{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T22:01:15Z","timestamp":1774994475279,"version":"3.50.1"},"reference-count":57,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T00:00:00Z","timestamp":1706659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Federal Ministry of Research and Education (BMBF)","doi-asserted-by":"publisher","award":["02WDG014A"],"award-info":[{"award-number":["02WDG014A"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>We present an evaluation of different deep learning and machine learning approaches for tree health classification in the Black Forest, the Harz Mountains, and the G\u00f6ttinger Forest on a unique, highly accurate tree-level dataset. The multispectral UAV data were collected from eight forest plots with diverse tree species, mostly conifers. As ground truth data (GTD), nearly 1500 tree polygons with related attribute information on the health status of the trees were used. This data were collected during extensive fieldwork using a mobile application and subsequent individual tree segmentation. Extensive preprocessing included normalization, NDVI calculations, data augmentation to deal with the underrepresented classes, and splitting the data into training, validation, and test sets. We conducted several experiments using a classical machine learning approach (random forests), as well as different convolutional neural networks (CNNs)\u2014ResNet50, ResNet101, VGG16, and Inception-v3\u2014on different datasets and classes to evaluate the potential of these algorithms for tree health classification. Our first experiment was a binary classifier of healthy and damaged trees, which did not consider the degree of damage or tree species. The best results of a 0.99 test accuracy and an F1 score of 0.99 were obtained with ResNet50 on four band composites using the red, green, blue, and infrared bands (RGBI images), while VGG16 had the worst performance, with an F1 score of only 0.78. In a second experiment, we also distinguished between coniferous and deciduous trees. The F1 scores ranged from 0.62 to 0.99, with the highest results obtained using ResNet101 on derived vegetation indices using the red edge band of the camera (NDVIre images). Finally, in a third experiment, we aimed at evaluating the degree of damage: healthy, slightly damaged, and medium or heavily damaged trees. Again, ResNet101 had the best performance, this time on RGBI images with a test accuracy of 0.98 and an average F1 score of 0.97. These results highlight the potential of CNNs to handle high-resolution multispectral UAV data for the early detection of damaged trees when good training data are available.<\/jats:p>","DOI":"10.3390\/rs16030561","type":"journal-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T09:43:22Z","timestamp":1706780602000},"page":"561","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Evaluating Different Deep Learning Approaches for Tree Health Classification Using High-Resolution Multispectral UAV Data in the Black Forest, Harz Region, and G\u00f6ttinger Forest"],"prefix":"10.3390","volume":"16","author":[{"given":"Julia","family":"Anwander","sequence":"first","affiliation":[{"name":"Technical University of Applied Sciences W\u00fcrzburg-Schweinfurt (THWS), 97070 W\u00fcrzburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6778-2508","authenticated-orcid":false,"given":"Melanie","family":"Brandmeier","sequence":"additional","affiliation":[{"name":"Technical University of Applied Sciences W\u00fcrzburg-Schweinfurt (THWS), 97070 W\u00fcrzburg, Germany"},{"name":"Esri Deutschland GmbH, 85402 Kranzberg, Germany"}]},{"given":"Sebastian","family":"Paczkowski","sequence":"additional","affiliation":[{"name":"Department of Forest Work Science and Engineering, Georg-August-University G\u00f6ttingen, 37077 G\u00f6ttingen, Germany"}]},{"given":"Tarek","family":"Neubert","sequence":"additional","affiliation":[{"name":"Department of Forest Work Science and Engineering, Georg-August-University G\u00f6ttingen, 37077 G\u00f6ttingen, Germany"}]},{"given":"Marta","family":"Paczkowska","sequence":"additional","affiliation":[{"name":"Department of Forest Work Science and Engineering, Georg-August-University G\u00f6ttingen, 37077 G\u00f6ttingen, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2024,1,31]]},"reference":[{"key":"ref_1","unstructured":"BMEL (2023). F\u00f6rderprogramm Klimaangepasstes Waldmanagement."},{"key":"ref_2","unstructured":"Johann Heinrich von Th\u00fcnen-Institut (2017). Wald in Deutschland\u2014Wald in Zahlen. Ergebnisse der Kohlenstoffinventur 2017, Johann Heinrich von Th\u00fcnen-Institut."