{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T05:25:36Z","timestamp":1772515536588,"version":"3.50.1"},"reference-count":38,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,4,30]],"date-time":"2021-04-30T00:00:00Z","timestamp":1619740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"2021 Naval Research Enterprise Internship Program (NREIP)","award":["NA"],"award-info":[{"award-number":["NA"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The objective of this project is to create a new implementation of a deep learning model that uses digital elevation data to detect shipwrecks automatically and rapidly over a large geographic area. This work is intended to apply a new methodology to the field of underwater archaeology. Shipwrecks represent a major resource to understand maritime human activity over millennia, but underwater archaeology is expensive, misappropriated, and hazardous. An automated tool to rapidly detect and map shipwrecks can therefore be used to create more accurate maps of natural and archaeological features to aid management objectives, study patterns across the landscape, and find new features. Additionally, more comprehensive and accurate shipwreck maps can help to prioritize site selection and plan excavation. The model is based on open source topo-bathymetric data and shipwreck data for the United States available from NOAA. The model uses transfer learning to compensate for a relatively small sample size and addresses a recurring problem that associated work has had with false positives by training the model both on shipwrecks and background topography. Results of statistical analyses conducted\u2014ANOVAs and box and whisker plots\u2014indicate that there are substantial differences between the morphologic characteristics that define shipwrecks vs. background topography, supporting this approach to addressing false positives. The model uses a YOLOv3 architecture and produced an F1 score of 0.92 and a precision score of 0.90, indicating that the approach taken herein to address false positives was successful.<\/jats:p>","DOI":"10.3390\/rs13091759","type":"journal-article","created":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T21:35:39Z","timestamp":1619904939000},"page":"1759","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8763-6068","authenticated-orcid":false,"given":"Leila","family":"Character","sequence":"first","affiliation":[{"name":"Department of Geography and the Environment, University of Texas at Austin, 305 E. 23rd St., A3100, Austin, TX 78712, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7018-7638","authenticated-orcid":false,"given":"Agustin","family":"Ortiz JR","sequence":"additional","affiliation":[{"name":"Underwater Archaeology Branch, Naval History and Heritage Command (NHHC), 805 Kidder Breese St. SE, Washington, DC 20374, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0097-7973","authenticated-orcid":false,"given":"Tim","family":"Beach","sequence":"additional","affiliation":[{"name":"Department of Geography and the Environment, University of Texas at Austin, 305 E. 23rd St., A3100, Austin, TX 78712, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9184-2427","authenticated-orcid":false,"given":"Sheryl","family":"Luzzadder-Beach","sequence":"additional","affiliation":[{"name":"Department of Geography and the Environment, University of Texas at Austin, 305 E. 23rd St., A3100, Austin, TX 78712, USA"}]}],"member":"1968","published-online":{"date-parts":[[2021,4,30]]},"reference":[{"key":"ref_1","unstructured":"Bowens, A. (2011). Underwater Archaeology: The NAS Guide to Principles and Practice, Blackwell Publishing. [2nd ed.]."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"348","DOI":"10.2307\/277518","article-title":"Underwater archaeology: Its nature and limitations","volume":"25","author":"Goggin","year":"1960","journal-title":"Am. Antiq."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"McCarthy, J.K., Benjamin, J., Winton, T., and van Duivenvoorde, W. (2019). 