A joint project of the Graduate School, Peabody College, and the Jean & Alexander Heard Library

Title page for ETD etd-03202015-110058


Type of Document Master's Thesis
Author Gray, Tami Michelle
Author's Email Address tami.m.gray@vanderbilt.edu
URN etd-03202015-110058
Title Automatic Volcanic Ash Detection from MODIS Observations using a Back-Propagation Neural Network
Degree Master of Science
Department Earth and Environmental Sciences
Advisory Committee
Advisor Name Title
Ralf Bennartz, Ph.D. Committee Chair
Calvin Miller, Ph.D. Committee Member
David Jon Furbish, Ph.D. Committee Member
Keywords
  • neural network
  • volcanic ash
  • MODIS
Date of Defense 2015-03-20
Availability unrestricted
Abstract
Due to the climate effects and aviation threats of volcanic eruptions, it is important to accurately locate ash in the atmosphere. This study aims to explore the accuracy and reliability of training a neural network to identify cases of ash using observations from the Moderate Resolution Imaging Spectroradiometer (MODIS). Satellite images were obtained for the following eruptions: Kasatochi, Aleutian Islands, 2008; Okmok, Aleutian Islands, 2008; Grímsvötn, northeastern Iceland, 2011; Chaitén, southern Chile, 2008; Puyehue-Cordón Caulle, central Chile, 2011; Sangeang Api, Indonesia, 2014; and Kelut, Indonesia, 2014. The Hybrid Single Particle Lagrangian Integrated Trajectory Model (HYSPLIT) was used to obtain ash concentrations for the same archived eruptions. A back-propagation neural network was then trained using brightness temperature differences as inputs obtained via the following band combinations: 12-11-μm, 11-8.6-μm, 11-7.3-μm, and 11-μm. Using the ash concentrations determined via HYSPLIT, a flag was created to differentiate between ash (1) and no ash (0) and used as output. When neural network output was compared to the test dataset, 93% of pixels containing ash were correctly identified and 7% were missed. Nearly 100% of pixels containing SO2-rich ash were correctly identified.
Files
  Filename       Size       Approximate Download Time (Hours:Minutes:Seconds) 
 
 28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access 
  Gray.pdf 5.90 Mb 00:27:18 00:14:02 00:12:17 00:06:08 00:00:31

Browse All Available ETDs by ( Author | Department )

If you have more questions or technical problems, please Contact LITS.