{"id":36258,"date":"2025-03-27T12:21:07","date_gmt":"2025-03-27T16:21:07","guid":{"rendered":"https:\/\/www.bu.edu\/hic\/?page_id=36258"},"modified":"2026-07-28T19:56:53","modified_gmt":"2026-07-28T23:56:53","slug":"ai-for-understanding-earthquakes-symposium","status":"publish","type":"page","link":"https:\/\/www.bu.edu\/hic\/programs\/focused-research-programs\/frp-events\/ai-for-understanding-earthquakes-symposium\/","title":{"rendered":"AI for Understanding Earthquakes Symposium"},"content":{"rendered":"<p><strong>Date:\u00a0<\/strong><span>Thursday, May 8, 2025<\/span><\/p>\n<p><strong>Start &amp; End Time:\u00a0<\/strong><span>10:00am &#8211; 3:00pm ET<\/span><\/p>\n<p><strong>Location<\/strong><span>\u00a0(In-person only)<\/span><strong>:<\/strong><span> Boston University, Duan Family Center for Computing &amp; Data Sciences, 665 Commonwealth Ave, Room 1101 (11th floor), Boston, MA\u00a0<\/span><\/p>\n<div class=\"bu_collapsible_container \" aria-live=\"polite\" data-customize-animation=\"false\"><h3 class=\"bu_collapsible\" aria-expanded=\"false\"tabindex=\"0\" role=\"button\">Logistics Information<\/h3><div class=\"bu_collapsible_section\" style=\"display: none;\"><b>Location (only in-person)<\/b><br \/>\nBoston University, Center for Computing &amp; Data Sciences, 665 Commonwealth Ave, Room 1101 (11th floor), Boston, MA. (To access the upper floors, please use the elevators near Saxby\u2019s caf\u00e9.)<br \/>\n&lt;nbsp;\/&gt;<br \/>\n<b>Public Transportation <\/b><br \/>\nDue to limited parking &amp; potential construction, we encourage public transportation. MBTA Green Line B branch, as well as a few minutes walking distance from stops on the C (St. Mary\u2019s Street) &amp; D (Fenway) branches.<br \/>\n&lt;nbsp;\/&gt;<br \/>\n<b>Parking<\/b><br \/>\nOn-street, two-hour meter parking is limited &amp; available on Commonwealth Ave. There is free two-hour parking on the side streets.<br \/>\n&lt;nbsp;\/&gt;<br \/>\n<b>Hotel Suggestions <\/b><br \/>\nBelow are our recommended hotels for participants attending the event. We suggest making reservations as early as possible to secure your stay.<br \/>\n\u2022 Hotel Commonwealth (866-784-4000) is a 10-minute walk.<br \/>\n\u2022 Eliot Hotel (1-800-44-ELIOT) is a 15-minute walk.<br \/>\n\u2022 Hyatt Regency Cambridge (1-800-233-1234) is a 5-minute taxi across the river.<br \/>\n&lt;nbsp;\/&gt;<br \/>\n<b>Boston University Wifi <\/b><br \/>\nThe BU Guest network allows visitors to access the Internet through BU\u2019s wireless network. Please note that personal wireless access points are prohibited on the BU network because they interfere with network traffic. To access BU Guest (unencrypted): Connect to the network called \u201cBU Guest (unencrypted)\u201c from your list of available networks.<\/div>\n<\/div>\n\n<h3>Symposium Mission:<\/h3>\n<p>AI techniques are increasingly important in the study of seismic events and changes in the structure of the earth over time.\u00a0For the last year, we have been undergoing a focused research project through the Hariri Institute at Boston University to develop novel approaches of using AI for understanding earthquakes.\u00a0The goal of this symposium is to foster discussion around the use of machine learning and AI in the study of earthquakes, and to build new collaborations in this area.<\/p>\n<p><em>This symposium is organized by the Hariri Institute\u2019s funded AI for Understanding Earthquakes Focused Research Program (FRP.) To learn more, <a href=\"https:\/\/www.bu.edu\/hic\/programs\/focused-research-programs\/frp-program-pages\/ai-for-understanding-earthquakes\/\" target=\"_blank\" rel=\"noopener\">visit the FRP program page.