http://hdl.handle.net/20.500.12160/122 Wed, 27 May 2026 18:48:12 GMT 2026-05-27T18:48:12Z http://hdl.handle.net/20.500.12160/2957 Near-real-time multiparametric seismic and visual monitoring of explosive activity at Sabancaya volcano, Peru Centeno, Riky; Gómez-Salcedo, Valeria; Lazarte, Ivonne; Vilca-Nina, Javier; Osores, María Soledad; Mayhua-Lopez, Efraín This study presents the development of a multiparametric system that utilizes artificial intelligence techniques to identify and analyze volcanic explosions in near real-time. The study analyzed 1343 explosions recorded between 2019 and 2021, along with seismic, meteorological, and visible image data from the Sabancaya volcano. Deep learning algorithms like the U-Net convolutional neural network were used to segment and measure volcanic plumes in images, while boosting-based machine learning ensembles were used to classify seismic events related to ash plumes. The findings demonstrate that these approaches effectively handle large amounts of data generated during seismic and eruptive crises. The U-Net network achieved precise segmentation of volcanic plumes with over 98% accuracy and the ability to generalize to new data. The CatBoost classifier achieved an average accuracy of 94.5% in classifying seismic events. These approaches enable the real-time estimation of eruptive parameters without human intervention, contributing to the development of early warning systems for volcanic hazards. In conclusion, this study highlights the feasibility of using seismic signals and images to detect and characterize volcanic explosions in near real-time, making a significant contribution to the field of volcanic monitoring. Mon, 01 Jul 2024 00:00:00 GMT http://hdl.handle.net/20.500.12160/2957 2024-07-01T00:00:00Z http://hdl.handle.net/20.500.12160/2577 Early warning systems and end-user decision-making: A risk formalism tool to aid communication and understanding de Elía, Ramón; Ruiz, Juan José; Francce, Verónica; Lohigorry, Pedro; Saucedo, Marcos; Menalled, Matías; D'Amen, Daniela In this work, we introduce a formalism to highlight the role of decision-making implicit in the setup of early warning systems (EWSs) and its consequences with respect to loss avoidance for end users. The formalism, a close relative of the cost/loss approach, combines EWS verification scores with traditional expressions of risk from the point of view of the user. This formalism articulates in mathematical format many well-known issues surrounding EWS usage, offering a conceptual anchor for concepts that otherwise may seem to wobble among the multidisciplinary perspectives participating in the EWS chain. Fil: de Elía, Ramón. Servicio Meteorológico Nacional. Dirección Nacional de Ciencia e Innovación en Productos y Servicios; Argentina. Fri, 01 Sep 2023 00:00:00 GMT http://hdl.handle.net/20.500.12160/2577 2023-09-01T00:00:00Z http://hdl.handle.net/20.500.12160/143 Investigating the nature of an ash cloud event in Southern Chile using remote sensing: volcanic eruption or resuspension? Toyos, Guillermo; Mingari, Leonardo; Pujol, Gloria Cristina; Villarosa, Gustavo On 14 December 2013, the Cooperative Institute for Meteorological Satellite Studies (United States) reported a volcanic ash cloud apparently emitted by the Puyehue Cordón Caulle Volcanic Complex (Chile) and indicated its cause was probably resuspension. The distinction of volcanic ash resuspension from volcanic eruptions is important because both processes pose different scenarios for civil protection authorities and besides, there is a special need of specific schemes for detecting and monitoring resuspension of volcanic ash. To this end, we intended to identify the cause of this event by using remote sensing technology. Remote sensing based volcanic ash products enabled us to confirm the presence of volcanic ash and observations on the Moderate Resolution Imaging Spectroradiometer (MODIS)–based cloud-integrated water path provided evidence in favour of a small and short-lived eruption. Thus, a volcanic eruption would constitute a plausible explanation for the cloud of 14 December 2013, but we were unable to discard resuspension. On the other hand, we found out that the water path product could constitute useful ancillary data to identify the origin of this kind of processes. The set of observations presented constitutes a good initial point towards the identification and subsequent development of decision support tools for the mitigation of the hazards posed by volcanic ash resulting from volcanic eruptions and resuspension. Artículo publicado en la Revista Remote Sensing Letters, Volume 8 No. 2, páginas 146-155. Wed, 25 Oct 2017 00:00:00 GMT http://hdl.handle.net/20.500.12160/143 2017-10-25T00:00:00Z