{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T16:33:37Z","timestamp":1775147617022,"version":"3.50.1"},"reference-count":38,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T00:00:00Z","timestamp":1566432000000},"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>Storms can cause significant damage to forest areas, affecting biodiversity and infrastructure and leading to economic loss. Thus, rapid detection and mapping of windthrows are crucially important for forest management. Recent advances in computer vision have led to highly-accurate image classification algorithms such as Convolutional Neural Network (CNN) architectures. In this study, we tested and implemented an algorithm based on CNNs in an ArcGIS environment for automatic detection and mapping of damaged areas. The algorithm was trained and tested on a forest area in Bavaria, Germany. . It is a based on a modified U-Net architecture that was optimized for the pixelwise classification of multispectral aerial remote sensing data. The neural network was trained on labeled damaged areas from after-storm aerial orthophotos of a ca.     109 k  m 2      forest area with RGB and NIR bands and 0.2-m spatial resolution. Around     10 7     pixels of labeled data were used in the process. Once the network is trained, predictions on further datasets can be computed within seconds, depending on the size of the input raster and the computational power used. The overall accuracy on our test dataset was     92 %    . During visual validation, labeling errors were found in the reference data that somewhat biased the results because the algorithm in some instance performed better than the human labeling procedure, while missing areas affected by shadows. Our results are very good in terms of precision, and the methods introduced in this paper have several additional advantages compared to traditional methods: CNNs automatically detect high- and low-level features in the data, leading to high classification accuracies, while only one after-storm image is needed in comparison to two images for approaches based on change detection. Furthermore, flight parameters do not affect the results in the same way as for approaches that require DSMs and DTMs as the classification is only based on the image data themselves, and errors occurring in the computation of DSMs and DTMs do not affect the results with respect to the z component. The integration into the ArcGIS Platform allows a streamlined workflow for forest management, as the results can be accessed by mobile devices in the field to allow for high-accuracy ground-truthing and additional mapping that can be synchronized back into the database. Our results and the provided automatic workflow highlight the potential of deep learning on high-resolution imagery and GIS for fast and efficient post-disaster damage assessment as a first step of disaster management.<\/jats:p>","DOI":"10.3390\/rs11171976","type":"journal-article","created":{"date-parts":[[2019,8,23]],"date-time":"2019-08-23T10:15:07Z","timestamp":1566555307000},"page":"1976","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":127,"title":["Forest Damage Assessment Using Deep Learning on High Resolution Remote Sensing Data"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1658-8243","authenticated-orcid":false,"given":"Zayd Mahmoud","family":"Hamdi","sequence":"first","affiliation":[{"name":"Department Science and Education, Esri Deutschland, Ringstr. 7, 85402 Kranzberg, Germany"},{"name":"Technical University of Munich, 21 Arcisstra\u00dfe, 8033 Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6778-2508","authenticated-orcid":false,"given":"Melanie","family":"Brandmeier","sequence":"additional","affiliation":[{"name":"Department Science and Education, Esri Deutschland, Ringstr. 7, 85402 Kranzberg, Germany"}]},{"given":"Christoph","family":"Straub","sequence":"additional","affiliation":[{"name":"Department of Information Technology, Bavarian State Institute of Forestry, Hans Carl-von-Carlowitz-Platz 1, 85354 Freising, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2019,8,22]]},"reference":[{"key":"ref_1","unstructured":"Gardiner, B., Blennow, K., Carnus, J.M., Fleischer, P., Ingemarson, F., Landmann, G., Lindner, M., Marzano, M., Nicoll, B., and Orazio, C. (2010). Destructive storms in European forests: past and forthcoming impacts. Destructive Storms in European Forests: Past and Forthcoming Impacts, European Forest Institute."},{"key":"ref_2","first-page":"18","article-title":"Waldschutzsituation 2017 in Bayern","volume":"6","author":"Triebenbacher","year":"2018","journal-title":"AFZ-DerWald"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1038\/nclimate3303","article-title":"Forest disturbances under climate change","volume":"7","author":"Seidl","year":"2017","journal-title":"Nat. Clim. Chang."},{"key":"ref_4","first-page":"1380","article-title":"Sturmsch\u00e4den in Schwaben von 1950 bis 1980","volume":"36","year":"1981","journal-title":"Allg. Forstz."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Mokros, M., V\u00fdbot\u2019ok, J., Merganic, J., Hollaus, M., Barton, I., Koren, M., Tomast\u00edk, J., and Cernava, J. (2017). Early Stage Forest Windthrow Estimation Based on Unmanned Aircraft System Imagery. Forests, 8.","DOI":"10.3390\/f8090306"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/S0961-9534(02)00170-8","article-title":"Spatial distribution of whole-tree carbon stocks and fluxes across the forests of Europe: where are the options for bio-energy?","volume":"24","author":"Nabuurs","year":"2003","journal-title":"Biomass Bioenergy"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Einzmann, K., Immitzer, M., B\u00f6ck, S., Bauer, O., Schmitt, A., and Atzberger, C. (2017). Windthrow Detection in European Forests with Very High-Resolution Optical Data. Forests, 8.","DOI":"10.3390\/f8010021"},{"key":"ref_8","first-page":"187","article-title":"Horizontal accuracy and applicability of smartphone GNSS positioning in forests","volume":"90","author":"Piroh","year":"2016","journal-title":"Forestry"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Wessel, M., Brandmeier, M., and Tiede, D. (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_10","doi-asserted-by":"crossref","unstructured":"Ho\u015bci\u0142o, A., and Lewandowska, A. (2019). Mapping Forest Type and Tree Species on a Regional Scale Using Multi-Temporal Sentinel-2 Data. Remote Sens., 11.","DOI":"10.3390\/rs11080929"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2919","DOI":"10.3390\/rs4102919","article-title":"Laser scanning in forests","volume":"4","author":"Holopainen","year":"2012","journal-title":"Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1717","DOI":"10.1109\/LGRS.2014.2306712","article-title":"A statistical framework for near-real time detection of beetle infestation in pine forests using MODIS data","volume":"11","author":"Anees","year":"2014","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1478","DOI":"10.1890\/13-0652.1","article-title":"Tracking forest phenology and seasonal physiology using digital repeat photography: a critical assessment","volume":"24","author":"Keenan","year":"2014","journal-title":"Ecol. Appl."