{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:46:38Z","timestamp":1766159198784,"version":"build-2065373602"},"reference-count":47,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Institute of Civil Military Technology Cooperation funded by the Defense Acquisition Program Administration and Ministry of Trade, Industry and Energy of Korean government","award":["22-CM-EO-02"],"award-info":[{"award-number":["22-CM-EO-02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>With the acceleration of global warming, research on forests has become important. Vertical forest structure is an indicator of forest vitality and diversity. Therefore, further studies are essential. The investigation of forest structures has traditionally been conducted through in situ surveys, which require substantial time and money. To overcome these drawbacks, in our previous study, vertical forest structure was mapped through machine learning techniques and multi-seasonal remote sensing data, and the classification performance was improved to a 0.92 F1-score. However, the use of multi-seasonal images includes tree location errors owing to changes in the timing and location of acquisition between images. This error can be reduced by using a modified U-Net model that generates a low-resolution output map from high-resolution input data. Therefore, we mapped vertical forest structures from a multi-seasonal unmanned aerial vehicle (UAV) optic and LiDAR data using three modified U-Net models to improve mapping performance. Spectral index maps related to forests were calculated as optic images, and canopy height maps were produced using the LiDAR-derived digital surface model (DSM) and digital terrain model (DTM). Spectral index maps and filtered canopy height maps were then used as input data and applied to the following three models: (1) a model that modified only the structure of the decoder, (2) a model that modified both the structure of the encoder and decoder, and (3) a model that modified the encoder, decoder, and the part that concatenated the encoder and decoder. Model 1 had the best performance with an F1-score of 0.97. The F1-score value was higher than 0.9 for both Model 2 and Model 3. Model 1 improved the performance by 5%, compared to our previous research. This implies that the model performance is enhanced by reducing the influence of position error.<\/jats:p>","DOI":"10.3390\/rs15112833","type":"journal-article","created":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T02:04:21Z","timestamp":1685412261000},"page":"2833","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Forest Vertical Structure Mapping Using Multi-Seasonal UAV Images and Lidar Data via Modified U-Net Approaches"],"prefix":"10.3390","volume":"15","author":[{"given":"Jin-Woo","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Geoinformatics, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, Republic of Korea"},{"name":"Department of Smart Cities, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2335-8438","authenticated-orcid":false,"given":"Hyung-Sup","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Geoinformatics, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, Republic of Korea"},{"name":"Department of Smart Cities, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, Republic of Korea"}]}],"member":"1968","published-online":{"date-parts":[[2023,5,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"4197","DOI":"10.1073\/pnas.0708921105","article-title":"A rapid upward shift of a forest ecotone during 40 years of warming in the Green Mountains of Vermont","volume":"105","author":"Beckage","year":"2008","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/s10584-005-6960-6","article-title":"An overview of terrestrial sequestration of carbon dioxide: The United States Department of Energy\u2019s fossil energy R&D program","volume":"74","author":"Litynski","year":"2006","journal-title":"Clim. Change"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/s13157-013-0382-4","article-title":"Insuring mangrove forests for their role in mitigating coastal erosion and storm-surge: An Australian case study","volume":"33","author":"Bell","year":"2013","journal-title":"Wetlands"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1016\/j.rse.2005.11.004","article-title":"Predicting lidar measured forest vertical structure from multi-angle spectral data","volume":"100","author":"Kimes","year":"2006","journal-title":"Remote Sens. Environ."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"160521","DOI":"10.1098\/rsos.160521","article-title":"The importance of forest structure to biodiversity\u2013productivity relationships","volume":"4","author":"Bohn","year":"2017","journal-title":"R. Soc. Open Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.rse.2014.11.011","article-title":"Quantifying forest canopy traits: Imaging spectroscopy versus field survey","volume":"158","author":"Asner","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/s40663-019-0173-3","article-title":"Forest in situ observations using unmanned aerial vehicle as an alternative of terrestrial measurements","volume":"6","author":"Liang","year":"2019","journal-title":"For. Ecosyst."