The great eruption of the Icelandic Eyjafjallajokull volcano that occurred from the 14th of April to the 23rd of May 2010 injected large and dense ash clouds into the atmosphere, causing major international air traffic disruption worldwide. The possibility offered by space-based sensors to monitor in near real time the phenomenon evolution, seems to be the most effective way to mitigate the aviation hazard. In this work we propose an innovative approach to the volcanic ash mass retrieval based on neural networks. In comparison with the multispectral TIR sensors' classical techniques based on the brightness temperature difference in the 11 and 12 μm channels, and radiative transfer model calculations, the proposed algorithm has shown similar accuracy and faster computation. A set of MODIS images collected during the Eyjafjallajokull eruption has been analyzed and the ash maps obtained with the Neural Network approach have been compared with the corresponding maps retrieved with the procedure based on the brightness temperature difference.
Picchiani, M., Chini, M., Corradini, S., Merucci, L., Sellitto, P., DEL FRATE, F., et al. (2011). Volcanic ash retrieval from IR multispectral measurements by means of neural networks: An analysis of the Eyjafjallajokull eruption. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2011 (pp.3546-3549). IEEE [10.1109/IGARSS.2011.6049987].
Volcanic ash retrieval from IR multispectral measurements by means of neural networks: An analysis of the Eyjafjallajokull eruption
DEL FRATE, FABIO;
2011-01-01
Abstract
The great eruption of the Icelandic Eyjafjallajokull volcano that occurred from the 14th of April to the 23rd of May 2010 injected large and dense ash clouds into the atmosphere, causing major international air traffic disruption worldwide. The possibility offered by space-based sensors to monitor in near real time the phenomenon evolution, seems to be the most effective way to mitigate the aviation hazard. In this work we propose an innovative approach to the volcanic ash mass retrieval based on neural networks. In comparison with the multispectral TIR sensors' classical techniques based on the brightness temperature difference in the 11 and 12 μm channels, and radiative transfer model calculations, the proposed algorithm has shown similar accuracy and faster computation. A set of MODIS images collected during the Eyjafjallajokull eruption has been analyzed and the ash maps obtained with the Neural Network approach have been compared with the corresponding maps retrieved with the procedure based on the brightness temperature difference.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