},{"key":"ref_3","unstructured":"BMEL (2022). Ergebnisse der Waldzustandserhebung 2022."},{"key":"ref_4","first-page":"1","article-title":"Bark Beetle Outbreaks in Europe: State of Knowledge and Ways Forward for Management","volume":"7","author":"Krokene","year":"2021","journal-title":"Curr. For. Rep."},{"key":"ref_5","first-page":"100","article-title":"The economic impact of the mountain pine beetle infestation in British Columbia: Provincial estimates from a CGE analysis","volume":"89","author":"Corbett","year":"2015","journal-title":"For. Int. J. For. Res."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Dale, V., Joyce, L., Mcnulty, S., Neilson, R., Ayres, M., Flannigan, M., Hanson, P., Irland, L., Lugo, A., and Peterson, C. (2001). Climate Change and Forest Disturbances. BioScience, 51.","DOI":"10.1641\/0006-3568(2001)051[0723:CCAFD]2.0.CO;2"},{"key":"ref_7","unstructured":"BMEL (2023). Massive Sch\u00e4den\u2014Einsatz f\u00fcr die W\u00e4lder."},{"key":"ref_8","unstructured":"Bavarian State Institute of Forestry (2022). Borkenk\u00e4ferjahr 2022, Bavarian State Institute of Forestry."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Barmpoutis, P., Stathaki, T., and Kamperidou, V. (2019, January 12\u201317). Monitoring of Trees\u2019 Health Condition Using a UAV Equipped with Low-cost Digital Camera. Proceedings of the ICASSP 2019\u20142019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.","DOI":"10.1109\/ICASSP.2019.8683128"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1080\/10095020.2017.1416994","article-title":"Unmanned aerial vehicles (UAV) for assessment of qualitative classification of Norway spruce in temperate forest stands","volume":"21","author":"Brovkina","year":"2018","journal-title":"Geo-Spat. Inf. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Mina\u0159\u00edk, R., Langhammer, J., and Lendzioch, T. (2021). Detection of Bark Beetle Disturbance at Tree Level Using UAS Multispectral Imagery and Deep Learning. Remote Sens., 13.","DOI":"10.3390\/rs13234768"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Albawi, S., Mohammed, T.A., and Al-Zawi, S. (2017, January 21\u201323). Understanding of a convolutional neural network. Proceedings of the 2017 International Conference on Engineering and Technology (ICET), Antalya, Turkey.","DOI":"10.1109\/ICEngTechnol.2017.8308186"},{"key":"ref_13","unstructured":"Immitzer, M., Vuolo, F., Einzmann, K., Ng, W.T., B\u00f6ck, S., and Atzberger, C. (2016, January 8\u20139). Verwendung von multispektralen Sentinel-2 Daten f\u00fcr die Baumartenklassifikation und Vergleich mit anderen Satellitensensoren. Proceedings of the Dreil\u00e4ndertagung der DGPF, der OVG und der SGPF, Bern, Switzerland."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wessel, M., Brandmeier, M., Tiede, D., and No, N. (2018). Evaluation of Different Machine Learning Algorithms for Scalable Classification of Tree Types and Tree Species Based on Sentinel-2 Data. Remote Sens., 10.","DOI":"10.3390\/rs10091419"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Dalponte, M., Solano-Correa, Y.T., Frizzera, L., and Gianelle, D. (2022). Mapping a European Spruce Bark Beetle Outbreak Using Sentinel-2 Remote Sensing Data. Remote Sens., 14.","DOI":"10.3390\/rs14133135"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Lausch, A., Erasmi, S., King, D.J., Magdon, P., and Heurich, M. (2017). Understanding Forest Health with Remote Sensing-Part II\u2014A Review of Approaches and Data Models. Remote Sens., 9.","DOI":"10.3390\/rs9020129"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2554","DOI":"10.1109\/JSTARS.2020.2995391","article-title":"Tree Detection and Health Monitoring in Multispectral Aerial Imagery and Photogrammetric Pointclouds Using Machine Learning","volume":"13","author":"Windrim","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Li, H., Hu, B., Li, Q., and Jing, L. (2021). CNN-Based Individual Tree Species Classification Using High-Resolution Satellite Imagery and Airborne LiDAR Data. Forests, 12.","DOI":"10.3390\/f12121697"},{"key":"ref_19","first-page":"102292","article-title":"Silvi-Net\u2014A dual-CNN approach for combined classification of tree species and standing dead trees from remote sensing data","volume":"98","author":"Briechle","year":"2021","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"112676","DOI":"10.1016\/j.rse.2021.112676","article-title":"Early detection of spruce vitality loss with hyperspectral data: Results of an experimental study in Bavaria, Germany","volume":"266","author":"Einzmann","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Nezami, S., Khoramshahi, E., Nevalainen, O., P\u00f6l\u00f6nen, I., and Honkavaara, E. (2020). Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks. Remote Sens., 12.","DOI":"10.20944\/preprints202002.0334.v1"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"112240","DOI":"10.1016\/j.rse.2020.112240","article-title":"Early detection of forest stress from European spruce bark beetle attack, and a new vegetation index: Normalized distance red & SWIR (NDRS)","volume":"255","author":"Huo","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref_23","first-page":"199","article-title":"European spruce bark beetle (Ips typographus, L.) green attack affects foliar reflectance and biochemical properties","volume":"64","author":"Abdullah","year":"2018","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"594","DOI":"10.3390\/f6030594","article-title":"Analysis of Unmanned Aerial System-Based CIR Images in Forestry\u2014A New Perspective to Monitor Pest Infestation Levels","volume":"6","author":"Lehmann","year":"2015","journal-title":"Forests"},{"key":"ref_25","first-page":"101900","article-title":"Timing of red-edge and shortwave infrared reflectance critical for early stress detection induced by bark beetle (Ips typographus, L.) attack","volume":"82","author":"Abdullah","year":"2019","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_26","unstructured":"Wiefels, A., and Baroja, C. (2022). Red Edge Detects Vegetative Stress Earlier in Plant Growth Cycle, MundoGEO Team. Section: Geospatial Technologies."},{"key":"ref_27","unstructured":"Kampen, M., Lederbauer, S., Mund, J.P., and Immitzer, M. (2019, January 20\u201322). UAV-Based Multispectral Data for Tree Species Classification and Tree Vitality Analysis. Proceedings of the Dreil\u00e4ndertagung der DGPF, der OVG und der SGPF, Vienna, Austria."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"119984","DOI":"10.1016\/j.foreco.2021.119984","article-title":"Comparison of field survey and remote sensing techniques for detection of bark beetle-infested trees","volume":"506","year":"2022","journal-title":"For. Ecol. Manag."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ecke, S., Dempewolf, J., Frey, J., Schwaller, A., Endres, E., Klemmt, H.J., Tiede, D., and Seifert, T. (2022). UAV-Based Forest Health Monitoring: A Systematic Review. Remote Sens., 14.","DOI":"10.3390\/rs14133205"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1186\/s40663-021-00342-8","article-title":"Assessing a novel modelling approach with high resolution UAV imagery for monitoring health status in priority riparian forests","volume":"8","year":"2021","journal-title":"For. Ecosyst."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Abdollahnejad, A., and Panagiotidis, D. (2020). Tree Species Classification and Health Status Assessment for a Mixed Broadleaf-Conifer Forest with UAS Multispectral Imaging. Remote Sens., 12.","DOI":"10.3390\/rs12223722"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Fraser, B.T., and Congalton, R.G. (2021). Monitoring Fine-Scale Forest Health Using Unmanned Aerial Systems (UAS) Multispectral Models. Remote Sens., 13.","DOI":"10.3390\/rs13234873"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Safonova, A., Hamad, Y., Dmitriev, E., Georgiev, G., Trenkin, V., Georgieva, M., Dimitrov, S., and Iliev, M. (2021). Individual Tree Crown Delineation for the Species Classification and Assessment of Vital Status of Forest Stands from UAV Images. Drones, 5.","DOI":"10.3390\/drones5030077"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"475","DOI":"10.5194\/isprs-archives-XLII-2-W13-475-2019","article-title":"Resnet-Based Tree Species Classification Using UAV Images","volume":"XLII-2-W13","author":"Natesan","year":"2019","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.isprsjprs.2019.07.010","article-title":"Mapping dead forest cover using a deep convolutional neural network and digital aerial photography","volume":"156","author":"Sylvain","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Safonova, A., Tabik, S., Alcaraz-Segura, D., Rubtsov, A., Maglinets, Y., and Herrera, F. (2019). Detection of Fir Trees (Abies sibirica) Damaged by the Bark Beetle in Unmanned Aerial Vehicle Images with Deep Learning. Remote Sens., 11.","DOI":"10.3390\/rs11060643"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Nguyen, H.T., Lopez Caceres, M.L., Moritake, K., Kentsch, S., Shu, H., and Diez, Y. (2021). Individual Sick Fir Tree (Abies mariesii) Identification in Insect Infested Forests by Means of UAV Images and Deep Learning. Remote Sens., 13.","DOI":"10.3390\/rs13020260"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Abu-zanona, M., Elaiwat, S., Younis, S., Innab, N., and Kamruzzaman, M.M. (2022). Classification of Palm Trees Diseases using Convolution Neural Network. Int. J. Adv. Comput. Sci. Appl., 13.","DOI":"10.14569\/IJACSA.2022.01306111"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Mamdouh, N., and Khattab, A. (2022, January 6\u20139). Olive Leaf Disease Identification Framework using Inception V3 Deep Learning. Proceedings of the 2022 IEEE International Conference on Design & Test of Integrated Micro & Nano-Systems (DTS), Cairo, Egypt.","DOI":"10.1109\/DTS55284.2022.9809893"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 22\u201329). Mask R-CNN. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_41","unstructured":"Lin, Y.L. (2021). Semi-Automatic Classification of Tree Species Using a Combination of RGB Drone Imagery and Mask RCNN: Case Study of the Highveld Region in Eswatini. [Master\u2019s Thesis, Universidade Nova de Lisboa]."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"144064","DOI":"10.1109\/ACCESS.2020.3012417","article-title":"Deep Learning-Based Automated Forest Health Diagnosis From Aerial Images","volume":"8","author":"Chiang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.rse.2016.08.013","article-title":"Review of studies on tree species classification from remotely sensed data","volume":"186","author":"Fassnacht","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_44","unstructured":"Bavarian State Forestry (2013). Fichtenw\u00e4lder in Bayern und ihre Biodiversit\u00e4t-LWF-Wissen 80, Bavarian State Forestry."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on Image Data Augmentation for Deep Learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_47","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"01052","DOI":"10.1051\/matecconf\/201823201052","article-title":"Image Captioning Based on Deep Neural Networks","volume":"232","author":"Liu","year":"2018","journal-title":"MATEC Web Conf."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Li, F.-F. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_51","unstructured":"(2023, November 19). Pytorch. Models and Pre-Trained Weights\u2014Torchvision 0.15 Documentation. Available online: https:\/\/pytorch.org\/vision\/0.15\/."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2015). Rethinking the Inception Architecture for Computer Vision. arXiv.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1016\/j.isprsjprs.2011.08.001","article-title":"An investigation into robust spectral indices for leaf chlorophyll estimation","volume":"66","author":"Main","year":"2011","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Egli, S., and H\u00f6pke, M. (2020). CNN-Based Tree Species Classification Using High Resolution RGB Image Data from Automated UAV Observations. Remote Sens., 12.","DOI":"10.3390\/rs12233892"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Saarinen, N., Vastaranta, M., N\u00e4si, R., Rosnell, T., Hakala, T., Honkavaara, E., Wulder, M.A., Luoma, V., Tommaselli, A.M.G., and Imai, N.N. (2018). Assessing Biodiversity in Boreal Forests with UAV-Based Photogrammetric Point Clouds and Hyperspectral Imaging. Remote Sens., 10.","DOI":"10.3390\/rs10020338"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"711","DOI":"10.5194\/isprs-archives-XLI-B8-711-2016","article-title":"Use of a Multispectral Uav Photogrammetry for Detection and Tracking of Forest Disturbance Dynamics","volume":"XLI-B8","author":"Langhammer","year":"2016","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.isprsjprs.2017.07.007","article-title":"Assessing very high resolution UAV imagery for monitoring forest health during a simulated disease outbreak","volume":"131","author":"Dash","year":"2017","journal-title":"ISPRS J. Photogramm. Remote Sens."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/3\/561\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:52:45Z","timestamp":1760104365000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/3\/561"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,31]]},"references-count":57,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["rs16030561"],"URL":"https:\/\/doi.org\/10.3390\/rs16030561","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,31]]}}}