Highway in Alaska.
68
Examining spring wet slab and glide avalanche occurrence along the going-to-the-sun road corridor, glacier national park, montana, usa
TL;DR: In this article, the authors investigated the timing of wet slab and glide avalanche occurrence along the GTSR from 2003 to 2011 using meteorological and snowpack data from two high-elevation weather stations, one SNOTEL site, and an avalanche database.
54
CUES—a study site for measuring snowpack energy balance in the Sierra Nevada
TL;DR: CUES as discussed by the authors is one of only five high altitude mountain sites in the Western US where a full suite of energy balance components are measured, including scans by an automated terrestrial LiDAR, passive and active microwave imaging of snow stratigraphy, microscopic images of snow grains, snowwater equivalent from different types of snow pillows, snowmelt from lysimeters, and concentration of impurities in the snowpack.
A data efficient machine learning model for autonomous operational avalanche forecasting
Manesh Chawla,Amreek Singh +1 more
TL;DR: A data efficient machine learning classifier using the technique of Random Forest is proposed which can be trained with significantly lesser training data compared to other avalanche forecasting models and it generates useful outputs to minimise and quantify uncertainty.
An examination of the snow and avalanche hazard on the Milford Road, Fiordland, New Zealand
Jordy Hendrikx
- 01 Jan 2005
TL;DR: Avalanches pose a significant natural hazard in many parts of the world and are being managed in a number of new and traditional methods, such as avalanche hazard index (AHI) and probability of death to individuals (PDI) as discussed by the authors.
8
References
•Book
Classification and regression trees
Leo Breiman
- 01 Jan 1983
TL;DR: The methodology used to construct tree structured rules is the focus of a monograph as mentioned in this paper, covering the use of trees as a data analysis method, and in a more mathematical framework, proving some of their fundamental properties.
22.7K
A Between-Storm Indicator of Avalanche Activity
Robert E. Davis,Kelly Elder +1 more
- 01 Jan 2000
TL;DR: In this paper, the authors used the results of the previous investigation to guide case studies taking a closer look at the temperature index, which has the name vapor gradient index (VGI), accumulates each day between storms by adding the current day's value VGI' with the accumulated value from the previous day.
Power‐laws and snow avalanches
TL;DR: In this article, the authors present evidence of frequency-size power-laws in several groups of snow avalanche paths, which may be used for quantifying the risk of large snow avalanches within a group of avalanche paths.