Online Program Home
My Program

Abstract Details

Activity Number: 319
Type: Contributed
Date/Time: Tuesday, August 2, 2016 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistics in Imaging
Abstract #319995 View Presentation
Title: Investigating Volcano Behavior with Novel Statistical and Technological Approaches
Author(s): Igor Barahona* and Luis Javier Alvarez and Antonio Sarmiento and Octavio Barahona
Companies: CONACYT-UNAM and Unidad Cuernavaca, Universidad Nacional and Unidad Cuernavaca, Universidad Nacional and Unidad Cuernavaca, Universidad Nacional
Keywords: Image pattern recognition ; Popocatepelt ; Nonlinear time series ; Dynamic systems ; Chaos ; Multivariate statistics.
Abstract:

Organizations specialized on disaster prevention take pictures of Popocatepelt volcano in Mexico every minute. Proper and accurate investigation of these pictures could be of great interest for disaster prevention and civil protection.

Using the methodology of pattern recognition, we apply concepts of discrete dynamic systems and non-linear time series to investigate a set of digital images of Popocatepetl volcano to identify different stages of its eruptive activity. We use packages 'ripa', 'fractal' and 'tseriesChaos' of "R" for data analysis.

Results allow us to identify the most relevant changes in volcano's behaviour and characterise the type of process corresponding to its signals. While this methodologies are well known in photography, music and energy industry, their application for investigating volcanoes represents a novel contribution.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association