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.

Share

COinS
 

URL: https://digitalcommons.calpoly.edu/ceng_surp/152

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.