Ученый USGS расскажет о применении машинного обучения для прогнозирования вулканических извержений

Tyler Paladino, research geophysicist at the United States Geological Survey (USGS), will give the talk "Preparing for volcanic eruption hazards using operational geodesy, machine learning, and probabilistic ash dispersal modeling tools," at 2 p.m. on Friday, Sept 11, in 117 Earth and Engineering Sciences Building at Penn State University Park. Talk will also be available via Zoom. The event is part of a fall seminar series hosted by TRAnscendIng Natural hazards forecasting (TRAIN). The talk is free and open to the public. Volcano observatories have a primary purpose of monitoring volcanic activity to aid in preparedness for volcanic eruptions. Observatories monitor volcano activity, evaluate their hazards, issue warnings, and advance scientific understanding to reduce impacts of volcano eruptions. "Numerous monitoring efforts and computational techniques exist to aid in preparedness, most of which are becoming increasingly automated," Paladino said. Paladino will detail two methods the volcano science center at the USGS uses to assist in volcano monitoring. One is using deep learning to automatically assess the shape change at Mauna Loa, Hawaii. The other is using modeling tools to assess the ash-fall hazards associated with Mount Spurr, Alaska. "The first explains how this machine learning model was built as well as its strengths and utility," Paladino said. "The latter discusses the probabilistic framework, the challenges of selecting eruption source parameters for ash dispersal modeling, and interactions with key stakeholders and emergency managers." Paladino is a research geophysicist at the USGS Cascades Volcano Observatory based in Vancouver, Washington. He received a bachelor of science in Earth sciences from the University of California, Santa Cruz, and his doctorate in geosciences from Idaho State University. His research has spanned geomorphic studies of Martian gullies and statistical analysis on Martian volcanism, Antarctic array seismology and eruption plume collapse scenario modeling. His current research interests focus on creating and improving operational frameworks for volcano monitoring and response as well as studying the dynamics of subsurface magma movements and explosive eruption plumes. About TRAIN TRAIN is an initiative through the Earth and Environmental Systems Institute (EESI) that aims to transform complex geophysical and atmospheric data and bridge the gap between raw information and community resilience. TRAIN aims to build the community at Penn State to become nationally recognized for research innovation to respond proactively to funding opportunities and coordinate natural hazard responses. /Public Release. This material from the originating organization/author(s) might be of the point-in-time nature, and edited for clarity, style and length. Mirage.News does not take institutional positions or sides, and all views, positions, and conclusions expressed herein are solely those of the author(s).View in full here.