Improved ground-truthing and benthic habitat characterization with machine learning models and 3D photogrammetry

By: , and 

Links

Abstract

Benthic mapping relies on a range of methods to ground truth remotely sensed data to map physical and biotic features. Traditional methods are labor-intensive and time-consuming with limited scalability. Autonomous underwater vehicles (AUVs) and remote operated vehicles (ROVs) can collect high volumes of quality data but require automated processing routines and pose other logistic challenges. This paper explores the automated use of multiple machine learning (ML) models to detect and delineate benthic habitat components from structure-from-motion (SfM) orthomosaics. Overlapping AUV photos were processed into high-resolution, seamless orthomosaics for a portion of the Lake Michigan lakebed. ML models were trained to delineate rocks and live mussels and subsequently applied to the SfM orthomosaics. Results demonstrate that a robust pipeline with SfM and ML models is an effective approach to efficiently, accurately, and comprehensively map benthic habitats.

Suggested Citation

Wernette, P., Esselman, P., Geglio, A., Galloway, A., Moradi, S., and Pierce, J., 2025, Improved ground-truthing and benthic habitat characterization with machine learning models and 3D photogrammetry, Oceans 2025, v. 2025, Chicago, IL, September 29-October 2, 2025, 11245182, 5 p., https://doi.org/10.23919/OCEANS59106.2025.11245182.

Publication type Conference Paper
Publication Subtype Conference Paper
Title Improved ground-truthing and benthic habitat characterization with machine learning models and 3D photogrammetry
DOI 10.23919/OCEANS59106.2025.11245182
Volume 2025
Publication Date November 25, 2025
Year Published 2025
Language English
Publisher IEEE
Contributing office(s) Great Lakes Science Center
Description 11245182, 5 p.
Conference Title Oceans 2025
Conference Location Chicago, IL
Conference Date September 29-October 2, 2025
Country United States
Other Geospatial Lake Michigan
Additional publication details