Neural network multispectral satellite images classification of volcanic ash plumes in a cloudy scenario

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. Si...

Full description

Bibliographic Details
Published in:Annals of Geophysics
Main Authors: Picchiani, M., Chini, M., Corradini, S., Merucci, L., Piscini, A., Del Frate, F.
Other Authors: Picchiani, M.; University of Rome Tor Vergata, Chini, M.; Luxembourg Institute of Science and Technology, Corradini, S.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione CNT, Roma, Italia, Merucci, L.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione CNT, Roma, Italia, Piscini, A.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione CNT, Roma, Italia, Del Frate, F.; University of Rome Tor Vergata, #PLACEHOLDER_PARENT_METADATA_VALUE#, Istituto Nazionale di Geofisica e Vulcanologia (INGV), Sezione ONT, Roma, Italia, University of Rome Tor Vergata
Format: Article in Journal/Newspaper
Language:English
Published: 2014
Subjects:
remote sensing
ash detection
neural networks
MODIS
04. Solid Earth::04.08. Volcanology::04.08.06. Volcano monitoring
04. Solid Earth::04.08. Volcanology::04.08.07. Instruments and techniques
05. General::05.02. Data dissemination::05.02.03. Volcanic eruptions
Eyjafjallajökull
Online Access:http://hdl.handle.net/2122/9710
https://doi.org/10.4401/ag-6638
Description
Summary: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 Eyjafjallajökull event, and equal to 74% for the Grimsvötn event. Published 5V. Sorveglianza vulcanica ed emergenze 5IT. Osservazioni satellitari JCR Journal open

Similar Items