<\/a>\u00a0<\/em><\/p>\n<h3>BU Hosts:<\/h3>\n\n\t<ul class=\"profile-listing profile-format-advanced\">\n\t\t\t\t\t\n<li class=\"profile-item profile-item-advanced has-title post-32895 profile type-profile status-publish hentry people-faculty-affiliate\">\n\t<a href=\"https:\/\/www.bu.edu\/hic\/profile\/rachel-abercrombie\/\" class=\"profile-link profile-link-advanced\">\n\t\t\t\t\t<figure class=\"profile-photo profile-photo-advanced\"><img width=\"150\" height=\"146\" src=\"\/hic\/files\/2024\/05\/RachelAbercrombie.jpg\" alt=\"\" \/><\/figure>\t\t\t\t<h6 class=\"profile-name profile-name-advanced\">Rachel Abercrombie<\/h6>\n\t\t<p class=\"profile-title profile-title-advanced\">Research Professor, Earth &#038; Environment<\/p>\t<\/a>\n\n\t\n<\/li>\n\t\t\t\t\t\n<li class=\"profile-item profile-item-advanced has-title post-12736 profile type-profile status-publish hentry centers-initiatives-air-initative people-core-faculty people-faculty-affiliate people-frp-leaders-fy25 people-steering-committee\">\n\t<a href=\"https:\/\/www.bu.edu\/hic\/profile\/brian-kulis\/\" class=\"profile-link profile-link-advanced\">\n\t\t\t\t\t<figure class=\"profile-photo profile-photo-advanced\"><img width=\"150\" height=\"150\" src=\"\/hic\/files\/2017\/09\/kulis.jpg\" alt=\"\" \/><\/figure>\t\t\t\t<h6 class=\"profile-name profile-name-advanced\">Brian Kulis, PhD<\/h6>\n\t\t<p class=\"profile-title profile-title-advanced\">Professor of Engineering (ECE, SE), Computer Science and Computing &#038; Data Sciences<\/p>\t<\/a>\n\n\t\n<\/li>\n\t\t\t<\/ul>\n\t\n<div class=\"bu_collapsible_container \" id=\"program\" aria-live=\"polite\" data-customize-animation=\"false\"><h3 class=\"bu_collapsible\" aria-expanded=\"false\"tabindex=\"0\" role=\"button\">Program<\/h3><div class=\"bu_collapsible_section\" style=\"display: none;\"><b>10:00am \u2013 10:10am: <\/b>Welcome &amp; Opening Remarks with Brian Kulis, Core Faculty of Hariri Institute\u2019s AI in Research Initiative, Associate Professor of Engineering, (ECE, CS, SE), CISE Faculty Affiliate and Faculty of Computing and Data Sciences, and Rachel Abercrombie, Research Professor of Earth and Environment<\/p>\n<p>&lt;nbsp;\/&gt;<\/p>\n<p><b>10:10am \u2013 10:40am: <\/b>\u201cOpportunities for AI to Rapidly Forecasting Earthquake Shaking\u201d with Timothy Clements, Research Geophysicist at the U.S. Geological Survey\u2019s Earthquake Science Center at Moffett Field, CA. Please note Tim will be presenting remotely to our in-person audience.<\/p>\n<p><b>10:40am \u2013 11:10am: <\/b>\u201cRapid Earthquake Magnitude Estimation on Fiber Optic Cables and Strain Meters via Machine Learning\u201d with Theresa Sawi, Mendenhall Postdoctoral Research Fellow at the U.S. Geological Survey\u2019s Earthquake Science Center at Moffett Field, CA. Please note Theresa will be presenting remotely to our in-person audience.<\/p>\n<p><b>11:10am \u2013 11:30am: <\/b>Summary of Our Hariri Institute Focused Research Program with Brian Kulis, Core Faculty of Hariri Institute\u2019s AI in Research Initiative, Associate Professor of Engineering, (ECE, CS, SE), CISE Faculty Affiliate and Faculty of Computing and Data Sciences; Janusz Konrad, Affiliate Faculty of the AI in Research Initiative at the Hariri Institute and Professor of Electrical and Computer Engineering; and Prakash Ishwar, Professor of Electrical and Computer Engineering and Affiliate Faculty of the AI in Research Initiative at the Hariri Institute<\/p>\n<p><b>11:30am \u2013 12:00pm: <\/b>Discussion<\/p>\n<p><b>12:00pm \u2013 1:00pm: <\/b>Lunch<\/p>\n<p><b>1:00pm \u2013 1:30pm: <\/b>\u201cMachine Learning and Remote Sensing for Earthquake Characterization\u201d with Sophie Giffard-Roisin, Visiting Fulbright Research Scholar at the Lamont Observatory, Columbia University<\/p>\n<p><b>1:30pm \u2013 2:00pm: <\/b>\u201cApplications of LLMs in Earthquake Science: Estimating the Intensity of Ground Motion\u201d with Mostafa Mousavi, Assistant Professor of Geology, Geophysics, and Planetary Science at Harvard University<\/p>\n<p><b>2:00pm \u2013 3:00pm: <\/b>Discussion \/ Breakouts<\/div>\n<\/div>\n\n<h3>Speakers:<\/h3>\n<p><div class=\"bu_collapsible_container \" id=\"Speaker1\" aria-live=\"polite\" data-customize-animation=\"false\"><h4 class=\"bu_collapsible\" aria-expanded=\"false\"tabindex=\"0\" role=\"button\">Mostafa Mousavi, Assistant Professor of Geology, Geophysics, and Planetary Science at Harvard University<\/h4><div class=\"bu_collapsible_section\" style=\"display: none;\"><b>Talk title:<\/b> Applications of LLMs in Earthquake Science: Estimating the Intensity of Ground Motion<\/p>\n<p>&lt;nbsp;\/&gt;<\/p>\n<p><b>Abstract:<\/b> Generative AI and Large Language Models (LLMs) have recently emerged as transformative technologies, revolutionizing various fields with their ability to generate complex outputs across diverse modalities. While these models have driven significant advancements in areas like natural language processing and computer vision, their potential for scientific applications remains largely unexplored. This study investigates the capabilities of LLMs to advance seismological research and enhance societal resilience to natural disasters. Using Gemini, Google&#8217;s most capable LLM, we estimate earthquake ground shaking intensity from multimodal social media posts and show how these estimates align with independent observational data. We demonstrate how Gemini can contribute to a deeper understanding of earthquake impacts, improve natural disaster mitigation strategies, and potentially aid in rapid earthquake response and damage assessment. Through this example application, we aim to showcase the power and potential of generative AI and LLMs for applications in seismology and earthquake science.<\/p>\n<p><img loading=\"lazy\" src=\"\/hic\/files\/2025\/04\/S.-Mostafa-Mousavi-.jpeg\" alt=\"\" width=\"200\" height=\"200\" class=\"alignnone size-medium wp-image-36521\" \/><\/p>\n<p><b>Bio: <\/b><\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>S. Mostafa Mousavi is an observational earthquake seismologist who uses AI to process large seismic datasets and gain insights into earthquake characteristics and dynamics. His research is an interdisciplinary blend of seismology, statistics, and computer science, focused on extracting insights about Earth&#8217;s physical processes from seismic signals. He is currently an assistant professor at Harvard and a research scientist at Google, where he works on the world&#8217;s largest and fastest Earthquake Early Warning system.<\/div>\n<\/div>\n<\/ul>\n<\/li>\n<\/ul>\n<p><div class=\"bu_collapsible_container \" aria-live=\"polite\" data-customize-animation=\"false\"><h4 class=\"bu_collapsible\" aria-expanded=\"false\"tabindex=\"0\" role=\"button\">Sophie Giffard-Roisin, Visiting Fulbright Research Scholar at the Lamont Observatory, Columbia University<\/h4><div class=\"bu_collapsible_section\" style=\"display: none;\"><b>Talk title:<\/b> Machine Learning and Remote Sensing for Earthquake Characterization<\/p>\n<p>&lt;nbsp;\/&gt;<\/p>\n<p><b>Abstract:<\/b> Machine learning has proven its usefulness in geoscience and seismology in recent years, for example in seismic picking. Similarly, machine learning applied to remote sensing has shown great effectiveness in solving large-scale tasks such as land cover mapping and atmospheric forecasting. In all these cases, large amounts of labeled data were available, thanks to manual or semi-automated methods.<br \/>\nHowever, for certain applications\u2014particularly regression or characterization problems\u2014real labeled data is often not accessible. In this talk, we will explore how physical simulations, combined with real remote sensing data, can be used to generate realistic labeled samples for training machine learning models. We will focus specifically on earthquake optical image correlation and fault scarp characterization.<\/p>\n<p><img loading=\"lazy\" src=\"\/hic\/files\/2025\/04\/SophieGiffardRosin.jpg\" alt=\"\" width=\"200\" height=\"200\" class=\"alignnone size-full wp-image-36524\" \/><\/p>\n<p><b>Bio: <\/b><\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>Sophie Giffard-Roisin has been a permanent researcher at the ISTerre laboratory in Grenoble, France since 2019, working on machine learning applied to natural hazards, particularly using remote sensing. She is currently a Fulbright Scholar Fellow at the Lamont-Doherty Earth Observatory, Columbia University.<\/div>\n<\/div>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><div class=\"bu_collapsible_container \" aria-live=\"polite\" data-customize-animation=\"false\"><h4 class=\"bu_collapsible\" aria-expanded=\"false\"tabindex=\"0\" role=\"button\">Theresa Sawi, Mendenhall Postdoctoral Research Fellow at the U.S. Geological Survey's Earthquake Science Center at Moffett Field, CA<\/h4><div class=\"bu_collapsible_section\" style=\"display: none;\"><b>Talk title: <\/b>Rapid Earthquake Magnitude Estimation on Fiber Optic Cables and Strain Meters via Machine Learning<\/p>\n<p>&lt;nbsp;\/&gt;<\/p>\n<p><b>Abstract:<\/b> As the volume and variety of seismic data increases, opportunities for seismologists to apply machine learning methods to these data for the purpose of earthquake early warning (EEW) becomes more apparent. Distributed Acoustic Sensing (DAS) utilizes fiber optic cables to measure shaking of the earth and offers a promising approach for EEW in subduction zones (i.e., underwater settings) where seismic networks are costly to maintain. However, key challenges remain in estimating earthquake magnitudes from DAS data, namely that locations are difficult to estimate given the primarily linear geometry of the DAS arrays, and due to the high volumes of data created by DAS, which can quickly reach the TB-range. Here, we develop a machine learning method to distinguish large (M\u22655.4) earthquakes from smaller ones within the first 4 seconds of a strain waveform after an initial earthquake arrival, without needing to determine earthquake location. Using a deep learning method to pick the earthquake arrivals on the DAS data, then using ensemble decision tree models trained on borehole strainmeter data (3.5\u2264M\u22647.1) and tested on onshore DAS waveforms (3.5\u2264M\u22647), we find that low-frequency wavelengths used in continuous wavelet transform coefficients are the strongest predictors of magnitude. Our method shows high precision compared to real-time EEW systems, supporting the use of DAS for terrestrial and submarine earthquake monitoring.<\/p>\n<p><img loading=\"lazy\" src=\"\/hic\/files\/2025\/04\/Theresa.jpeg\" alt=\"\" width=\"200\" height=\"200\" class=\"alignnone size-full wp-image-36522\" \/><\/p>\n<p><b>Bio: <\/b><\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>Dr. Theresa Sawi is a Mendenhall Postdoctoral Research Fellow at the U.S. Geological Survey\u2019s Earthquake Science Center at Moffett Field in California. She researches how distributed acoustic sensing (DAS), i.e., fiber optic cables, can be utilized to improve earthquake early warning. Her work seeks to better understand the rupture processes of large earthquakes, the behavior of repeating earthquake sequences, and generally how to best apply machine to aid in solving seismological problems. Her scientific interests also include seismic array processing and seismicity in fluid-rich glaciers.