A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence

<p>The development of a system that monitors social media continuously for general landslide-related content using a landslide classification model to identify and retain the most relevant information is described and validated. The system harvests photographs in real-time from these data and...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Catherine V.L. Pennington (18426939) (author)
مؤلفون آخرون: Rémy Bossu (9090281) (author), Ferda Ofli (8983517) (author), Muhammad Imran (282621) (author), Umair Qazi (8983514) (author), Julien Roch (9090278) (author), Vanessa J. Banks (18426942) (author)
منشور في: 2022
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513518604124160
author Catherine V.L. Pennington (18426939)
author2 Rémy Bossu (9090281)
Ferda Ofli (8983517)
Muhammad Imran (282621)
Umair Qazi (8983514)
Julien Roch (9090278)
Vanessa J. Banks (18426942)
author2_role author
author
author
author
author
author
author_facet Catherine V.L. Pennington (18426939)
Rémy Bossu (9090281)
Ferda Ofli (8983517)
Muhammad Imran (282621)
Umair Qazi (8983514)
Julien Roch (9090278)
Vanessa J. Banks (18426942)
author_role author
dc.creator.none.fl_str_mv Catherine V.L. Pennington (18426939)
Rémy Bossu (9090281)
Ferda Ofli (8983517)
Muhammad Imran (282621)
Umair Qazi (8983514)
Julien Roch (9090278)
Vanessa J. Banks (18426942)
dc.date.none.fl_str_mv 2022-07-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.ijdrr.2022.103089
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_near-real-time_global_landslide_incident_reporting_tool_demonstrator_using_social_media_and_artificial_intelligence/25671762
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Built environment and design
Building
Earth sciences
Geology
Engineering
Civil engineering
6 max)
Landslides
Triggered-landslides
Image-labelling
Artificial intelligence
Database
dc.title.none.fl_str_mv A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>The development of a system that monitors social media continuously for general landslide-related content using a landslide classification model to identify and retain the most relevant information is described and validated. The system harvests photographs in real-time from these data and tags each image as landslide or not-landslide. A training model was developed with input from computer scientists, geologists (landslide specialists) and social media specialists to establish a large image dataset that has then been applied to the live Twitter data stream. The preliminary model was developed by training a convolutional neural network on the dataset. Quantitative verification of the system's performance during a real-world deployment shows that the system can detect landslide reports with Precision = 76%. The demonstrator model is currently running live https://landslide-aidr.qcri.org/service.php; the next stage of development will incorporate stakeholder and user feedback.</p><h2>Other Information</h2> <p> Published in: International Journal of Disaster Risk Reduction<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.ijdrr.2022.103089" target="_blank">https://dx.doi.org/10.1016/j.ijdrr.2022.103089</a></p>
eu_rights_str_mv openAccess
id Manara2_f837343b16826077eb3d9388b5e11889
identifier_str_mv 10.1016/j.ijdrr.2022.103089
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25671762
publishDate 2022
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligenceCatherine V.L. Pennington (18426939)Rémy Bossu (9090281)Ferda Ofli (8983517)Muhammad Imran (282621)Umair Qazi (8983514)Julien Roch (9090278)Vanessa J. Banks (18426942)Built environment and designBuildingEarth sciencesGeologyEngineeringCivil engineering6 max)LandslidesTriggered-landslidesImage-labellingArtificial intelligenceDatabase<p>The development of a system that monitors social media continuously for general landslide-related content using a landslide classification model to identify and retain the most relevant information is described and validated. The system harvests photographs in real-time from these data and tags each image as landslide or not-landslide. A training model was developed with input from computer scientists, geologists (landslide specialists) and social media specialists to establish a large image dataset that has then been applied to the live Twitter data stream. The preliminary model was developed by training a convolutional neural network on the dataset. Quantitative verification of the system's performance during a real-world deployment shows that the system can detect landslide reports with Precision = 76%. The demonstrator model is currently running live https://landslide-aidr.qcri.org/service.php; the next stage of development will incorporate stakeholder and user feedback.</p><h2>Other Information</h2> <p> Published in: International Journal of Disaster Risk Reduction<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.ijdrr.2022.103089" target="_blank">https://dx.doi.org/10.1016/j.ijdrr.2022.103089</a></p>2022-07-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.ijdrr.2022.103089https://figshare.com/articles/journal_contribution/A_near-real-time_global_landslide_incident_reporting_tool_demonstrator_using_social_media_and_artificial_intelligence/25671762CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/256717622022-07-01T00:00:00Z
spellingShingle A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence
Catherine V.L. Pennington (18426939)
Built environment and design
Building
Earth sciences
Geology
Engineering
Civil engineering
6 max)
Landslides
Triggered-landslides
Image-labelling
Artificial intelligence
Database
status_str publishedVersion
title A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence
title_full A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence
title_fullStr A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence
title_full_unstemmed A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence
title_short A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence
title_sort A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence
topic Built environment and design
Building
Earth sciences
Geology
Engineering
Civil engineering
6 max)
Landslides
Triggered-landslides
Image-labelling
Artificial intelligence
Database