Publications

Petracca, I; De Santis, D; Picchiani, M; Corradini, S; Guerrieri, L; Prata, F; Merucci, L; Stelitano, D; Del Frate, F; Salvucci, G; Schiavon, G (2022). Volcanic cloud detection using Sentinel-3 satellite data by means of neural networks: the Raikoke 2019 eruption test case. ATMOSPHERIC MEASUREMENT TECHNIQUES, 15(24), 7195-7210.

Abstract
Accurate automatic volcanic cloud detection by means of satellite data is achallenging task and is of great concern for both the scientific community andaviation stakeholders due to well-known issues generated by strong eruptionevents in relation to aviation safety and health impacts. In this context,machine learning techniques applied to satellite data acquired from recentspaceborne sensors have shown promising results in the last few years. This work focuses on the application of a neural-network-based model toSentinel-3 SLSTR (Sea and Land Surface Temperature Radiometer) daytimeproducts in order to detect volcanic ash plumes generated by the 2019Raikoke eruption. A classification of meteorological clouds and of othersurfaces comprising the scene is also carried out. The neural network hasbeen trained with MODIS (Moderate Resolution Imaging Spectroradiometer)daytime imagery collected during the 2010 Eyjafjallajokull eruption. Thesimilar acquisition channels of SLSTR and MODIS sensors and the comparablelatitudes of the eruptions permit an extension of the approach to SLSTR,thereby overcoming the lack in Sentinel-3 products collected in previousmid- to high-latitude eruptions. The results show that the neural network modelis able to detect volcanic ash with good accuracy if compared to RGBvisual inspection and BTD (brightness temperature difference) procedures.Moreover, the comparison between the ash cloud obtained by the neuralnetwork (NN) and a plume mask manually generated for the specific SLSTRimages considered shows significant agreement, with an F-measure of around0.7. Thus, the proposed approach allows for an automatic image classificationduring eruption events, and it is also considerably faster thantime-consuming manual algorithms. Furthermore, the whole image classification indicates the overall reliability of the algorithm, particularly for recognition and discrimination between volcanic clouds and other objects.

DOI:
10.5194/amt-15-7195-2022

ISSN:
1867-8548