Aproximación a la metodología basada en árboles de decisión (CART): Mortalidad hospitalaria del infarto agudo de miocardio Approach to the methodology of classification and regression trees

The highway C-28 is located in the Central Pyrenees and links the Aran valley with Catalonia along 20 km over the Bonaigua Pass. It constitutes a key access route for winter visitors. Most of the slopes affecting the road face to the south, with heights varying between 1600 and 2300 meters. We started from 12 years of meteorological and avalanche data collected by the local avalanche warning service of Aran Valley. Weather data were obtained from two automatic weather stations and a flowcapt, whereas avalanche activity was manually recorded in a GIS. We selected several weather parameters including snow drift, elapsed time, trend and categorical parameters. Using a classification tree method, we have developed a model to determine periods of significant avalanche activity in terms of the predefined avalanche day concept. The model is performed for the entire road in a combined analysis and also for three individual sub-areas within the Pass. Results showed that conventional factors describing snow depth were more significant than temperature and precipitation factors. Derived snow drift parameters from snow depth and water precipitacion showed more importance than drift data from the flowcapt. Radiation and wind direction variables had low importance in all the tests. The detailed analysis by subareas has not achieved the objective due to the reduction of the database. However, it has allowed to confirm the differences between one of the sub-areas and the dynamics of the rest of the highway.

/pdf/a-model-for-avalanche-forecasting-on-the-bonaigua-pass-spain-1mdkvcxl0n.pdf

Pablo Gorospe

Papers

A Model for Avalanche Forecasting on the Bonaigua Pass, Spain, Using Classification Trees