{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:59:46Z","timestamp":1760147986093,"version":"build-2065373602"},"reference-count":48,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2023,3,21]],"date-time":"2023-03-21T00:00:00Z","timestamp":1679356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"China scholarship council (CSC)","award":["KL 894\/23-2","1444\/1-2"],"award-info":[{"award-number":["KL 894\/23-2","1444\/1-2"]}]},{"name":"German Research Foundation (DFG)","award":["KL 894\/23-2","1444\/1-2"],"award-info":[{"award-number":["KL 894\/23-2","1444\/1-2"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Deep learning has emerged as a prominent technique for extracting vegetation information from high-resolution satellite imagery. However, less attention has been paid to the quality of dataset labeling as compared to research into networks and models, despite data quality consistently having a high impact on final accuracies. In this work, we trained a U-Net model for tree cover segmentation in 30 cm WorldView-3 imagery and assessed the impact of training data quality on segmentation accuracy. We produced two reference tree cover masks of different qualities by labeling images accurately or roughly and trained the model on a combination of both, with varying proportions. Our results show that models trained with accurately delineated masks achieved higher accuracy (88.06%) than models trained on masks that were only roughly delineated (81.13%). When combining the accurately and roughly delineated masks at varying proportions, we found that the segmentation accuracy increased with the proportion of accurately delineated masks. Furthermore, we applied semisupervised active learning techniques to identify an efficient strategy for selecting images for labeling. This showed that semisupervised active learning saved nearly 50% of the labeling cost when applied to accurate masks, while maintaining high accuracy (88.07%). Our study suggests that accurate mask delineation and semisupervised active learning are essential for efficiently generating training datasets in the context of tree cover segmentation from high-resolution satellite imagery.<\/jats:p>","DOI":"10.3390\/rs15061691","type":"journal-article","created":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T06:00:01Z","timestamp":1679464801000},"page":"1691","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The Impacts of Quality-Oriented Dataset Labeling on Tree Cover Segmentation Using U-Net: A Case Study in WorldView-3 Imagery"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8838-8457","authenticated-orcid":false,"given":"Tao","family":"Jiang","sequence":"first","affiliation":[{"name":"Forest Inventory and Remote Sensing, Faculty of Forest Sciences and Forest Ecology, University of G\u00f6ttingen, B\u00fcsgenweg 5, D-37077 G\u00f6ttingen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5831-6150","authenticated-orcid":false,"given":"Maximilian","family":"Freudenberg","sequence":"additional","affiliation":[{"name":"Forest Inventory and Remote Sensing, Faculty of Forest Sciences and Forest Ecology, University of G\u00f6ttingen, B\u00fcsgenweg 5, D-37077 G\u00f6ttingen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8625-3492","authenticated-orcid":false,"given":"Christoph","family":"Kleinn","sequence":"additional","affiliation":[{"name":"Forest Inventory and Remote Sensing, Faculty of Forest Sciences and Forest Ecology, University of G\u00f6ttingen, B\u00fcsgenweg 5, D-37077 G\u00f6ttingen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2392-5105","authenticated-orcid":false,"given":"Alexander","family":"Ecker","sequence":"additional","affiliation":[{"name":"Institute of Computer Science and Campus Institute Data Science, University of G\u00f6ttingen, Goldschmidtstra\u00dfe 1, D-37077 G\u00f6ttingen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4925-2287","authenticated-orcid":false,"given":"Nils","family":"N\u00f6lke","sequence":"additional","affiliation":[{"name":"Forest Inventory and Remote Sensing, Faculty of Forest Sciences and Forest Ecology, University of G\u00f6ttingen, B\u00fcsgenweg 5, D-37077 G\u00f6ttingen, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2023,3,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1002\/ppp3.39","article-title":"The benefits of trees for livable and sustainable communities","volume":"1","author":"Cavender","year":"2019","journal-title":"Plants People Planet"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3005","DOI":"10.1007\/s10531-017-1453-2","article-title":"Forest biodiversity, ecosystem functioning and the provision of ecosystem services","volume":"26","author":"Brockerhoff","year":"2017","journal-title":"Biodivers. Conserv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.rse.2013.05.001","article-title":"Urban vegetation classification: Benefits of multitemporal RapidEye satellite data","volume":"136","author":"Tigges","year":"2013","journal-title":"Remote Sens. Environ."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.ufug.2018.01.021","article-title":"Mapping vegetation functional types in urban areas with WorldView-2 imagery: Integrating object-based classification with phenology","volume":"31","author":"Yan","year":"2018","journal-title":"Urban For. Urban Green."