{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:35:16Z","timestamp":1781973316948,"version":"3.54.5"},"reference-count":35,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2020,3,26]],"date-time":"2020-03-26T00:00:00Z","timestamp":1585180800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, biomass estimation, etc. Deep neural networks (DNN) have shown superior results when comparing with conventional machine learning methods such as multi-layer perceptron (MLP) in cases of huge input data. The objective of this research is to investigate 3D convolutional neural networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were employed to classify tree species in a test site in Finland. The classifiers were trained with a dataset of 3039 manually labelled trees. Then the accuracies were assessed by employing independent datasets of 803 records. To find the most efficient set of feature combination, we compare the performances of 3D-CNN models trained with hyperspectral (HS) channels, Red-Green-Blue (RGB) channels, and canopy height model (CHM), separately and combined. It is demonstrated that the proposed 3D-CNN model with RGB and HS layers produces the highest classification accuracy. The producer accuracy of the best 3D-CNN classifier on the test dataset were 99.6%, 94.8%, and 97.4% for pines, spruces, and birches, respectively. The best 3D-CNN classifier produced ~5% better classification accuracy than the MLP with all layers. Our results suggest that the proposed method provides excellent classification results with acceptable performance metrics for HS datasets. Our results show that pine class was detectable in most layers. Spruce was most detectable in RGB data, while birch was most detectable in the HS layers. Furthermore, the RGB datasets provide acceptable results for many low-accuracy applications.<\/jats:p>","DOI":"10.3390\/rs12071070","type":"journal-article","created":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T03:44:13Z","timestamp":1585712653000},"page":"1070","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":95,"title":["Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks"],"prefix":"10.3390","volume":"12","author":[{"given":"Somayeh","family":"Nezami","sequence":"first","affiliation":[{"name":"Department of Remote Sensing and Photogrammetry of the Finnish Geospatial Research Institute FGI, Geodeetinrinne 2, FI-02430 Masala, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7352-9138","authenticated-orcid":false,"given":"Ehsan","family":"Khoramshahi","sequence":"additional","affiliation":[{"name":"Department of Remote Sensing and Photogrammetry of the Finnish Geospatial Research Institute FGI, Geodeetinrinne 2, FI-02430 Masala, Finland"},{"name":"Department of Computer Science, University of Helsinki, FI-00560 Helsinki, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4826-2929","authenticated-orcid":false,"given":"Olli","family":"Nevalainen","sequence":"additional","affiliation":[{"name":"Finnish Meteorological Institute, Climate System Research, 00560 Helsinki, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5129-7364","authenticated-orcid":false,"given":"Ilkka","family":"P\u00f6l\u00f6nen","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, University of Jyv\u00e4skyl\u00e4, Mattilanniemi 2, 40014 Jyv\u00e4skyl\u00e4, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7236-2145","authenticated-orcid":false,"given":"Eija","family":"Honkavaara","sequence":"additional","affiliation":[{"name":"Department of Remote Sensing and Photogrammetry of the Finnish Geospatial Research Institute FGI, Geodeetinrinne 2, FI-02430 Masala, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,3,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Yu, X., Hyypp\u00e4, J., Litkey, P., Kaartinen, H., Vastaranta, M., and Holopainen, M. (2017). Single-Sensor Solution to Tree Species Classification Using Multispectral Airborne Laser Scanning. Remote Sens., 9.","DOI":"10.3390\/rs9020108"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"P\u00f6l\u00f6nen, I., Annala, L., Rahkonen, S., Nevalainen, O., Honkavaara, E., Tuominen, S., Viljanen, N., and Hakala, T. (2018, January 23\u201326). Tree Species Identification Using 3D Spectral Data and 3D Convolutional Neural Network. Proceedings of the 2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), Amsterdam, The Netherlands.","DOI":"10.1109\/WHISPERS.2018.8747253"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5019","DOI":"10.3390\/rs6065019","article-title":"Object-based image classification of summer crops with machine learning methods","volume":"6","author":"Six","year":"2014","journal-title":"Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, H., and Shen, Q. (2017). Spectral\u2013spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sens., 9.","DOI":"10.3390\/rs9010067"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2094","DOI":"10.1109\/JSTARS.2014.2329330","article-title":"Deep learning-based classification of hyperspectral data","volume":"7","author":"Chen","year":"2014","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Xie, Z., Chen, Y., Lu, D., Li, G., and Chen, E. (2019). Classification of Land Cover, Forest, and Tree Species Classes with ZiYuan-3 Multispectral and Stereo Data. Remote Sens., 11.","DOI":"10.3390\/rs11020164"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Nevalainen, O., Honkavaara, E., Tuominen, S., Viljanen, N., Hakala, T., Yu, X., Hyypp\u00e4, J., Saari, H., P\u00f6l\u00f6nen, I., and Imai, N.N. (2017). Individual tree detection and classification with UAV-based photogrammetric point clouds and hyperspectral imaging. Remote Sens., 9.","DOI":"10.3390\/rs9030185"},{"key":"ref_8","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_9","first-page":"49","article-title":"Extreme Learning Machine for classification of high resolution remote sensing images and its comparison with traditional Artificial Neural Networks (ANN)","volume":"13","author":"Shrestha","year":"2014","journal-title":"EARSeL eProc."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ji, S., Zhang, C., Xu, A., Shi, Y., and Duan, Y. (2018). 3D convolutional neural networks for crop classification with multi-temporal remote sensing images. Remote Sens., 10.","DOI":"10.3390\/rs10010075"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Honkavaara, E., and Khoramshahi, E. (2018). Radiometric correction of close-range spectral image blocks captured using an unmanned aerial vehicle with a radiometric block adjustment. Remote Sens., 10.","DOI":"10.3390\/rs10020256"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Friedman, J., Hastie, T., and Tibshirani, R. (2001). The Elements of Statistical Learning, Springer Series in Statistics.","DOI":"10.1007\/978-0-387-21606-5"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1080\/22797254.2017.1299557","article-title":"Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images","volume":"50","author":"Raczko","year":"2017","journal-title":"Eur. J. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5236","DOI":"10.1080\/01431161.2017.1363442","article-title":"Deciduous tree species classification using object-based analysis and machine learning with unmanned aerial vehicle multispectral data","volume":"39","author":"Franklin","year":"2018","journal-title":"Int. J. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/S0034-4257(03)00140-8","article-title":"Identifying species of individual trees using airborne laser scanner","volume":"90","author":"Holmgren","year":"2004","journal-title":"Remote Sens. Environ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1080\/2150704X.2018.1458344","article-title":"A study on the drivers of canopy reflectance variability in a boreal forest","volume":"9","author":"Hadi","year":"2018","journal-title":"Remote Sens. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Hovi, A., Raitio, P., and Rautiainen, M. (2017). A spectral analysis of 25 boreal tree species. Silva Fenn., 51.","DOI":"10.14214\/sf.7753"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"319","DOI":"10.14214\/sf.156","article-title":"Tree species classification using airborne LiDAR\u2013effects of stand and tree parameters, downsizing of training set, intensity normalization, and sensor type","volume":"44","author":"Korpela","year":"2010","journal-title":"Silva Fenn."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2632","DOI":"10.1109\/TGRS.2012.2216272","article-title":"Tree Species Classification in Boreal Forests with Hyperspectral Data","volume":"51","author":"Dalponte","year":"2013","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","first-page":"152","article-title":"Exploring full-waveform LiDAR parameters for tree species classification","volume":"13","author":"Heinzel","year":"2011","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_21","first-page":"101","article-title":"Investigating multiple data sources for tree species classification in temperate forest and use for single tree delineation","volume":"18","author":"Heinzel","year":"2012","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/j.rse.2012.03.027","article-title":"Tree species classification and estimation of stem volume and DBH based on single tree extraction by exploiting airborne full-waveform LiDAR data","volume":"123","author":"Yao","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_23","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_24","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.isprsjprs.2019.01.019","article-title":"Tree species classification in tropical forests using visible to shortwave infrared WorldView-3 images and texture analysis","volume":"149","author":"Ferreira","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tuominen, S., Balazs, A., Honkavaara, E., P\u00f6l\u00f6nen, I., Saari, H., Hakala, T., and Viljanen, N. (2017). Hyperspectral UAV-imagery and photogrammetric canopy height model in estimating forest stand variables. Silva Fenn., 51.","DOI":"10.14214\/sf.7721"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"5006","DOI":"10.3390\/rs5105006","article-title":"Processing and assessment of spectrometric, stereoscopic imagery collected using a lightweight UAV spectral camera for precision agriculture","volume":"5","author":"Honkavaara","year":"2013","journal-title":"Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"81860Y","DOI":"10.1117\/12.897712","article-title":"Unmanned aerial vehicle (UAV) operated megapixel spectral camera","volume":"Volume 8186","author":"Holmlund","year":"2011","journal-title":"Electro-Optical Remote Sensing, Photonic Technologies, and Applications V"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"88891O","DOI":"10.1117\/12.2028972","article-title":"Miniaturized hyperspectral imager calibration and UAV flight campaigns","volume":"Volume 8889","author":"Saari","year":"2013","journal-title":"Sensors, Systems, and Next-Generation Satellites XVII"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.isprsjprs.2017.10.014","article-title":"Band registration of tuneable frame format hyperspectral UAV imagers in complex scenes","volume":"134","author":"Honkavaara","year":"2017","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/BF02551274","article-title":"Approximation by superpositions of a sigmoidal function","volume":"2","author":"Cybenko","year":"1989","journal-title":"Math. Control Signals Syst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/0893-6080(91)90009-T","article-title":"Approximation capabilities of multilayer feedforward networks","volume":"4","author":"Hornik","year":"1991","journal-title":"Neural Netw."},{"key":"ref_32","unstructured":"Dumoulin, V., and Visin, F. (2016). A guide to convolution arithmetic for deep learning. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","article-title":"The use of the area under the ROC curve in the evaluation of machine learning algorithms","volume":"30","author":"Bradley","year":"1997","journal-title":"Pattern Recognit."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Vedaldi, A., and Lenc, K. (2015, January 26\u201330). Matconvnet: Convolutional neural networks for matlab. Proceedings of the 23rd ACM International Conference on Multimedia, Brisbane, Australia.","DOI":"10.1145\/2733373.2807412"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Aasen, H., Honkavaara, E., Lucieer, A., and Zarco-Tejada, P.J. (2018). Quantitative remote sensing at ultra-high resolution with UAV spectroscopy: A review of sensor technology, measurement procedures, and data correction workflows. Remote Sens., 10.","DOI":"10.3390\/rs10071091"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/7\/1070\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:12:01Z","timestamp":1760173921000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/7\/1070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,26]]},"references-count":35,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2020,4]]}},"alternative-id":["rs12071070"],"URL":"https:\/\/doi.org\/10.3390\/rs12071070","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,26]]}}}