},{"key":"ref_8","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_9","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/S0169-5347(03)00070-3","article-title":"Remote sensing for biodiversity science and conservation","volume":"18","author":"Turner","year":"2003","journal-title":"Trends Ecol. Evol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TGRS.2007.904836","article-title":"Remote estimation of crop chlorophyll content using spectral indices derived from hyperspectral data","volume":"46","author":"Haboudane","year":"2008","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_11","unstructured":"Campbell, J.B., and Wynne, R.H. (2011). Introduction to Remote Sensing, Guilford Press."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1007\/s11831-019-09344-w","article-title":"A survey of deep learning and its applications: A new paradigm to machine learning","volume":"27","author":"Dargan","year":"2020","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1002\/jcc.24764","article-title":"Deep learning for computational chemistry","volume":"38","author":"Goh","year":"2017","journal-title":"J. Comput. Chem."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Park, S.H., Jung, H.S., Lee, S., and Kim, E.S. (2021). Mapping Forest Vertical Structure in Sogwang-ri Forest from Full-Waveform Lidar Point Clouds Using Deep Neural Network. Remote Sens., 13.","DOI":"10.3390\/rs13183736"},{"key":"ref_16","first-page":"447","article-title":"Forest vertical Structure classification in Gongju city, Korea from optic and RADAR satellite images using artificial neural network","volume":"35","author":"Lee","year":"2019","journal-title":"Korean J. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yu, J.W., Yoon, Y.W., Baek, W.K., and Jung, H.S. (2021). Forest Vertical Structure Mapping Using Two-Seasonal Optic Images and LiDAR DSM Acquired from UAV Platform through Random Forest, XGBoost, and Support Vector Machine Approaches. Remote Sens., 13.","DOI":"10.3390\/rs13214282"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.eja.2014.01.004","article-title":"Tree height quantification using very high resolution imagery ac-quired from an unmanned aerial vehicle and automatic 3D photo-reconstruction methods","volume":"55","author":"Angileri","year":"2014","journal-title":"Eur. J. Agron."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1736","DOI":"10.3390\/rs70201736","article-title":"Time series analysis of landslide dynamics using an unmanned aerial vehicle","volume":"7","author":"Turner","year":"2015","journal-title":"Remote Sens."},{"key":"ref_20","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_21","doi-asserted-by":"crossref","unstructured":"Sun, X., Zhang, P., Wang, D., Cao, Y., and Liu, B. (2019, January 16\u201319). Colorectal polyp segmentation by u-net with dilation convolution. Proceedings of the 2019 18th IEEE International Conference On Machine Learning And21 Applications, Boca Raton, FL, USA.","DOI":"10.1109\/ICMLA.2019.00148"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"104449","DOI":"10.1016\/j.compbiomed.2021.104449","article-title":"Hybrid dilation and attention residual U-Net for medical image segmentation","volume":"134","author":"Wang","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1834","DOI":"10.1002\/ima.22571","article-title":"ME-Net: Multi-encoder net framework for brain tumor seg-mentation","volume":"31","author":"Zhang","year":"2021","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"ref_24","unstructured":"Korea University (2018). Development of Analyzing Method for Three-Dimensional Vegetation Structure and Policy Application Using Drone, Korea Environmental Industry & Technology Institute."},{"key":"ref_25","unstructured":"Kim, J.H. (2019). Seasonal Changes in Plants in Temperate Forests in Korea. [Ph.D. Thesis, The Seoul National University]."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1644","DOI":"10.3390\/rs3081644","article-title":"Evaluation of sub-pixel cloud noises on MODIS daily spectral indices based on in situ measurements","volume":"3","author":"Motohka","year":"2011","journal-title":"Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2188","DOI":"10.1109\/LGRS.2015.2450218","article-title":"An analysis of shadow effects on spectral vegetation indexes using a ground-based imaging spectrometer","volume":"12","author":"Zhang","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1590\/S1982-21702016000100006","article-title":"Topographic effect on spectral vegetation indices from landsat TM data: Is topographic correction necessary?","volume":"22","author":"Valeriano","year":"2016","journal-title":"Bol. De Ci\u00eancias Geod\u00e9sicas"},{"key":"ref_29","first-page":"167","article-title":"Reducing background effects in orchards through spectral vegetation index