You are here

Forecasting Volcanic Activity Using An Event Tree Analysis System and Logistic Regression

Download pdf | Full Screen View

Date Issued:
2012
Abstract/Description:
Forecasts of short term volcanic activity are generated using an event tree process that is driven by a set of empirical statistical models derived through logistic regression. Each of the logistic models are constructed from a sparse and geographically diverse dataset that was assembled from a collection of historic volcanic unrest episodes. The dataset consists of monitoring measurements (e.g. seismic), source modeling results, and historic eruption information. Incorporating this data into a single set of models provides a simple mechanism for simultaneously accounting for the geophysical changes occurring within the volcano and the historic behavior of analog volcanoes. A bootstrapping analysis of the training dataset allowed for the estimation of robust logistic model coefficients. Probabilities generated from the logistic models increase with positive modeling results, escalating seismicity, and high eruption frequency. The cross validation process produced a series of receiver operating characteristic (ROC) curves with areas ranging between 0.78 - 0.81, which indicate the algorithm has good predictive capabilities. In addition, ROC curves also allowed for the determination of a false positive rate and optimum detection threshold for each stage of the algorithm. The results demonstrate the logistic models are highly transportable and can compete with, and in some cases outperform, non-transportable empirical models trained with site specific information. The incorporation of source modeling results into the event tree's decision making process has begun the transition of volcano monitoring applications from simple mechanized pattern recognition algorithms to a physical model based forecasting system.
Title: Forecasting Volcanic Activity Using An Event Tree Analysis System and Logistic Regression.
12 views
6 downloads
Name(s): Junek, William, Author
Jones, W, Committee Chair
Simaan, Marwan, Committee Member
Foroosh, Hassan, Committee Member
Woods, Mark, Committee Member
University of Central Florida, Degree Grantor
Type of Resource: text
Date Issued: 2012
Publisher: University of Central Florida
Language(s): English
Abstract/Description: Forecasts of short term volcanic activity are generated using an event tree process that is driven by a set of empirical statistical models derived through logistic regression. Each of the logistic models are constructed from a sparse and geographically diverse dataset that was assembled from a collection of historic volcanic unrest episodes. The dataset consists of monitoring measurements (e.g. seismic), source modeling results, and historic eruption information. Incorporating this data into a single set of models provides a simple mechanism for simultaneously accounting for the geophysical changes occurring within the volcano and the historic behavior of analog volcanoes. A bootstrapping analysis of the training dataset allowed for the estimation of robust logistic model coefficients. Probabilities generated from the logistic models increase with positive modeling results, escalating seismicity, and high eruption frequency. The cross validation process produced a series of receiver operating characteristic (ROC) curves with areas ranging between 0.78 - 0.81, which indicate the algorithm has good predictive capabilities. In addition, ROC curves also allowed for the determination of a false positive rate and optimum detection threshold for each stage of the algorithm. The results demonstrate the logistic models are highly transportable and can compete with, and in some cases outperform, non-transportable empirical models trained with site specific information. The incorporation of source modeling results into the event tree's decision making process has begun the transition of volcano monitoring applications from simple mechanized pattern recognition algorithms to a physical model based forecasting system.
Identifier: CFE0004253 (IID), ucf:49517 (fedora)
Note(s): 2012-05-01
Ph.D.
Engineering and Computer Science, Electrical Engineering and Computer Science
Doctoral
This record was generated from author submitted information.
Subject(s): Logistic Regression -- Volcanic Eruption Forecasting -- Event Tree -- Remote Sensing
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFE0004253
Restrictions on Access: public 2012-05-15
Host Institution: UCF

In Collections