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.isprsjprs.2020.12.010","article-title":"Review on Convolutional Neural Networks (CNN) in vegetation remote sensing","volume":"173","author":"Kattenborn","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MGRS.2017.2762307","article-title":"Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources","volume":"5","author":"Zhu","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","article-title":"Fully Convolutional Networks for Semantic Segmentation","volume":"39","author":"Shelhamer","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"56267","DOI":"10.1109\/ACCESS.2022.3175978","article-title":"Land Cover Classification of Resources Survey Remote Sensing Images Based on Segmentation Model","volume":"10","author":"Fan","year":"2022","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Sol\u00f3rzano, J.V., Mas, J.F., Gao, Y., and Gallardo-Cruz, J.A. (2021). Land use land cover classification with U-net: Advantages of combining sentinel-1 and sentinel-2 imagery. Remote Sens., 13.","DOI":"10.3390\/rs13183600"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1109\/LGRS.2018.2802944","article-title":"Road extraction by deep residual u-net","volume":"15","author":"Zhang","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"108549","DOI":"10.1016\/j.patcog.2022.108549","article-title":"SDUNet: Road extraction via spatial enhanced and densely connected UNet","volume":"126","author":"Yang","year":"2022","journal-title":"Pattern Recognit."},{"key":"ref_13","first-page":"1","article-title":"Simple multiscale unet for change detection with heterogeneous remote sensing images","volume":"19","author":"Lv","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1038\/s41586-020-2824-5","article-title":"An unexpectedly large count of trees in the West African Sahara and Sahel","volume":"587","author":"Brandt","year":"2020","journal-title":"Nature"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1038\/s41558-022-01544-w","article-title":"Nation-wide mapping of tree-level aboveground carbon stocks in Rwanda","volume":"13","author":"Mugabowindekwe","year":"2022","journal-title":"Nat. Clim. Chang."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"22197","DOI":"10.1007\/s00521-022-07640-4","article-title":"Individual tree crown delineation in high-resolution remote sensing images based on U-Net","volume":"34","author":"Freudenberg","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, W., Fu, H., Yu, L., and Cracknell, A. (2017). Deep Learning Based Oil Palm Tree Detection and Counting for High-Resolution Remote Sensing Images. Remote Sens., 9.","DOI":"10.3390\/rs9010022"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Li, W., Dong, R., Fu, H., and Yu, L. (2019). Large-Scale Oil Palm Tree Detection from High-Resolution Satellite Images Using Two-Stage Convolutional Neural Networks. Remote Sens., 11.","DOI":"10.3390\/rs11010011"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Freudenberg, M., N\u00f6lke, N., Agostini, A., Urban, K., W\u00f6rg\u00f6tter, F., and Kleinn, C. (2019). Large Scale Palm Tree Detection in High Resolution Satellite Images Using U-Net. Remote Sens., 11.","DOI":"10.3390\/rs11030312"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1002\/rse2.111","article-title":"Using the U-net convolutional network to map forest types and disturbance in the Atlantic rainforest with very high resolution images","volume":"5","author":"Wagner","year":"2019","journal-title":"Remote Sens. Ecol. Conserv."},{"key":"ref_21","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 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_22","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention u-net: Learning where to look for the pancreas. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"101279","DOI":"10.1016\/j.ecoinf.2021.101279","article-title":"Amazon forest cover change mapping based on semantic segmentation by U-Nets","volume":"62","author":"Bragagnolo","year":"2021","journal-title":"Ecol. Inform."},{"key":"ref_24","first-page":"102685","article-title":"An attention-based U-Net for detecting deforestation within satellite sensor imagery","volume":"107","author":"John","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.isprsjprs.2020.09.025","article-title":"Identifying and mapping individual plants in a highly diverse high-elevation ecosystem using UAV imagery and deep learning","volume":"169","author":"Zhang","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cao, K., and Zhang, X. (2020). An Improved Res-UNet Model for Tree Species Classification Using Airborne High-Resolution Images. Remote Sens., 12.","DOI":"10.3390\/rs12071128"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chen, C., Jing, L., Li, H., and Tang, Y. (2021). A new individual tree species classification method based on the ResU-Net model. Forests, 12.","DOI":"10.3390\/f12091202"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Men, G., He, G., and Wang, G. (2021). Concatenated Residual Attention UNet for Semantic Segmentation of Urban Green Space. Forests, 12.","DOI":"10.3390\/f12111441"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Graves, S.J., Asner, G.P., Martin, R.E., Anderson, C.B., Colgan, M.S., Kalantari, L., and