<\/div>\n<\/div>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><div class=\"bu_collapsible_container \" aria-live=\"polite\" data-customize-animation=\"false\"><h4 class=\"bu_collapsible\" aria-expanded=\"false\"tabindex=\"0\" role=\"button\">Timothy Clements, Research Geophysicist at the U.S. Geological Survey's Earthquake Science Center at Moffett Field, CA<\/h4><div class=\"bu_collapsible_section\" style=\"display: none;\"><b>Talk title:<\/b> Opportunities for AI to Rapidly Forecasting Earthquake Shaking<\/p>\n<p>&lt;nbsp;\/&gt;<\/p>\n<p><b>Abstract:<\/b> Earthquake early warning (EEW) systems characterize when and where strong shaking is expected as soon as possible after an earthquake starts. By necessity, EEW systems run 24\/7 and deliver shaking alerts in an automated manner. There is an inherent tradeoff between the speed and accuracy of EEW alerts \u2013 the earliest shaking alerts based on initial data are more likely to be inaccurate, whereas more reliable shaking predictions often arrive after they are needed. An AI-based shaking forecasting system could offer faster and more accurate predictions by learning the complexities of ground motion physics from the wealth of archived seismic data. Here, we introduce two approaches to AI shaking forecasting: (1) the Graph Prediction of Earthquake Shaking (GRAPES) model, which characterizes EEW as a spatio-temporal graph learning problem and predicts future shaking across a seismic network using an end-to-end set of convolutional, fully connected, and graph neural network layers and (2) the Generate Unsupervised Aftershock Velocity Amplitudes (GUAVA) model, a generative pre-trained transformer with ~100 million model parameters that generates time series of ground motion intensity autoregressively. We train both models to forecast future shaking using massive sets of seismic waveforms recorded in Japan and California. We show that AI-based shaking forecasts perform well through learning expressive representations of the seismic wavefield and the statistics of earthquakes.<\/p>\n<p><img loading=\"lazy\" src=\"\/hic\/files\/2025\/04\/Timothy-.jpg\" alt=\"\" width=\"200\" height=\"200\" class=\"alignnone size-medium wp-image-36523\" \/><\/p>\n<p><b>Bio: <\/b><\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>Tim Clements is a research geophysicist at the U.S. Geological Survey\u2019s Earthquake Science Center in Moffett Field, CA. He conducts research on earthquake early warning, ground motion forecasting, and low-cost sensor development with a focus on applying computation to continuous seismic waveforms.<\/div>\n<\/div>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><em><\/em><\/p>\n\n<p><span>For administrative questions, please email Katherine D\u2019Angelo, Assistant Director, Programs &amp; Events, at <\/span><a href=\"mailto:ktd@bu.edu\" title=\"mailto:ktd@bu.edu\"><span>ktd@bu.edu<\/span><\/a><span>.\u00a0\u00a0\u00a0\u00a0<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Date:\u00a0Thursday, May 8, 2025 Start &amp; End Time:\u00a010:00am &#8211; 3:00pm ET Location\u00a0(In-person only): Boston University, Duan Family Center for Computing &amp; Data Sciences, 665 Commonwealth Ave, Room 1101 (11th floor), Boston, MA\u00a0 Symposium Mission: AI techniques are increasingly important in the study of seismic events and changes in the structure of the earth over time.\u00a0For [&hellip;]<\/p>\n","protected":false},"author":16894,"featured_media":0,"parent":42518,"menu_order":3,"comment_status":"closed","ping_status":"closed","template":"","meta":[],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/pages\/36258"}],"collection":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/users\/16894"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/comments?post=36258"}],"version-history":[{"count":29,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/pages\/36258\/revisions"}],"predecessor-version":[{"id":43168,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/pages\/36258\/revisions\/43168"}],"up":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/pages\/42518"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/media?parent=36258"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}