{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T06:56:30Z","timestamp":1768892190637,"version":"3.49.0"},"reference-count":50,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T00:00:00Z","timestamp":1733702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union","award":["101160158"],"award-info":[{"award-number":["101160158"]}]},{"name":"European Union","award":["739578"],"award-info":[{"award-number":["739578"]}]},{"name":"European Union\u2019s Horizon 2020 research and innovation programme","award":["101160158"],"award-info":[{"award-number":["101160158"]}]},{"name":"European Union\u2019s Horizon 2020 research and innovation programme","award":["739578"],"award-info":[{"award-number":["739578"]}]},{"name":"Government of the Republic of Cyprus","award":["101160158"],"award-info":[{"award-number":["101160158"]}]},{"name":"Government of the Republic of Cyprus","award":["739578"],"award-info":[{"award-number":["739578"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Forest ecosystems play an essential role in ecological balance, supporting biodiversity and climate change mitigation. These ecosystems are crucial not only for ecological stability but also for the local economy. Performing a tree census at a country scale via traditional methods is resource-demanding, error-prone, and requires significant effort by a large number of experts. While emerging technologies such as satellite imagery and AI provide the means for achieving promising results in this task with less effort, considerable effort is still required by experts to annotate hundreds or thousands of images. This study introduces a novel methodology for a tree census classification system which leverages historical and partially labeled data, employs probabilistic data imputation and a weakly supervised training technique, and thus achieves state-of-the-art precision in classifying the dominant tree species of Cyprus. A crucial component of our methodology is a ResNet50 model which takes as input high spatial resolution satellite imagery in the visible band and near-infrared band, as well as topographical features. By applying a multimodal training approach, a classification accuracy of 90% among nine targeted tree species is achieved.<\/jats:p>","DOI":"10.3390\/rs16234611","type":"journal-article","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T10:11:47Z","timestamp":1733739107000},"page":"4611","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A Weakly Supervised Multimodal Deep Learning Approach for Large-Scale Tree Classification: A Case Study in Cyprus"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7432-332X","authenticated-orcid":false,"given":"Arslan","family":"Amin","sequence":"first","affiliation":[{"name":"Cyens Centre of Excellence, Dimarchou Lellou Dimitriadi 23, Nicosia 1016, Cyprus"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8484-4256","authenticated-orcid":false,"given":"Andreas","family":"Kamilaris","sequence":"additional","affiliation":[{"name":"Cyens Centre of Excellence, Dimarchou Lellou Dimitriadi 23, Nicosia 1016, Cyprus"},{"name":"Department of Computer Science, University of Twente, 7522 NB Enschede, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4034-7709","authenticated-orcid":false,"given":"Savvas","family":"Karatsiolis","sequence":"additional","affiliation":[{"name":"Cyens Centre of Excellence, Dimarchou Lellou Dimitriadi 23, Nicosia 1016, Cyprus"}]}],"member":"1968","published-online":{"date-parts":[[2024,12,9]]},"reference":[{"key":"ref_1","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_2","doi-asserted-by":"crossref","first-page":"120186","DOI":"10.1016\/j.foreco.2022.120186","article-title":"Managing existing forests can mitigate climate change","volume":"513","author":"Kauppi","year":"2022","journal-title":"For. Ecol. Manag."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Psistaki, K., Tsantopoulos, G., and Paschalidou, A.K. (2024). An Overview of the Role of Forests in Climate Change Mitigation. Sustainability, 16.","DOI":"10.3390\/su16146089"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"174168","DOI":"10.1016\/j.scitotenv.2024.174168","article-title":"Adaptive forest management improves stand-level resilience of temperate forests under multiple stressors","volume":"948","author":"Guignabert","year":"2024","journal-title":"Sci. Total Environ."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1016\/j.oneear.2020.08.016","article-title":"The Number and Spatial Distribution of Forest-Proximate People Globally","volume":"3","author":"Newton","year":"2020","journal-title":"One Earth"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"100366","DOI":"10.1016\/j.envc.2021.100366","article-title":"Tree population structure, diversity, regeneration status, and potential disturbances in Abu Gadaf natural reserved forest, Sudan","volume":"5","author":"Mohammed","year":"2021","journal-title":"Environ. Chall."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"He, T., Zhou, H., Xu, C., Hu, J., Xue, X., Xu, L., Lou, X., Zeng, K., and Wang, Q. (2023). Deep Learning in Forest Tree Species Classification Using Sentinel-2 on Google Earth Engine: A Case Study of Qingyuan County. Sustainability, 15.","DOI":"10.3390\/su15032741"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"106844","DOI":"10.1016\/j.compag.2022.106844","article-title":"A comprehensive review of remote sensing platforms, sensors, and applications in nut crops","volume":"197","author":"Jafarbiglu","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"111716","DOI":"10.1016\/j.rse.2020.111716","article-title":"Deep learning in environmental remote sensing: Achievements and challenges","volume":"241","author":"Yuan","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Jiang, X., Jiang, M., Gou, Y., Li, Q., and Zhou, Q. (2022). Forestry Digital Twin with Machine Learning in Landsat 7 Data. Front. Plant Sci., 13.","DOI":"10.3389\/fpls.2022.916900"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"D\u00f6llner, J., de Amicis, R., Burmeister, J.M., and Richter, R. (2023, January 9\u201311). Forests in the Digital Age: Concepts and Technologies for Designing and Deploying Forest Digital Twins. Proceedings of the 28th International ACM Conference on 3D Web Technology, San Sebastian, Spain.","DOI":"10.1145\/3611314.3616067"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Jamil, A., Padubidri, C., Karatsiolis, S., Kalita, I., Guley, A., and Kamilaris, A. (2023). GAEA: A Country-Scale Geospatial Environmental Modelling Tool: Towards a Digital Twin for Real Estate. Environmental Informatics, Springer Nature.","DOI":"10.1007\/978-3-031-46902-2_10"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Prodromou, M., Theocharidis, C., Gitas, I.Z., Eliades, F., Themistocleous, K., Papasavvas, K., Dimitrakopoulos, C., Danezis, C., and Hadjimitsis, D. (2024). Forest habitat mapping in Natura2000 regions in Cyprus using Sentinel-1, Sentinel-2 and topographical features. Remote Sens., 16.","DOI":"10.3390\/rs16081373"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Lechner, M., Dost\u00e1lov\u00e1, A., Hollaus, M., Atzberger, C., and Immitzer, M. (2022). Combination of Sentinel-1 and Sentinel-2 data for tree species classification in a Central European biosphere reserve. Remote Sens., 14.","DOI":"10.3390\/rs14112687"},{"key":"ref_15","unstructured":"Rolnick, D., Veit, A., Belongie, S., and Shavit, N. (2018). Deep Learning is Robust to Massive Label Noise. arXiv."},{"key":"ref_16","first-page":"102318","article-title":"Tree species classification using Sentinel-2 imagery and Bayesian inference","volume":"100","author":"Axelsson","year":"2021","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Persson, M., Lindberg, E., and Reese, H. (2018). Tree Species Classification with Multi-Temporal Sentinel-2 Data. Remote Sens., 10.","DOI":"10.3390\/rs10111794"},{"key":"ref_18","first-page":"32","article-title":"Use of Sentinel-2 for forest classification in Mediterranean environments","volume":"42","author":"Puletti","year":"2018","journal-title":"Ann. Silvic. Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1016\/j.rse.2017.09.031","article-title":"Fractional cover mapping of spruce and pine at 1ha resolution combining very high and medium spatial resolution satellite imagery","volume":"204","author":"Immitzer","year":"2018","journal-title":"Remote Sens. Environ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"111811","DOI":"10.1016\/j.rse.2020.111811","article-title":"Discriminating tree species at different taxonomic levels using multi-temporal WorldView-3 imagery in Washington D.C., USA","volume":"246","author":"Fang","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, B., Liu, J., Li, J., and Li, M. (2023). UAV LiDAR and Hyperspectral Data Synergy for Tree Species Classification in the Maoershan Forest Farm Region. Remote Sens., 15.","DOI":"10.3390\/rs15041000"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2661","DOI":"10.3390\/rs4092661","article-title":"Tree Species Classification with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data","volume":"4","author":"Immitzer","year":"2012","journal-title":"Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Shelestov, A., Lavreniuk, M., Kussul, N., Novikov, A., and Skakun, S. (2017). Exploring Google Earth Engine Platform for Big Data Processing: Classification of Multi-Temporal Satellite Imagery for Crop Mapping. Front. Earth Sci., 5.","DOI":"10.3389\/feart.2017.00017"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Welle, T., Aschenbrenner, L., Kuonath, K., Kirmaier, S., and Franke, J. (2022). Mapping Dominant Tree Species of German Forests. Remote Sens., 14.","DOI":"10.3390\/rs14143330"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Koonce, B. (2021). ResNet 50. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, Apress.","DOI":"10.1007\/978-1-4842-6168-2"},{"key":"ref_26","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_27","doi-asserted-by":"crossref","first-page":"5349","DOI":"10.1109\/TNNLS.2020.2966319","article-title":"Why ResNet Works? Residuals Generalize","volume":"31","author":"He","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely Connected Convolutional Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Liu, Y., Gong, W., Hu, X., and Gong, J. (2018). Forest Type Identification with Random Forest Using Sentinel-1A, Sentinel-2A, Multi-Temporal Landsat-8 and DEM Data. Remote Sens., 10.","DOI":"10.3390\/rs10060946"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chiang, S.H., and Valdez, M. (2019). Tree Species Classification by Integrating Satellite Imagery and Topographic Variables Using Maximum Entropy Method in a Mongolian Forest. Forests, 10.","DOI":"10.3390\/f10110961"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"111392","DOI":"10.1016\/j.ecolind.2023.111392","article-title":"Improving Grassland Classification Accuracy Using Optimal Spectral-Phenological-Topographic Features in Combination with Machine Learning Algorithm","volume":"158","author":"Yu","year":"2024","journal-title":"Ecol. Indic."