Vis enkel innførsel

dc.contributor.authorMann, Hjalte M. R.
dc.contributor.authorIosifidis, Alexandros
dc.contributor.authorJepsen, Jane Uhd
dc.contributor.authorWelker, Jeffrey M.
dc.contributor.authorLoonen, Maarten J.J.E.
dc.contributor.authorHøye, Toke T.
dc.date.accessioned2022-06-08T11:29:36Z
dc.date.available2022-06-08T11:29:36Z
dc.date.created2022-06-02T14:18:00Z
dc.date.issued2022
dc.identifier.issn2056-3485
dc.identifier.urihttps://hdl.handle.net/11250/2997893
dc.description.abstractThe advancement of spring is a widespread biological response to climate change observed across taxa and biomes. However, the species level responses to warming are complex and the underlying mechanisms are difficult to disentangle. This is partly due to a lack of data, which are typically collected by direct observations, and thus very time-consuming to obtain. Data deficiency is especially pronounced in the Arctic where the warming is particularly severe. We present a method for automated monitoring of flowering phenology of specific plant species at very high temporal resolution through full growing seasons and across geographical regions. The method consists of image-based monitoring of field plots using near-surface time-lapse cameras and subsequent automated detection and counting of flowers in the images using a convolutional neural network. We demonstrate the feasibility of collecting flower phenology data using automatic time-lapse cameras and show that the temporal resolution of the results surpasses what can be collected by traditional observation methods. We focus on two Arctic species, the mountain avens Dryas octopetala and Dryas integrifolia in 20 image series from four sites. Our flower detection model proved capable of detecting flowers of the two species with a remarkable precision of 0.918 (adjusted to 0.966) and a recall of 0.907. Thus, the method can automatically quantify the seasonal dynamics of flower abundance at fine scale and return reliable estimates of traditional phenological variables such as the timing of onset, peak, and end of flowering. We describe the system and compare manual and automatic extraction of flowering phenology data from the images. Our method can be directly applied on sites containing mountain avens using our trained model, or the model could be fine-tuned to other species. We discuss the potential of automatic image-based monitoring of flower phenology and how the method can be improved and expanded for future studies. Arctic, computer vision, convolutional neural network, Dryas integrifolia, Dryas octopetala, ecological monitoring, life-history variation, machine learningen_US
dc.language.isoengen_US
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/deed.no*
dc.subjectArcticen_US
dc.subjectcomputer visionen_US
dc.subjectconvolutional neural networken_US
dc.subjectDryas integrifoliaen_US
dc.subjectDryas octopetalaen_US
dc.subjectecological monitoringen_US
dc.subjectlife-history variationen_US
dc.subjectmachine learningen_US
dc.titleAutomatic flower detection and phenology monitoring using time-lapse cameras and deep learningen_US
dc.title.alternativeAutomatic flower detection and phenology monitoring using time-lapse cameras and deep learningen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionpublishedVersionen_US
dc.rights.holder© 2022 The Authorsen_US
dc.subject.nsiVDP::Zoologiske og botaniske fag: 480en_US
dc.subject.nsiVDP::Zoology and botany: 480en_US
dc.source.journalRemote Sensing in Ecology and Conservationen_US
dc.identifier.doi10.1002/rse2.275
dc.identifier.cristin2029135
dc.relation.projectFramsenteret: Fram Centre terrestrial flagship program. Research, Thuleen_US
dc.relation.projectAndre: University of Oulu, Finklanden_US
dc.relation.projectAndre: NSF grant 1836837en_US
dc.relation.projectAndre: Independent Research Fund Denmark Grant 8021- 00423Ben_US
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode1


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel

Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal
Med mindre annet er angitt, så er denne innførselen lisensiert som Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal