Integrating Machine Learning with GIS Tools for Automated Shipwreck Detection from Sonar Imagery

Summary

This is an abstract from the session entitled "Exploration-Forward Archaeology Through Community-Driven Research", at the 2024 annual meeting of the Society for Historical Archaeology.

Recent advances in sensor technology and marine robotic platforms have enabled efficient data collection over large areas across oceans, lakes, and coastal regions. These efforts have resulted in massive amounts of data that contain rich information relevant to ocean exploration. However, processing these large datasets is costly and time consuming. In this presentation, we will describe recent efforts to leverage machine learning to automate processing of sonar imagery for the task of automated shipwreck detection. We will demonstrate tools to integrate machine learning output into geographic information system (GIS) software for further evaluation and visualization. Lastly, we will discuss challenges and opportunities for future work to enable accessible software tools for machine learning for ocean exploration.

This Resource is Part of the Following Collections

• Society for Historical Archaeology 2024   •
• Exploration-Forward Archaeology Through Community-Driven Research

Keywords

Individual & Institutional Roles

Contact(s): Nicole Haddow