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"150","DOI":"10.3832\/ifor0715-006","article-title":"Rapid assessment of wind storm-caused forest damage using satellite images and stand-wise forest inventory data","volume":"6","author":"Mozgeris","year":"2013","journal-title":"iFor. Biogeosci. For."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.rse.2013.12.020","article-title":"Landsat remote sensing of forest windfall disturbance","volume":"143","author":"Baumann","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1405","DOI":"10.3390\/rs5031405","article-title":"Automatic Storm Damage Detection in Forests Using High-Altitude Photogrammetric Imagery","volume":"5","author":"Honkavaara","year":"2013","journal-title":"Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1007\/s13595-017-0669-3","article-title":"Stand-level wind damage can be assessed using diachronic photogrammetric canopy height models","volume":"74","author":"Renaud","year":"2017","journal-title":"Ann. For. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_20","unstructured":"Lu, C., Chen, H., Chen, Q., Law, H., Xiao, Y., and Tang, C.K. (2014). 1-HKUST: Object Detection in ILSVRC 2014. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1007\/s12524-019-00945-3","article-title":"Object-Oriented Method Combined with Deep Convolutional Neural Networks for Land-Use-Type Classification of Remote Sensing Images","volume":"47","author":"Jin","year":"2019","journal-title":"J. Indian Soc. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3030","DOI":"10.1109\/JSTARS.2018.2846178","article-title":"Deep Convolutional Neural Network for Complex Wetland Classification Using Optical Remote Sensing Imagery","volume":"11","author":"Rezaee","year":"2018","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_23","unstructured":"Onishi, M., and Ise, T. (2018). Automatic classification of trees using a UAV onboard camera and deep learning. arXiv."},{"key":"ref_24","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_25","doi-asserted-by":"crossref","unstructured":"Wagner, F.H., Sanchez, A., Tarabalka, Y., Lotte, R.G., Ferreira, M.P., Aidar, M.P.M., Gloor, E., Phillips, O.L., and Arag\u00e3o, L.E.O.C. (2019). Using the U-net convolutional network to map forest types and disturbance in the Atlantic rainforest with very high resolution images. Remote Sens. Ecol. Conserv.","DOI":"10.1002\/rse2.111"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hafemann, L.G., Oliveira, L.S., and Cavalin, P. (2014, January 24\u201328). Forest species recognition using deep convolutional neural networks. Proceedings of the 2014 22nd IEEE International Conference on Pattern Recognition, Stockholm, Sweden.","DOI":"10.1109\/ICPR.2014.199"},{"key":"ref_27","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1021\/ac00075a002","article-title":"Characterization of human breast biopsy specimens with near-IR Raman spectroscopy","volume":"66","author":"Frank","year":"1994","journal-title":"Anal. Chem."},{"key":"ref_29","unstructured":"Chollet, F. (2019, August 20). Keras. Available online: https:\/\/github.com\/fchollet\/keras."},{"key":"ref_30","unstructured":"Jeffrey, D. (2015). TensorFlow: A System for Large-Scale Machine Learning, Google Brain."},{"key":"ref_31","unstructured":"Kingma, D.P., and Ba, J. (2015). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_32","unstructured":"Nair, V., and Hinton, G.E. (2010, January 21\u201324). Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel."},{"key":"ref_33","unstructured":"Veli\u010dkovi\u0107, P. (2017). Be nice to your neurons: Initialisation, Normalisation, Regularisation and Optimisation. Introduction to Deep Learning (COMPGI23), University College London."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Mor\u00e9, J.J. (1978). The Levenberg-Marquardt algorithm: implementation and theory. Numerical Analysis, Springer.","DOI":"10.1007\/BFb0067700"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.agrformet.2009.09.009","article-title":"Post-hurricane forest damage assessment using satellite remote sensing","volume":"150","author":"Wang","year":"2010","journal-title":"Agric. For. Meteorol."},{"key":"ref_36","first-page":"67","article-title":"Forest damage assessment using SAR and optical data: evaluating the potential for rapid mapping in mountains","volume":"13","author":"Remelgado","year":"2014","journal-title":"EARSeL eProc."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"R\u00fcetschi, M., Small, D., and Waser, L.T. (2019). Rapid Detection of Windthrows Using Sentinel-1 C-Band SAR Data. Remote Sens., 11.","DOI":"10.3390\/rs11020115"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Eriksson, L.E.B., Fransson, J.E.S., Soja, M.J., and Santoro, M. (2012, January 22\u201327). Backscatter signatures of wind-thrown forest in satellite SAR images. Proceedings of the 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, Germany.","DOI":"10.1109\/IGARSS.2012.6352732"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/17\/1976\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:13:00Z","timestamp":1760188380000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/17\/1976"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,22]]},"references-count":38,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2019,9]]}},"alternative-id":["rs11171976"],"URL":"https:\/\/doi.org\/10.3390\/rs11171976","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,22]]}}}