{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T22:16:02Z","timestamp":1776636962421,"version":"3.51.2"},"reference-count":53,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2023,4,23]],"date-time":"2023-04-23T00:00:00Z","timestamp":1682208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"ARC LIEF","award":["LE200100083"],"award-info":[{"award-number":["LE200100083"]}]},{"name":"Holsworth Wildlife Research Endowment and the Ecological Society of Australia","award":["LE200100083"],"award-info":[{"award-number":["LE200100083"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Coral reefs and their associated marine communities are increasingly threatened by anthropogenic climate change. A key step in the management of climate threats is an efficient and accurate end-to-end system of coral monitoring that can be generally applied to shallow water reefs. Here, we used RGB drone-based imagery and a deep learning algorithm to develop a system of classifying bleached and unbleached corals. Imagery was collected five times across one year, between November 2018 and November 2019, to assess coral bleaching and potential recovery around Lord Howe Island, Australia, using object-based image analysis. This training mask was used to develop a large training dataset, and an mRES-uNet architecture was chosen for automated segmentation. Unbleached coral classifications achieved a precision of 0.96, a recall of 0.92, and a Jaccard index of 0.89, while bleached corals achieved 0.28 precision, 0.58 recall, and a 0.23 Jaccard index score. Subsequently, methods were further refined by creating bleached coral objects (&gt;16 pixels total) using the neural network classifications of bleached coral pixels, to minimize pixel error and count bleached coral colonies. This method achieved a prediction precision of 0.76 in imagery regions with &gt;2000 bleached corals present, and 0.58 when run on an entire orthomosaic image. Bleached corals accounted for the largest percentage of the study area in September 2019 (6.98%), and were also significantly present in March (2.21%). Unbleached corals were the least dominant in March (28.24%), but generally accounted for ~50% of imagery across other months. Overall, we demonstrate that drone-based RGB imagery, combined with artificial intelligence, is an effective method of coral reef monitoring, providing accurate and high-resolution information on shallow reef environments in a cost-effective manner.<\/jats:p>","DOI":"10.3390\/rs15092238","type":"journal-article","created":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T02:06:11Z","timestamp":1682301971000},"page":"2238","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Combining Drones and Deep Learning to Automate Coral Reef Assessment with RGB Imagery"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6538-7862","authenticated-orcid":false,"given":"Anna Barbara","family":"Giles","sequence":"first","affiliation":[{"name":"National Marine Science Centre, Faculty of Science and Engineering, Southern Cross University, 2 Bay Drive, Coffs Harbour, NSW 2450, Australia"}]},{"given":"Keven","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Physics, The University of Melbourne, Parkville, VIC 3010, Australia"}]},{"given":"James Edward","family":"Davies","sequence":"additional","affiliation":[{"name":"School of Physics, The University of Melbourne, Parkville, VIC 3010, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3311-2730","authenticated-orcid":false,"given":"David","family":"Abrego","sequence":"additional","affiliation":[{"name":"National Marine Science Centre, Faculty of Science and Engineering, Southern Cross University, 2 Bay Drive, Coffs Harbour, NSW 2450, Australia"}]},{"given":"Brendan","family":"Kelaher","sequence":"additional","affiliation":[{"name":"National Marine Science Centre, Faculty of Science and Engineering, Southern Cross University, 2 Bay Drive, Coffs Harbour, NSW 2450, Australia"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1890\/120150","article-title":"Lightweight unmanned aerial vehicles will revolutionize spatial ecology","volume":"11","author":"Anderson","year":"2013","journal-title":"Front. Ecol. Environ."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1038\/nature21707","article-title":"Global warming and recurrent mass bleaching of corals","volume":"543","author":"Hughes","year":"2017","journal-title":"Nature"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1038\/s41586-018-0359-9","article-title":"Ecosystem restructuring along the Great Barrier Reef following mass coral bleaching","volume":"560","author":"Brown","year":"2018","journal-title":"Nature"},{"key":"ref_4","unstructured":"Cantin, N.E., and Spalding, M. (2018). Coral Bleaching Ecological Studies, Springer."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1890\/110266","article-title":"CoralWatch: Education, monitoring, and sustainability through citizen science","volume":"10","author":"Marshall","year":"2012","journal-title":"Front. Ecol. Environ."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.marpolbul.2003.10.031","article-title":"Remote sensing of coral reefs and their physical environment","volume":"48","author":"Mumby","year":"2004","journal-title":"Mar. Pollut. Bull."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Hedley, J.D., Roelfsema, C.M., Chollett, I., Harborne, A.R., Heron, S.F., Weeks, S., Skirving, W.J., Strong, A.E., Eakin, C.M., and Christensen, T.R.L. (2016). Remote Sensing of Coral Reefs for Monitoring and Management: A Review. Remote Sens., 8.","DOI":"10.3390\/rs8020118"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.1016\/j.marpolbul.2010.07.033","article-title":"The next step in shallow coral reef monitoring: Combining remote sensing and in situ approaches","volume":"60","author":"Phinn","year":"2010","journal-title":"Mar. Pollut. Bull."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.rse.2003.12.005","article-title":"Detection limits of coral reef bleaching by satellite remote sensing: Simulation and data analysis","volume":"90","author":"Yamano","year":"2004","journal-title":"Remote Sens. Environ."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1071\/MF17380","article-title":"Principles and practice of acquiring drone-based image data in marine environments","volume":"70","author":"Joyce","year":"2019","journal-title":"Mar. Freshw. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1177\/194008291200500202","article-title":"Dawn of Drone Ecology: Low-Cost Autonomous Aerial Vehicles for Conservation","volume":"5","author":"Koh","year":"2012","journal-title":"Trop. Conserv. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/s11852-008-0011-1","article-title":"Development of rapid, cost effective coral survey techniques: Tools for management and conservation planning","volume":"11","author":"Alquezar","year":"2007","journal-title":"J. Coast. Conserv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Parsons, M., Bratanov, D., Gaston, K.J., and Gonzalez, F. (2018). UAVs, Hyperspectral Remote Sensing, and Machine Learning Revolutionizing Reef Monitoring. Sensors, 18.","DOI":"10.3390\/s18072026"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"30","DOI":"10.3390\/oceans3010003","article-title":"A Review of Current and New Optical Techniques for Coral Monitoring","volume":"3","author":"Teague","year":"2022","journal-title":"Oceans"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Fallati, L., Saponari, L., Savini, A., Marchese, F., Corselli, C., and Galli, P. (2020). Multi-Temporal UAV Data and Object-Based Image Analysis (OBIA) for Estimation of Substrate Changes in a Post-Bleaching Scenario on a Maldivian Reef. Remote Sens., 12.","DOI":"10.3390\/rs12132093"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1007\/s00338-018-1662-5","article-title":"Assessing the spatial distribution of coral bleaching using small unmanned aerial systems","volume":"37","author":"Levy","year":"2018","journal-title":"Coral Reefs"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Nababan, B., Mastu, L.O.K., Idris, N.H., and Panjaitan, J.P. (2021). Shallow-Water Benthic Habitat Mapping Using Drone with Object Based Image Analyses. Remote Sens., 13.","DOI":"10.3390\/rs13214452"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"5676","DOI":"10.1080\/01431161.2018.1500072","article-title":"Very high resolution mapping of coral reef state using airborne bathymetric LiDAR surface-intensity and drone imagery","volume":"39","author":"Collin","year":"2018","journal-title":"Int. J. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"603829","DOI":"10.3389\/fmars.2020.603829","article-title":"What Can Artificial Intelligence Offer Coral Reef Managers?","volume":"1049","author":"Hamylton","year":"2020","journal-title":"Front. Mar. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Jamil, S., Rahman, M., and Haider, A. (2021). Bag of Features (BoF) Based Deep Learning Framework for Bleached Corals Detection. Big Data Cogn. Comput., 5.","DOI":"10.3390\/bdcc5040053"},{"key":"ref_21","unstructured":"Dey, V., Zhang, Y., and Zhong, M. (2010, January 5\u20137). A review on image segmentation techniques with remote sensing perspective. Proceedings of the ISPRS TC VII Symposium\u2014100 Years ISPRS, Vienna, Austria."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3329784","article-title":"Understanding Deep Learning Techniques for Image Segmentation","volume":"52","author":"Ghosh","year":"2019","journal-title":"ACM Comput. Surv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1071\/MF9950457","article-title":"The coral communities of Lord Howe Island","volume":"46","author":"Harriott","year":"1995","journal-title":"Mar. Freshw. Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1007\/s00338-010-0610-9","article-title":"Impacts of a population outbreak of the urchin Tripneustes gratilla amongst Lord Howe Island coral communities","volume":"29","author":"Valentine","year":"2010","journal-title":"Coral Reefs"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1007\/s00338-011-0778-7","article-title":"Extensive coral bleaching on the world\u2019s southernmost coral reef at Lord Howe Island, Australia","volume":"30","author":"Harrison","year":"2011","journal-title":"Coral Reefs"},{"key":"ref_26","unstructured":"NSW Government (2021, October 06). Seascapes. Department of Primary Industries 2022, Available online: https:\/\/www.dpi.nsw.gov.au\/fishing\/marine-protected-areas\/marine-parks\/lord-howe-island-marine-park\/life-under-the-sea\/landscapes."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.isprsjprs.2021.09.004","article-title":"A deep learning algorithm to detect and classify sun glint from high-resolution aerial imagery over shallow marine environments","volume":"181","author":"Giles","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.neunet.2019.08.025","article-title":"MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation","volume":"121","author":"Ibtehaz","year":"2020","journal-title":"Neural Netw."},{"key":"ref_29","unstructured":"Zhao, S. (2021, October 06). Demystify Transposed Convolutional Layers. Medium. Available online: https:\/\/medium.com\/analytics-vidhya\/demystify-transposed-convolutional-layers-6f7b61485454."},{"key":"ref_30","unstructured":"Shafkat, I. (2021, October 11). Intuitively Understanding Convolutions for Deep Learning. Towards Data Science. Available online: https:\/\/towardsdatascience.com\/intuitively-understanding-convolutions-for-deep-learning-1f6f42faee1."