College - Author 1
College of Engineering
Department - Author 1
Computer Engineering Department
College - Author 2
College of Engineering
Department - Author 2
Computer Science Department
Advisor
Andrew Fricker, College of Liberal Arts, Social Sciences Department; Jonathan Ventura, College of Engineering, Civil and Environmental Engineering Department; Ryan Walter, Bailey College of Science and Mathematics, Physics Department
Date
10-2025
Abstract/Summary
Previous work from our group utilized drone-based images and a novel machine learning classification model to quickly and accurately quantify spatial variability in eelgrass in Morro Bay. In this SURP project we aim to develop and evaluate quantifiable estimates of the model’s prediction uncertainty. Our model produces a binary labeling indicating the presence or absence of eelgrass at each pixel. However, internally the model produces a probabilistic output indicating the likelihood of detection at each pixel that we propose to use to produce uncertainty estimates and a confidence interval for the cumulative extent of eelgrass detected. This would allow for more credible communication of measurements when measuring the area of eelgrass across a study area or analyzing the change in the amount of eelgrass over time. To evaluate and calibrate our uncertainty predictions, we will compare them to the empirical uncertainty observed in our ground truth annotations.
October 1, 2025.
Included in
URL: https://digitalcommons.calpoly.edu/ceng_surp/152