In the last decade, video surveillance cameras have experienced a great technological advance, making capturing and processing of digital images and videos more reliable in many fields of application. Hence, video-camera-based systems appear as one of the techniques most widely used in the world for monitoring volcanoes, providing a low cost and handy tool in emergency phases, although the processing of large data volumes from continuous acquisition still represents a challenge. To make these systems more effective in cases of emergency, each pixel of the acquired images must be assigned to class labels to categorise them and to locate and segment the observable eruptive activity. This paper is focused on the detection and segmentation of volcanic ash plumes using convolutional neural networks. Two well-established architectures, the segNet and the U-Net, have been used for the processing of in situ images to validate their usability in the field of volcanology. The dataset fed into the two CNN models was acquired from in situ visible video cameras from a ground-based network (Etna_NETVIS) located on Mount Etna (Italy) during the eruptive episode of 24th December 2018, when 560 images were captured from three different stations: CATANIA-CUAD, BRONTE, and Mt. CAGLIATO. In the preprocessing phase, data labelling for computer vision was used, adding one meaningful and informative label to provide eruptive context and the appropriate input for the training of the machine-learning neural network. Methods presented in this work offer a generalised toolset for volcano monitoring to detect, segment, and track ash plume emissions. The automatic detection of plumes helps to significantly reduce the storage of useless data, starting to register and save eruptive events at the time of unrest when a volcano leaves the rest status, and the semantic segmentation allows volcanic plumes to be tracked automatically and allows geometric parameters to be calculated.
Ancient mining and quarrying activities left anthropogenic geomorphologies that have shaped the natural landscape and affected environmental equilibria. The artificial structures and their related effects on the surrounding environment are analyzed here to characterize the quarrying landscape in the southeast area of Rome in terms of its dimensions, typology, state of preservation and interface with the urban environment. The increased occurrence of sinkhole events in urban areas has already been scientifically correlated to ancient cavities under increasing urban pressure. In this scenario, additional interacting anthropogenic factors, such as the aerial bombardments perpetrated during the Second World War, are considered here. These three factors have been investigated by employing a combined geomatic methodology. Information on air raids has been organized in vector archives. A dataset of historical aerial photographs has been processed into Digital Surface Models and orthomosaics to reconstruct the quarry landscape and its evolution, identify typologies of exploitation and forms of collapse and corroborate the discussion concerning the induced historical and recent subsidence phenomena, comparing these outputs with photogrammetric products obtained from recent satellite data. Geological and urbanistic characterization of the study area allowed a better connection between these historical and environmental factors. In light of the information gathered so far, SAR interferometric products allowed a preliminary interpretation of ground instabilities surrounding historical quarries, air raids and recent subsidence events. Various sub-areas of the AOI where the presence of the considered factors also corresponds to areas in slight subsidence in the SAR velocity maps have been highlighted. Bivariate hotspot analysis allowed substantiating the hypothesis of a spatial correlation between these multiple aspects.