},{"key":"ref_31","unstructured":"Powell, V. (2021, November 12). Image Kernels. Setosa. Available online: https:\/\/setosa.io\/ev\/image-kernels\/."},{"key":"ref_32","unstructured":"Mishra, D. (2021, October 06). Transposed Convolutions Demystified. Towards Data Science. Available online: https:\/\/towardsdatascience.com\/transposed-convolution-demystified-84ca81b4baba#:~:text=Transposed%20convolution%20is%20also%20known,upsample%20the%20input%20feature%20map."},{"key":"ref_33","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2016). Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv."},{"key":"ref_34","unstructured":"Chollet, F. (2018, December 26). Keras. Available online: https:\/\/keras.io."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s10113-010-0189-2","article-title":"Coral reef ecosystems and anthropogenic climate change","volume":"11","year":"2011","journal-title":"Reg. Environ. Chang."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1038\/nature02691","article-title":"Confronting the coral reef crisis","volume":"429","author":"Bellwood","year":"2004","journal-title":"Nature"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T.M., and Asari, V.K. (2018). Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation. arXiv.","DOI":"10.1109\/NAECON.2018.8556686"},{"key":"ref_38","unstructured":"Iglovikov, V., and Shvets, A. (2018). Ternausnet: U-net with vgg11 encoder pre-trained on imagenet for image segmentation. arXiv."},{"key":"ref_39","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_40","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1177\/0309133317744998","article-title":"Mapping coral reef environments: A review of historical methods, recent advances and future opportunities","volume":"41","author":"Hamylton","year":"2017","journal-title":"Prog. Phys. Geogr."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Congalton, R.G., and Green, K. (2019). Assessing the Accuracy of Remotely Sensed Data: Principles and Practices, CRC Press. Available online: https:\/\/books.google.com.ec\/books?hl=es&lr=&id=yTmDDwAAQBAJ&oi=fnd&pg=PP1&ots=1HaQilihig&sig=hfe0btykmLoM6xWds0y0mqZebIU&redir_esc=y#v=onepage&q&f=false.","DOI":"10.1201\/9780429052729"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Bennett, M.K., Younes, N., and Joyce, K.E. (2020). Automating Drone Image Processing to Map Coral Reef Substrates Using Google Earth Engine. Drones, 4.","DOI":"10.3390\/drones4030050"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Cheng, B., Girshick, R., Doll\u00e1r, P., Berg, A.C., and Kirillov, A. (2021, January 20\u201325). Boundary IoU: Improving object-centric image segmentation evaluation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2021, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01508"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Ammour, N., Alhichri, H., Bazi, Y., Ben Jdira, B., Alajlan, N., and Zuair, M. (2017). Deep Learning Approach for Car Detection in UAV Imagery. Remote Sens., 9.","DOI":"10.3390\/rs9040312"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/j.isprsjprs.2017.06.001","article-title":"A review of supervised object-based land-cover image classification","volume":"130","author":"Ma","year":"2017","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"3386","DOI":"10.1109\/JSTARS.2017.2680324","article-title":"Object-Based Convolutional Neural Network for High-Resolution Imagery Classification","volume":"10","author":"Zhao","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Veeranampalayam, S., Arun, N., Li, J., Scott, S., Psota, E., Jhala, J.A., Luck, J.D., and Shi, Y. (2020). Comparison of Object Detection and Patch-Based Classification Deep Learning Models on Mid- to Late-Season Weed Detection in UAV Imagery. Remote Sens., 12.","DOI":"10.3390\/rs12132136"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1007\/s00338-002-0233-x","article-title":"Choosing the appropriate spatial resolution for monitoring coral bleaching events using remote sensing","volume":"21","author":"Berkelmans","year":"2002","journal-title":"Coral Reefs"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/S0065-2881(08)60224-2","article-title":"Adaptations of Reef Corals to Physical Environmental Stress","volume":"Volume 31","author":"Blaxter","year":"1997","journal-title":"Advances in Marine Biology"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.isprsjprs.2021.01.012","article-title":"A nested drone-satellite approach to monitoring the ecological conditions of wetlands","volume":"174","author":"Bhatnagar","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_51","unstructured":"Majewski, J. (2021, October 11). Why Should You Label Your Own Data in Image Classification Experiments? Towards Data Science. Available online: https:\/\/towardsdatascience.com\/why-should-you-label-your-own-data-in-image-classification-experiments-6b499c68773e."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1109\/TMI.2016.2535302","article-title":"Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?","volume":"35","author":"Tajbakhsh","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Jim\u00e9nez L\u00f3pez, J., and Mulero-P\u00e1zm\u00e1ny, M. (2019). Drones for Conservation in Protected Areas: Present and Future. Drones, 3.","DOI":"10.3390\/drones3010010"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/9\/2238\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:21:44Z","timestamp":1760124104000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/9\/2238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,23]]},"references-count":53,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,5]]}},"alternative-id":["rs15092238"],"URL":"https:\/\/doi.org\/10.3390\/rs15092238","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,23]]}}}