3D Recoding and Interpretation for Marine Archaeology, Springer.","DOI":"10.1007\/978-3-030-03635-5"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wickham-Jones, C. (2019). Studying Scientific Archaeology: Landscape Beneath the Waves: The Archaeological Investigation of Underwater Landscapes, Oxbow.","DOI":"10.2307\/j.ctvh1dhkp"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"McCarthy, J.K., Benjamin, J., Winton, T., and van Duivenvoorde, W. (2019). Deepwater archaeological survey: An interdisciplinary and complex process. 3D Recording and Interpretation for Maritime Archaeology, Springer.","DOI":"10.1007\/978-3-030-03635-5"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1002\/arp.1730","article-title":"Object-based image analysis: A review of developments and future directions of automated feature detection in archaeology","volume":"26","author":"Davis","year":"2018","journal-title":"Archaeol. Prospect."},{"key":"ref_7","first-page":"e00152","article-title":"Defining what we study: The contribution of machine automation in archaeological research","volume":"18","author":"Davis","year":"2020","journal-title":"Digit. Appl. Archaeol. Cult. Herit."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"111280","DOI":"10.1016\/j.rse.2019.111280","article-title":"Airborne and spaceborne remote sensing for archaeological and cultural heritage applications: A review of the century (1907\u20132017)","volume":"232","author":"Luo","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1111\/aman.13411","article-title":"Confronting the Present: Archaeology in 2019","volume":"122","author":"Rosenzweig","year":"2020","journal-title":"Am. Anthropol."},{"key":"ref_10","first-page":"485","article-title":"Pixel versus object\u2013A comparison of strategies for the semi-automated mapping of archaeological features using airborne laser scanning data","volume":"5","author":"Sevara","year":"2016","journal-title":"J. Archaeol. Sci. Rep."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"104998","DOI":"10.1016\/j.jas.2019.104998","article-title":"Convolutional neural networks for archaeological site detection\u2013Finding \u201cprincely\u201d tombs","volume":"110","author":"Caspari","year":"2019","journal-title":"J. Archaeol. Sci."},{"key":"ref_12","unstructured":"Pasquet, J., Demesticha, S., Skarlatos, D., Merad, D., and Drap, P. (2017, January 23\u201325). Amphora detection based on a gradient weighted error in a convolutional neural network. Proceedings of the IMEKO International Conference on Metrology for Archaeology and Cultural Heritage, Lecce, Italy."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Somrak, M., Dzeroski, S., and Kokalj, Z. (2020). Learning to classify structures in ALS-derived visualizations of ancient Maya settlements with CNN. Remote Sens., 12.","DOI":"10.3390\/rs12142215"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1002\/arp.1731","article-title":"Using deep neural networks on airborne laser scanning data: Results from a case study of semi-automatic mapping of archaeological topography on Arran, Scotland","volume":"26","author":"Trier","year":"2019","journal-title":"Archaeol. Prospect."},{"key":"ref_15","first-page":"31","article-title":"Learning to Look at LiDAR: The Use of R-CNN in the Automated Detection of Archaeological Objects in LiDAR Data from the Netherlands","volume":"2","author":"Wouter","year":"2019","journal-title":"J. Comput. Appl. Archaeol."},{"key":"ref_16","unstructured":"Chollet, F. (2018). Deep Learning with Python, Manning Publications Co."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/978-981-15-9460-1_16","article-title":"Machine learning techniques for AUV side scan sonar data feature extraction as applied to intelligent search for underwater archaeology sites","volume":"16","author":"Nayak","year":"2021","journal-title":"Field Serv. Robot."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhu, B., Wang, X., Chu, Z., Yang, Y., and Shi, J. (2019). Active learning for recognition of shipwreck target in side-scan sonar image. Remote Sens., 11.","DOI":"10.3390\/rs11030243"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"283","DOI":"10.3389\/fmars.2019.00283","article-title":"Seafloor mapping\u2014The challenge of a truly global bathymetry","volume":"6","author":"Snaith","year":"2019","journal-title":"Front. Mar. Sci."},{"key":"ref_20","unstructured":"(2021, March 30). NOAA Dataviewer, Available online: https:\/\/coast.noaa.gov\/dataviewer\/#\/lidar\/search\/."},{"key":"ref_21","unstructured":"(2021, March 30). NOAA Wrecks and Obstructions Database, Available online: https:\/\/nauticalcharts.noaa.gov\/data\/wrecks-and-obstructions.html."},{"key":"ref_22","unstructured":"G\u00e9ron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, O\u2019Reilly Media, Inc."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1111\/j.1095-9270.2010.00271.x","article-title":"Using multibeam echo-sounder data to identify shipwreck sites: Archaeological assessment of the Joint Irish Bathymetric Survey data","volume":"40","author":"Plets","year":"2011","journal-title":"Int. J. Naut. Archaeol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Shih, P.T.-Y., Chen, Y.-H., and Chen, J.C. (2013). Historic shipwreck study in Dongsha Atoll with bathymetric LiDAR. Archaeol. Prospect., 21.","DOI":"10.1002\/arp.1466"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ye, X., Li, C., Zhang, S., Yang, P., and Li, X. (2018, January 22\u201325). Research on side-scan sonar image target classification method based on transfer learning. Proceedings of the OCEANS MTS\/IEEE, Charleston, SC, USA.","DOI":"10.1109\/OCEANS.2018.8604691"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Xu, L., Wang, X., and Wang, X. (2019, January 24\u201327). Shipwrecks detection based on deep generation network and transfer learning with small amount of sonar images. Proceedings of the IEEE 8th Data Driven Control and Learning Systems Conference, Dali, China.","DOI":"10.1109\/DDCLS.2019.8909011"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Davis, D.S., Buffa, D.C., and Wrobleski, A.C. (2020). Assessing the utility of open-access bathymetric data for shipwreck detection in the United States. Heritage, 3.","DOI":"10.3390\/heritage3020022"},{"key":"ref_28","unstructured":"GitHub (2021, March 30). Repository for Microsoft\u2019s Visual Object Tagging Tool. Available online: https:\/\/github.com\/microsoft\/VoTT."},{"key":"ref_29","unstructured":"Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv."},{"key":"ref_30","unstructured":"GitHub (2021, March 30). Repository for YOLOv3, Qqwweee. Available online: https:\/\/github.com\/qqwweee\/keras-yolo3."},{"key":"ref_31","unstructured":"GitHub (2021, March 30). Repository for YOLOv3, Anton Mu. Available online: https:\/\/github.com\/AntonMu\/TrainYourOwnYOLO."},{"key":"ref_32","unstructured":"(2021, March 30). ImageNet1000. Available online: http:\/\/image-net.org\/challenges\/LSVRC\/2015\/index."},{"key":"ref_33","unstructured":"Brownlee, J. (2021, March 30). How to use ROC Curves and Precision-Recall Curves for Classification in Python. Available online: https:\/\/machinelearningmastery.com\/roc-curves-and-precision-recall-curves-for-classification-in-python\/."},{"key":"ref_34","unstructured":"(2021, March 30). Accuracy Trap! Pay Attention to Recall, Precision, F-score, AUC. Available online: https:\/\/medium.com\/datadriveninvestor\/accuracy-trap-pay-attention-to-recall-precision-f-score-auc-d02f28d3299c."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Hosmer, D.W., Lemeshow, S., and Sturdivant, R.X. (2013). Applied Logistic Regression, John Wiley and Sons.","DOI":"10.1002\/9781118548387"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1097\/JTO.0b013e3181ec173d","article-title":"Receiver operating characteristic curve in diagnostic test assessment","volume":"5","author":"Mandrekar","year":"2010","journal-title":"J. Thorac. Oncol."},{"key":"ref_37","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster R-CNN: Toward Real-Time Object Detection with Region Proposal Networks. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3169","DOI":"10.1073\/pnas.1519566113","article-title":"Shipwreck Rates Reveal Caribbean Tropical Cyclone Response to Past Radiative Forcing","volume":"113","author":"Trouet","year":"2016","journal-title":"Proc. Natl. Acad. Sci. USA"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/9\/1759\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:56:20Z","timestamp":1760162180000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/9\/1759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,30]]},"references-count":38,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["rs13091759"],"URL":"https:\/\/doi.org\/10.3390\/rs13091759","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,30]]}}}