Neural network multispectral satellite images classification of volcanic ash plumes in a cloudy scenario
<div class="WordSection1"><div class="page" title="Page 1"><div class="layoutArea"><div class="column"><p><span>This work shows the potential use of neural networks in the characterization of eruptive events monito...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Istituto Nazionale di Geofisica e Vulcanologia (INGV)
2015-03-01
|
Series: | Annals of Geophysics |
Subjects: | |
Online Access: | http://www.annalsofgeophysics.eu/index.php/annals/article/view/6638 |
id |
doaj-9efbea6f566d43bb9085e707483499b3 |
---|---|
record_format |
Article |
spelling |
doaj-9efbea6f566d43bb9085e707483499b32020-11-24T22:43:56ZengIstituto Nazionale di Geofisica e Vulcanologia (INGV)Annals of Geophysics1593-52132037-416X2015-03-0157010.4401/ag-66385985Neural network multispectral satellite images classification of volcanic ash plumes in a cloudy scenarioMatteo Picchiani0Marco Chini1Stefano Corradini2Luca Merucci3Alessandro Piscini4Fabio Del Frate5Dipartimento di Ingegneria Civile e Ingegneria Informatica, Università di Roma Tor Vergata, RomeLuxembourg Institute of Science and Technology, Environmental Research and Innovation Department, BelvauxIstituto Nazionale di Geofisica e Vulcanologia, Geomagnetismo, Aeronomia e Geofisica Ambientale, RomeIstituto Nazionale di Geofisica e Vulcanologia, CNT, RomeIstituto Nazionale di Geofisica e Vulcanologia, CNT, RomeDipartimento di Ingegneria Civile e Ingegneria Informatica, Università di Roma Tor Vergata, Rome<div class="WordSection1"><div class="page" title="Page 1"><div class="layoutArea"><div class="column"><p><span>This work shows the potential use of neural networks in the characterization of eruptive events monitored by satellite, through fast and automatic classification of multispectral images. The algorithm has been developed for the MODIS instrument and can easily be extended to other similar sensors. Six classes have been defined paying particular attention to image regions that represent the different surfaces that could possibly be found under volcanic ash clouds. Complex cloudy scenarios composed by images collected during the Icelandic eruptions of the Eyjafjallajökull (2010) and Grimsvötn (2011) volcanoes have been considered as test cases. A sensitivity analysis on the MODIS TIR and VIS channels has been performed to optimize the algorithm. The neural network has been trained with the first image of the dataset, while the remaining data have been considered as independent validation sets. Finally, the neural network classifier’s results have been compared with maps classified with several interactive procedures performed in a consolidated operational framework. This comparison shows that the automatic methodology proposed achieves a very promising performance, showing an overall accuracy greater than 84%, for the Eyjafjalla - jökull event, and equal to 74% for the Grimsvötn event. </span></p></div></div></div><p><em><br /></em></p><p><em><br /></em></p></div><em><br clear="all" /></em>http://www.annalsofgeophysics.eu/index.php/annals/article/view/6638Neural Networks, Volcanic Ash detection, BTD |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Matteo Picchiani Marco Chini Stefano Corradini Luca Merucci Alessandro Piscini Fabio Del Frate |
spellingShingle |
Matteo Picchiani Marco Chini Stefano Corradini Luca Merucci Alessandro Piscini Fabio Del Frate Neural network multispectral satellite images classification of volcanic ash plumes in a cloudy scenario Annals of Geophysics Neural Networks, Volcanic Ash detection, BTD |
author_facet |
Matteo Picchiani Marco Chini Stefano Corradini Luca Merucci Alessandro Piscini Fabio Del Frate |
author_sort |
Matteo Picchiani |
title |
Neural network multispectral satellite images classification of volcanic ash plumes in a cloudy scenario |
title_short |
Neural network multispectral satellite images classification of volcanic ash plumes in a cloudy scenario |
title_full |
Neural network multispectral satellite images classification of volcanic ash plumes in a cloudy scenario |
title_fullStr |
Neural network multispectral satellite images classification of volcanic ash plumes in a cloudy scenario |
title_full_unstemmed |
Neural network multispectral satellite images classification of volcanic ash plumes in a cloudy scenario |
title_sort |
neural network multispectral satellite images classification of volcanic ash plumes in a cloudy scenario |
publisher |
Istituto Nazionale di Geofisica e Vulcanologia (INGV) |
series |
Annals of Geophysics |
issn |
1593-5213 2037-416X |
publishDate |
2015-03-01 |
description |
<div class="WordSection1"><div class="page" title="Page 1"><div class="layoutArea"><div class="column"><p><span>This work shows the potential use of neural networks in the characterization of eruptive events monitored by satellite, through fast and automatic classification of multispectral images. The algorithm has been developed for the MODIS instrument and can easily be extended to other similar sensors. Six classes have been defined paying particular attention to image regions that represent the different surfaces that could possibly be found under volcanic ash clouds. Complex cloudy scenarios composed by images collected during the Icelandic eruptions of the Eyjafjallajökull (2010) and Grimsvötn (2011) volcanoes have been considered as test cases. A sensitivity analysis on the MODIS TIR and VIS channels has been performed to optimize the algorithm. The neural network has been trained with the first image of the dataset, while the remaining data have been considered as independent validation sets. Finally, the neural network classifier’s results have been compared with maps classified with several interactive procedures performed in a consolidated operational framework. This comparison shows that the automatic methodology proposed achieves a very promising performance, showing an overall accuracy greater than 84%, for the Eyjafjalla - jökull event, and equal to 74% for the Grimsvötn event. </span></p></div></div></div><p><em><br /></em></p><p><em><br /></em></p></div><em><br clear="all" /></em> |
topic |
Neural Networks, Volcanic Ash detection, BTD |
url |
http://www.annalsofgeophysics.eu/index.php/annals/article/view/6638 |
work_keys_str_mv |
AT matteopicchiani neuralnetworkmultispectralsatelliteimagesclassificationofvolcanicashplumesinacloudyscenario AT marcochini neuralnetworkmultispectralsatelliteimagesclassificationofvolcanicashplumesinacloudyscenario AT stefanocorradini neuralnetworkmultispectralsatelliteimagesclassificationofvolcanicashplumesinacloudyscenario AT lucamerucci neuralnetworkmultispectralsatelliteimagesclassificationofvolcanicashplumesinacloudyscenario AT alessandropiscini neuralnetworkmultispectralsatelliteimagesclassificationofvolcanicashplumesinacloudyscenario AT fabiodelfrate neuralnetworkmultispectralsatelliteimagesclassificationofvolcanicashplumesinacloudyscenario |
_version_ |
1725693792206454784 |