Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar
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 r...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/9/1759 |
| _version_ | 1797535592202895360 |
|---|---|
| author | Leila Character Agustin Ortiz JR Tim Beach Sheryl Luzzadder-Beach |
| author_facet | Leila Character Agustin Ortiz JR Tim Beach Sheryl Luzzadder-Beach |
| author_sort | Leila Character |
| collection | DOAJ |
| description | 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—ANOVAs and box and whisker plots—indicate 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. |
| first_indexed | 2024-03-10T11:46:38Z |
| format | Article |
| id | doaj.art-d95e383eb64b45e291c273e4ff985971 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T11:46:38Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d95e383eb64b45e291c273e4ff9859712023-11-21T18:03:14ZengMDPI AGRemote Sensing2072-42922021-04-01139175910.3390/rs13091759Archaeologic Machine Learning for Shipwreck Detection Using Lidar and SonarLeila Character0Agustin Ortiz JR1Tim Beach2Sheryl Luzzadder-Beach3Department of Geography and the Environment, University of Texas at Austin, 305 E. 23rd St., A3100, Austin, TX 78712, USAUnderwater Archaeology Branch, Naval History and Heritage Command (NHHC), 805 Kidder Breese St. SE, Washington, DC 20374, USADepartment of Geography and the Environment, University of Texas at Austin, 305 E. 23rd St., A3100, Austin, TX 78712, USADepartment of Geography and the Environment, University of Texas at Austin, 305 E. 23rd St., A3100, Austin, TX 78712, USAThe 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—ANOVAs and box and whisker plots—indicate 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.https://www.mdpi.com/2072-4292/13/9/1759deep learningmachine learninglidarsonarshipwrecksarchaeology |
| spellingShingle | Leila Character Agustin Ortiz JR Tim Beach Sheryl Luzzadder-Beach Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar Remote Sensing deep learning machine learning lidar sonar shipwrecks archaeology |
| title | Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar |
| title_full | Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar |
| title_fullStr | Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar |
| title_full_unstemmed | Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar |
| title_short | Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar |
| title_sort | archaeologic machine learning for shipwreck detection using lidar and sonar |
| topic | deep learning machine learning lidar sonar shipwrecks archaeology |
| url | https://www.mdpi.com/2072-4292/13/9/1759 |
| work_keys_str_mv | AT leilacharacter archaeologicmachinelearningforshipwreckdetectionusinglidarandsonar AT agustinortizjr archaeologicmachinelearningforshipwreckdetectionusinglidarandsonar AT timbeach archaeologicmachinelearningforshipwreckdetectionusinglidarandsonar AT sherylluzzadderbeach archaeologicmachinelearningforshipwreckdetectionusinglidarandsonar |