Show simple item record

dc.contributor.authorTurkulainen, Emma
dc.contributor.authorHonkavaara, Eija
dc.contributor.authorNäsi, Roope
dc.contributor.authorOliveira, Raquel A.
dc.contributor.authorHakala, Teemu
dc.contributor.authorJunttila, Samuli
dc.contributor.authorKarila, Kirsi
dc.contributor.authorKoivumäki, Niko
dc.contributor.authorPelto-Arvo, Mikko
dc.contributor.authorTuviala, Johanna
dc.contributor.authorÖstersund, Madeleine
dc.contributor.authorPölönen, Ilkka
dc.contributor.authorLyytikäinen-Saarenmaa, Päivi
dc.date.accessioned2023-10-24T08:33:49Z
dc.date.available2023-10-24T08:33:49Z
dc.date.issued2023
dc.identifier.citationTurkulainen, E., Honkavaara, E., Näsi, R., Oliveira, R. A., Hakala, T., Junttila, S., Karila, K., Koivumäki, N., Pelto-Arvo, M., Tuviala, J., Östersund, M., Pölönen, I., & Lyytikäinen-Saarenmaa, P. (2023). Comparison of Deep Neural Networks in the Classification of Bark Beetle-Induced Spruce Damage Using UAS Images. <i>Remote Sensing</i>, <i>15</i>(20), Article 4928. <a href="https://doi.org/10.3390/rs15204928" target="_blank">https://doi.org/10.3390/rs15204928</a>
dc.identifier.otherCONVID_193542608
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/90589
dc.description.abstractThe widespread tree mortality caused by the European spruce bark beetle (Ips typographus L.) is a significant concern for Norway spruce-dominated (Picea abies H. Karst) forests in Europe and there is evidence of increases in the affected areas due to climate warming. Effective forest monitoring methods are urgently needed for providing timely data on tree health status for conducting forest management operations that aim to prepare and mitigate the damage caused by the beetle. Unoccupied aircraft systems (UASs) in combination with machine learning image analysis have emerged as a powerful tool for the fast-response monitoring of forest health. This research aims to assess the effectiveness of deep neural networks (DNNs) in identifying bark beetle infestations at the individual tree level from UAS images. The study compares the efficacy of RGB, multispectral (MS), and hyperspectral (HS) imaging, and evaluates various neural network structures for each image type. The findings reveal that MS and HS images perform better than RGB images. A 2D-3D-CNN model trained on HS images proves to be the best for detecting infested trees, with an F1-score of 0.759, while for dead and healthy trees, the F1-scores are 0.880 and 0.928, respectively. The study also demonstrates that the tested classifier networks outperform the state-of-the-art You Only Look Once (YOLO) classifier module, and that an effective analyzer can be implemented by integrating YOLO and the DNN classifier model. The current research provides a foundation for the further exploration of MS and HS imaging in detecting bark beetle disturbances in time, which can play a crucial role in forest management efforts to combat large-scale outbreaks. The study highlights the potential of remote sensing and machine learning in monitoring forest health and mitigating the impacts of biotic stresses. It also offers valuable insights into the effectiveness of DNNs in detecting bark beetle infestations using UAS-based remote sensing technology.en
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherMDPI AG
dc.relation.ispartofseriesRemote Sensing
dc.rightsCC BY 4.0
dc.subject.otherbark beetle
dc.subject.otherdrone
dc.subject.otherdeep learning
dc.subject.otherhyperspectral imaging
dc.subject.otherimage classification
dc.subject.othermultispectral imaging
dc.subject.otherobject detection
dc.subject.otherRGB
dc.subject.othertree health
dc.subject.otherUAS
dc.titleComparison of Deep Neural Networks in the Classification of Bark Beetle-Induced Spruce Damage Using UAS Images
dc.typearticle
dc.identifier.urnURN:NBN:fi:jyu-202310246621
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineTietotekniikkafi
dc.contributor.oppiaineComputing, Information Technology and Mathematicsfi
dc.contributor.oppiaineLaskennallinen tiedefi
dc.contributor.oppiaineMathematical Information Technologyen
dc.contributor.oppiaineComputing, Information Technology and Mathematicsen
dc.contributor.oppiaineComputational Scienceen
dc.type.urihttp://purl.org/eprint/type/JournalArticle
dc.type.coarhttp://purl.org/coar/resource_type/c_2df8fbb1
dc.description.reviewstatuspeerReviewed
dc.relation.issn2072-4292
dc.relation.numberinseries20
dc.relation.volume15
dc.type.versionpublishedVersion
dc.rights.copyright© 2023 by the authors. Licensee MDPI, Basel, Switzerland.
dc.rights.accesslevelopenAccessfi
dc.subject.ysomiehittämättömät ilma-alukset
dc.subject.ysometsäkuusi
dc.subject.ysokoneoppiminen
dc.subject.ysokirjanpainaja (kaarnakuoriaiset)
dc.subject.ysoneuroverkot
dc.subject.ysospektrikuvaus
dc.subject.ysosyväoppiminen
dc.subject.ysohyperspektrikuvantaminen
dc.subject.ysohyönteistuhot
dc.subject.ysometsätuhot
dc.subject.ysokaukokartoitus
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p24149
jyx.subject.urihttp://www.yso.fi/onto/yso/p5552
jyx.subject.urihttp://www.yso.fi/onto/yso/p21846
jyx.subject.urihttp://www.yso.fi/onto/yso/p19853
jyx.subject.urihttp://www.yso.fi/onto/yso/p7292
jyx.subject.urihttp://www.yso.fi/onto/yso/p26364
jyx.subject.urihttp://www.yso.fi/onto/yso/p39324
jyx.subject.urihttp://www.yso.fi/onto/yso/p39290
jyx.subject.urihttp://www.yso.fi/onto/yso/p14444
jyx.subject.urihttp://www.yso.fi/onto/yso/p11854
jyx.subject.urihttp://www.yso.fi/onto/yso/p2521
dc.rights.urlhttps://creativecommons.org/licenses/by/4.0/
dc.relation.doi10.3390/rs15204928
dc.type.okmA1


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

CC BY 4.0
Except where otherwise noted, this item's license is described as CC BY 4.0