Bohlman, S.A. (2016). Tree species abundance predictions in a tropical agricultural landscape with a supervised classification model and imbalanced data. Remote Sens., 8.","DOI":"10.3390\/rs8020161"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ramezan, C.A., Warner, T.A., Maxwell, A.E., and Price, B.S. (2021). Effects of training set size on supervised machine-learning land-cover classification of large-area high-resolution remotely sensed data. Remote Sens., 13.","DOI":"10.3390\/rs13030368"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Hao, Z., Post, C.J., Mikhailova, E.A., Lin, L., Liu, J., and Yu, K. (2022). How Does Sample Labeling and Distribution Affect the Accuracy and Efficiency of a Deep Learning Model for Individual Tree-Crown Detection and Delineation. Remote Sens., 14.","DOI":"10.3390\/rs14071561"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, H., Cui, Z., Lei, K., Zuo, Y., Wang, J., Hu, X., and Qiu, H. (2023). Very High Resolution Images and Superpixel-Enhanced Deep Neural Forest Promote Urban Tree Canopy Detection. Remote Sens., 15.","DOI":"10.3390\/rs15020519"},{"key":"ref_33","first-page":"1","article-title":"A Survey of Deep Active Learning","volume":"54","author":"Ren","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"9524","DOI":"10.1109\/TGRS.2019.2927393","article-title":"Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery Using Deep CNNs and Active Learning","volume":"57","author":"Kellenberger","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2591","DOI":"10.1109\/TCSVT.2016.2589879","article-title":"Cost-Effective Active Learning for Deep Image Classification","volume":"27","author":"Wang","year":"2017","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhang, Y., Chen, J., Zhang, S., and Chen, D.Z. (2017, January 11\u201313). Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation. Proceedings of the MICCAI 2017: 20th International Conference, Quebec City, QC, Canada.","DOI":"10.1007\/978-3-319-66179-7_46"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"112479","DOI":"10.1016\/j.rse.2021.112479","article-title":"Mapping oil palm density at country scale: An active learning approach","volume":"261","author":"Schindler","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1007\/s10994-019-05855-6","article-title":"A survey on semi-supervised learning","volume":"109","author":"Hoos","year":"2020","journal-title":"Mach. Learn."},{"key":"ref_39","unstructured":"Sudhira, H.S., and Nagendra, H. (2013). Urbanization, Biodiversity and Ecosystem Services: Challenges and Opportunities: A Global Assessment, Springer."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.ufug.2009.12.005","article-title":"Street trees in Bangalore: Density, diversity, composition and distribution","volume":"9","author":"Nagendra","year":"2010","journal-title":"Urban For. Urban Green."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1687-6180-2011-79","article-title":"A survey of classical methods and new trends in pansharpening of multispectral images","volume":"2011","author":"Amro","year":"2011","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Carneiro, G., Mateus, D., Peter, L., Bradley, A., Tavares, J.M.R.S., Belagiannis, V., Papa, J.P., Nascimento, J.C., Loog, M., and Lu, Z. (2016, January 21). The Importance of Skip Connections in Biomedical Image Segmentation. Proceedings of the Deep Learning and Data Labeling for Medical Applications, Athens, Greece.","DOI":"10.1007\/978-3-319-46976-8"},{"key":"ref_43","unstructured":"Wang, J., Wen, S., Chen, K., Yu, J., Zhou, X., Gao, P., Li, C., and Xie, G. (2020). Semi-supervised active learning for instance segmentation via scoring predictions. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Balaram, S., Nguyen, C.M., Kassim, A., and Krishnaswamy, P. (2022, January 18\u201322). Consistency-Based Semi-supervised Evidential Active Learning for Diagnostic Radiograph Classification. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Singapore.","DOI":"10.1007\/978-3-031-16431-6_64"},{"key":"ref_45","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_46","first-page":"1050","article-title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","volume":"Volume 48","author":"Balcan","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1002\/rse2.146","article-title":"Convolutional Neural Networks accurately predict cover fractions of plant species and communities in Unmanned Aerial Vehicle imagery","volume":"6","author":"Kattenborn","year":"2020","journal-title":"Remote Sens. Ecol. Conserv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.isprsjprs.2020.08.005","article-title":"Detecting and mapping tree seedlings in UAV imagery using convolutional neural networks and field-verified data","volume":"168","author":"Pearse","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/6\/1691\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:59:48Z","timestamp":1760122788000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/6\/1691"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,21]]},"references-count":48,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["rs15061691"],"URL":"https:\/\/doi.org\/10.3390\/rs15061691","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2023,3,21]]}}}