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chiang, S.H., Valdez, M., and Chen, C.F. (2016, January 12\u201319). Forest Tree Species Distribution Mapping Using Landsat Satellite Imagery and Topographic Variables with the Maximum Entropy Method in Mongolia. Proceedings of the International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXIII ISPRS Congress, ISPRS, Prague, Czech Republic.","DOI":"10.5194\/isprsarchives-XLI-B8-593-2016"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Illarionova, S., Trekin, A., Ignatiev, V., and Oseledets, I. (2021). Tree Species Mapping on Sentinel-2 Satellite Imagery with Weakly Supervised Classification and Object-Wise Sampling. Forests, 12.","DOI":"10.3390\/f12101413"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Yin, H., Khamzina, A., Pflugmacher, D., and Martius, C. (2017). Forest cover mapping in post-Soviet Central Asia using multi-resolution remote sensing imagery. Sci. Rep., 7.","DOI":"10.1038\/s41598-017-01582-x"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/s00606-011-0453-z","article-title":"High genetic diversity and significant population structure in Cedrus brevifolia Henry, a narrow endemic Mediterranean tree from Cyprus","volume":"294","author":"Eliades","year":"2011","journal-title":"Plant Syst. Evol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"185","DOI":"10.5091\/plecevo.2018.1423","article-title":"Assessment of plant species diversity associated with the carob tree (Ceratonia siliqua, Fabaceae) at the Mediterranean scale","volume":"151","author":"Baumel","year":"2018","journal-title":"Plant Ecol. Evol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"345","DOI":"10.17221\/52\/2018-JFS","article-title":"Ecological assessment of Juniperus turbinata Guss. forest on the Strofades Islands, Ionian Sea, Greece","volume":"64","author":"Martinis","year":"2018","journal-title":"J. For. Sci."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.21833\/ijaas.2019.11.001","article-title":"Plant biodiversity and values of cultural landscapes in Cyprus","volume":"6","author":"Ozden","year":"2019","journal-title":"Int. J. Adv. Appl. Sci."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"107234","DOI":"10.1016\/j.agee.2020.107234","article-title":"Olive agroforestry can improve land productivity even under low water availability in the South Mediterranean","volume":"307","author":"Fida","year":"2021","journal-title":"Agric. Ecosyst. Environ."},{"key":"ref_40","unstructured":"Mauri, A., Di Leo, M., de Rigo, D., and Caudullo, G. (2016). Pinus halepensis and Pinus brutia in Europe: Distribution, habitat, usage and threats. European Atlas of Forest Tree Species, European Union."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zagorcheva, T., Rusanov, K., Bosmali, E., Savvides, A., Madesis, P., Fotopoulos, V., Rusanova, M., Ustabashiev, F., and Atanassov, I. (2024). SRAP markers for characterization of the genetic diversity and differentiation of Pinus nigra populations in protected forested areas in Bulgaria, Greece, and Cyprus. Biotechnol. Biotechnol. Equip., 38.","DOI":"10.1080\/13102818.2024.2331192"},{"key":"ref_42","first-page":"291","article-title":"Contribution to the study of the plant diversity in communities with Quercus alnifolia in Cyprus","volume":"32","author":"Constantinou","year":"2022","journal-title":"Flora Mediterr."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Markou, M., Moraiti, C.A., Stylianou, A., and Papadavid, G. (2020). Addressing Climate Change Impacts on Agriculture: Adaptation Measures for Six Crops in Cyprus. Atmosphere, 11.","DOI":"10.3390\/atmos11050483"},{"key":"ref_44","unstructured":"Google Earth 9.194 (2024, May 21). Cyprus GE Satellite Images. Available online: https:\/\/earth.google.com."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Frazier, A.E., and Hemingway, B.L. (2021). A Technical Review of Planet Smallsat Data: Practical Considerations for Processing and Using PlanetScope Imagery. Remote Sens., 13.","DOI":"10.3390\/rs13193930"},{"key":"ref_46","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 (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_47","unstructured":"Srivastava, R.K., Greff, K., and Schmidhuber, J. (2015). Highway Networks. arXiv."},{"key":"ref_48","first-page":"3239","article-title":"Learning to Compose Domain-Specific Transformations for Data Augmentation","volume":"30","author":"Ratner","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_49","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_50","doi-asserted-by":"crossref","first-page":"113576","DOI":"10.1016\/j.rse.2023.113576","article-title":"Mapping tree species diversity in temperate montane forests using Sentinel-1 and Sentinel-2 imagery and topography data","volume":"292","author":"Liu","year":"2023","journal-title":"Remote Sens. Environ."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/23\/4611\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:50:39Z","timestamp":1760115039000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/23\/4611"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,9]]},"references-count":50,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["rs16234611"],"URL":"https:\/\/doi.org\/10.3390\/rs16234611","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,9]]}}}