Mostrar el registro sencillo del ítem

Integrating camera imagery, crowdsourcing, and deep learning to improve high-frequency automated monitoring of snow at continental-to-global scales

hal.structure.identifierDepartment of Organismic and Evolutionary Biology
dc.contributor.authorKOSMALA, Margaret
hal.structure.identifierInteractions Sol Plante Atmosphère [UMR ISPA]
hal.structure.identifierDepartment of Organismic and Evolutionary Biology
dc.contributor.authorHUFKENS, Koen
hal.structure.identifierDepartment of Organismic and Evolutionary Biology
hal.structure.identifierSchool of Informatics, Computing, and Cyber Systems [SICCS]
dc.contributor.authorRICHARDSON, Andrew D.
dc.date.accessioned2024-04-08T12:05:48Z
dc.date.available2024-04-08T12:05:48Z
dc.date.issued2018
dc.identifier.issn1932-6203
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/196375
dc.description.abstractEnSnow is important for local to global climate and surface hydrology, but spatial and temporal heterogeneity in the extent of snow cover make accurate, fine-scale mapping and monitoring of snow an enormous challenge. We took 184,453 daily near-surface images acquired by 133 automated cameras and processed them using crowdsourcing and deep learning to determine whether snow was present or absent in each image. We found that the crowdsourced data had an accuracy of 99.1% when compared with expert evaluation of the same imagery. We then used the image classification to train a deep convolutional neural network via transfer learning, with accuracies of 92% to 98%, depending on the image set and training method. The majority of neural network errors were due to snow that was present not being detected. We used the results of the neural networks to validate the presence or absence of snow inferred from the MODIS satellite sensor and obtained similar results to those from other validation studies. This method of using automated sensors, crowdsourcing, and deep learning in combination produced an accurate high temporal dataset of snow presence across a continent. It holds broad potential for real-time large-scale acquisition and processing of ecological and environmental data in support of monitoring, management, and research objectives.
dc.language.isoen
dc.publisherPublic Library of Science
dc.rights.urihttp://creativecommons.org/licenses/by/
dc.title.enIntegrating camera imagery, crowdsourcing, and deep learning to improve high-frequency automated monitoring of snow at continental-to-global scales
dc.typeArticle de revue
dc.identifier.doi10.1371/journal.pone.0209649
dc.subject.halSciences du Vivant [q-bio]
dc.subject.halSciences de l'environnement
bordeaux.journalPLoS ONE
bordeaux.page1-19
bordeaux.volume13
bordeaux.hal.laboratoriesInteractions Soil Plant Atmosphere (ISPA) - UMR 1391*
bordeaux.issue12
bordeaux.institutionBordeaux Sciences Agro
bordeaux.institutionINRAE
bordeaux.peerReviewedoui
hal.identifierhal-02621651
hal.version1
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-02621651v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=PLoS%20ONE&rft.date=2018&rft.volume=13&rft.issue=12&rft.spage=1-19&rft.epage=1-19&rft.eissn=1932-6203&rft.issn=1932-6203&rft.au=KOSMALA,%20Margaret&HUFKENS,%20Koen&RICHARDSON,%20Andrew%20D.&rft.genre=article


Archivos en el ítem

ArchivosTamañoFormatoVer

No hay archivos asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem