Full seismic waveform analysis combined with transformer neural networks improves coseismic landslide prediction

dc.contributor.authorDahal, Ashok
dc.contributor.authorTanyaş, Hakan
dc.contributor.authorLombardo, Luigi
dc.contributor.institutionUniversity of Twente, Faculty of Geo-Information Science and Earth Observation (ITC), PO Box 217, Enschede, AE, 7500, Netherlands
dc.date.accessioned2024-02-11T08:30:23Z
dc.date.available2024-02-11T08:30:23Z
dc.date.issued2024-02-09
dc.description.abstractSeismic waves can shake mountainous landscapes, triggering thousands of landslides. Regional-scale landslide models primarily rely on shaking intensity parameters obtained by simplifying ground motion time-series into peak scalar values. Such an approach neglects the contribution of ground motion phase and amplitude and their variations over space and time. Here, we address this problem by developing an explainable deep-learning model able to treat the entire wavefield and benchmark it against a model equipped with scalar intensity parameters. The experiments run on the area affected by the 2015 M$_{w}$7.8 Gorkha, Nepal earthquake reveal a 16% improvement in predictive capacity when incorporating full waveforms. This improvement is achieved mainly on gentle (~25°) hillslopes exposed to low ground shaking (~0.2 m/s). Moreover, we can largely attribute this improvement to the ground motion before and much after the peak velocity arrival. This underscores the limits of single-intensity measures and the untapped potential of full waveform information.
dc.description.sponsorshipThis work used the Dutch national e-infrastructure with the support of the SURF Cooperative using grant No. EINF-7984. This work was funded by the NATO Science for Peace and Security Program (SPS project G6190). We would also like to thank the KAUST competitive research grant (CRG) office for funding support for this research under grant URF/1/4338-01-01. We would like to thank Laura Gnesko from the University of Canterbury for proofreading the paper.
dc.identifier.doi10.1038/s43247-024-01243-8
dc.identifier.issn2662-4435
dc.identifier.issue1
dc.identifier.journalCommunications Earth & Environment
dc.identifier.urihttps://repository.kaust.edu.sa/handle/10754/697107
dc.identifier.volume5
dc.publisherSpringer Science and Business Media LLC
dc.relation.urlhttps://www.nature.com/articles/s43247-024-01243-8
dc.titleFull seismic waveform analysis combined with transformer neural networks improves coseismic landslide prediction
dc.typeArticle
display.details.left<span><h5>Type</h5>Article<br><br><h5>Authors</h5><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0003-3269-5575&spc.sf=dc.date.issued&spc.sd=DESC">Dahal, Ashok</a> <a href="https://orcid.org/0000-0003-3269-5575" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0002-0609-2140&spc.sf=dc.date.issued&spc.sd=DESC">Tanyaş, Hakan</a> <a href="https://orcid.org/0000-0002-0609-2140" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0003-4348-7288&spc.sf=dc.date.issued&spc.sd=DESC">Lombardo, Luigi</a> <a href="https://orcid.org/0000-0003-4348-7288" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><br><h5>KAUST Grant Number</h5>CRG<br>URF/1/4338-01-01<br><br><h5>Date</h5>2024-02-09</span>
display.details.right<span><h5>Abstract</h5>Seismic waves can shake mountainous landscapes, triggering thousands of landslides. Regional-scale landslide models primarily rely on shaking intensity parameters obtained by simplifying ground motion time-series into peak scalar values. Such an approach neglects the contribution of ground motion phase and amplitude and their variations over space and time. Here, we address this problem by developing an explainable deep-learning model able to treat the entire wavefield and benchmark it against a model equipped with scalar intensity parameters. The experiments run on the area affected by the 2015 M$_{w}$7.8 Gorkha, Nepal earthquake reveal a 16% improvement in predictive capacity when incorporating full waveforms. This improvement is achieved mainly on gentle (~25°) hillslopes exposed to low ground shaking (~0.2 m/s). Moreover, we can largely attribute this improvement to the ground motion before and much after the peak velocity arrival. This underscores the limits of single-intensity measures and the untapped potential of full waveform information.<br><br><h5>Acknowledgements</h5>This work used the Dutch national e-infrastructure with the support of the SURF Cooperative using grant No. EINF-7984. This work was funded by the NATO Science for Peace and Security Program (SPS project G6190). We would also like to thank the KAUST competitive research grant (CRG) office for funding support for this research under grant URF/1/4338-01-01. We would like to thank Laura Gnesko from the University of Canterbury for proofreading the paper.<br><br><h5>Publisher</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.publisher=Springer Science and Business Media LLC,equals">Springer Science and Business Media LLC</a><br><br><h5>Journal</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.journal=Communications Earth & Environment,equals">Communications Earth & Environment</a><br><br><h5>DOI</h5><a href="https://doi.org/10.1038/s43247-024-01243-8">10.1038/s43247-024-01243-8</a><br><br><h5>Additional Links</h5>https://www.nature.com/articles/s43247-024-01243-8</span>
kaust.acknowledged.supportUnitCRG
kaust.grant.numberCRG
kaust.grant.numberURF/1/4338-01-01
orcid.authorDahal, Ashok::0000-0003-3269-5575
orcid.authorTanyaş, Hakan::0000-0002-0609-2140
orcid.authorLombardo, Luigi::0000-0003-4348-7288
Files