correction","volume":"34","author":"Tits","year":"2015","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Pettorelli, N. (2013). The Normalized Difference Vegetation Index, Oxford University Press.","DOI":"10.1093\/acprof:osobl\/9780199693160.001.0001"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Garc\u00eda C\u00e1rdenas, D.A., Ram\u00f3n Valencia, J.A., Alzate Vel\u00e1squez, D.F., and Palacios Gonzalez, J.R. (2018, January 21\u201323). Dynamics of the indices NDVI and GNDVI in a rice growing in its reproduction phase from multi-spectral aerial images taken by drones. Proceedings of the International Conference of ICT for Adapting Agriculture to Climate Change, Cali, Colombia.","DOI":"10.1007\/978-3-030-04447-3_7"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1080\/22797254.2019.1572459","article-title":"Detection of irrigation inhomogeneities in an olive grove using the NDRE vegetation index ob-tained from UAV images","volume":"52","author":"Jorge","year":"2019","journal-title":"Eur. J. Remote Sens."},{"key":"ref_33","first-page":"221","article-title":"Semi-empirical indices to assess carotenoids\/chlorophyll a ratio from leaf spectral reflectance","volume":"31","author":"Penuelas","year":"1995","journal-title":"Photosynthetica"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"128","DOI":"10.14445\/22312803\/IJCTT-V48P126","article-title":"Supervised machine learning algo-rithms: Classification and comparison","volume":"48","author":"Osisanwo","year":"2017","journal-title":"Int. J. Comput. Trends Technol."},{"key":"ref_35","first-page":"547","article-title":"Effectiveness of normalization pre-processing of big data to the machine learning performance","volume":"14","author":"Jo","year":"2019","journal-title":"J. Korea Inst. Electron. Commun. Sci."},{"key":"ref_36","unstructured":"Benesty, J., Chen, J., Huang, Y., and Cohen, I. (2009). Noise Reduction in Speech Processing, Springer."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/0034-4257(95)00189-1","article-title":"An object-specific image-texture analysis of H-resolution forest imagery","volume":"55","author":"Hay","year":"1996","journal-title":"Remote Sens. Environ."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Kwon, S.K., Jung, H.S., Baek, W.K., and Kim, D. (2017). Classification of forest vertical structure in south Korea from aerial orthophoto and lidar data using an artificial neural network. Appl. Sci., 7.","DOI":"10.3390\/app7101046"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Lee, B., Yamanakkanavar, N., and Choi, J.Y. (2020). Automatic segmentation of brain MRI using a novel patch-wise U-net deep architecture. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0236493"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/BF00135077","article-title":"Alternative model formulations for a stochastic simulation of landscape change","volume":"9","author":"Flamm","year":"1994","journal-title":"Landsc. Ecol."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Kwak, G.H., and Park, N.W. (2019). Impact of texture information on crop classification with machine learning and UAV images. Appl. Sci., 9.","DOI":"10.3390\/app9040643"},{"key":"ref_42","first-page":"29935","article-title":"Data augmentation can improve robustness","volume":"34","author":"Rebuffi","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"112322","DOI":"10.1016\/j.rse.2021.112322","article-title":"Tree species classification from airborne hyperspectral and LiDAR data using 3D convolutional neural networks","volume":"256","author":"Kivinen","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1002\/(SICI)1097-4571(199401)45:1<12::AID-ASI2>3.0.CO;2-L","article-title":"The relationship between recall and precision","volume":"45","author":"Buckland","year":"1994","journal-title":"J. Am. Soc. Inf. Sci."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1002\/(SICI)1097-4571(198905)40:3<145::AID-ASI1>3.0.CO;2-I","article-title":"Recall-precision trade-off: A derivation","volume":"40","author":"Gordon","year":"1989","journal-title":"J. Am. Soc. Inf. Sci."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1002\/bimj.201800148","article-title":"Tuning model parameters in class-imbalanced learning with precision-recall curve","volume":"61","author":"Fu","year":"2019","journal-title":"Biom. J."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Chicco, D., and Jurman, G. (2020). The advantages of the Matthews correlation coefficient over F1 score and accuracy in binary clas-sification evaluation. BMC Genom., 21.","DOI":"10.1186\/s12864-019-6413-7"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/11\/2833\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:44:41Z","timestamp":1760125481000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/11\/2833"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":47,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["rs15112833"],"URL":"https:\/\/doi.org\/10.3390\/rs15112833","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2023,5,29]]}}}