2026-09-19T04:57:22Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1242612026-06-06T00:56:13Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Miho Mazereeuw. Quintero, Abraham,M. Eng.Massachusetts Institute of Technology. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2020-03-24T15:36:53Z 2020-03-24T15:36:53Z 2019 2019 https://hdl.handle.net/1721.1/124261 1145167309 This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 49-52). The United Nations Office for Disaster Risk Reduction (UNDRR) states that economic losses due to natural disasters have risen 151 percent in the past 20 years. Of these disasters, floods are the most common. The Sendai Framework for Disaster Risk Reduction was created by the UNDRR in order to chart goals for future risk mitigation; among its seven global targets is increasing the availability of disaster risk information and assessment systems. Disaster information systems use state of the art techniques such as remote sensing in order to mitigate damages from natural and man made hazards. It is common in developed countries utilize networks of advanced sensors and ahead of time mapping in order to facilitate emergency responses; however, such systems are not available in developing countries due to cost limitations. The widespread proliferation of smart phones and social media use in developing countries means that citizens can be used as sensors by reporting disaster information online. The Riskmap system was developed by the Urban Risk Lab at MIT in order to gather citizen report streams. Such citizen disaster reports have two issues: a large influx of reports can cause information overload in emergency operations centers, which makes it difficult to summarize the situation. Machine learning has previously been used in order to analyze and simplify information for human consumption. This work seeks to use novel machine learning techniques to fully utilize crowd-sourced social media reports gathered using the Riskmap system. by Abraham Quintero. M.Eng. M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 52 pages eng Massachusetts Institute of Technology MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. REACT: the Riskmap Evaluation and Coordination Terminal Riskmap Evaluation and Coordination Terminal Thesis application/pdf 2020-03-24T15:36:52Z Publication Master EECS unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="ec03b3d0-9b95-441d-8067-b394cc5ed51c"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>REACT: the Riskmap Evaluation and Coordination Terminal</Title> <Subtitle>Riskmap Evaluation and Coordination Terminal</Subtitle> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2019</PublicationDate> <Authors> <Author> <DisplayName>Quintero, Abraham,M. Eng.Massachusetts Institute of Technology.</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Electrical Engineering and Computer Science.</Keyword> <Abstract>The United Nations Office for Disaster Risk Reduction (UNDRR) states that economic losses due to natural disasters have risen 151 percent in the past 20 years. Of these disasters, floods are the most common. The Sendai Framework for Disaster Risk Reduction was created by the UNDRR in order to chart goals for future risk mitigation; among its seven global targets is increasing the availability of disaster risk information and assessment systems. Disaster information systems use state of the art techniques such as remote sensing in order to mitigate damages from natural and man made hazards. It is common in developed countries utilize networks of advanced sensors and ahead of time mapping in order to facilitate emergency responses; however, such systems are not available in developing countries due to cost limitations. The widespread proliferation of smart phones and social media use in developing countries means that citizens can be used as sensors by reporting disaster information online. The Riskmap system was developed by the Urban Risk Lab at MIT in order to gather citizen report streams. Such citizen disaster reports have two issues: a large influx of reports can cause information overload in emergency operations centers, which makes it difficult to summarize the situation. Machine learning has previously been used in order to analyze and simplify information for human consumption. This work seeks to use novel machine learning techniques to fully utilize crowd-sourced social media reports gathered using the Riskmap system.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>