Date of Award

8-31-2026

Document Type

Open Access Thesis

Degree Name

Master of Science (MS)

Department

Biology

First Advisor

Stephanie Wood, Lecturer Chairperson of Committee

Second Advisor

Scott Kraus, Research Faculty Member

Third Advisor

Jarrett Byrnes, Associate Professor Member

Abstract

Real-time detection of large whales at sea is critical for mitigating serious injury and mortality from ship strikes and other human activities such as seismic surveys, especially for endangered species such as the critically endangered North Atlantic Right Whale (Eubalaena glacialis). Traditional marine mammal observers are limited by environmental conditions and human factors, necessitating a robust, 24-hour solution. This study investigates the efficacy of a novel onboard detection tool infrared (IR) technology to detect whale blows and body parts. While IR is a promising advancement, its performance under varying sea conditions (e.g., fog, humidity) and its ability to distinguish all species and behaviors remain unproven. IR data were collected from 2014–2015 and 2021–2023 from five whale species displaying a variety of behaviors in variable sea conditions. Data included observer visual records, behavioral sequencing, and exact distance and surface times recorded by suction-cup tagged whales with Fastloc-GPS. Contrast luminance values were defined in this study to calculate an IR “grade”—the ease for detectability—to assess which species and behaviors are most likely to be detected by convolutional neural network (CNN) algorithms used in autodetection software. Detection distance functions and Spearman Rank Correlation models were used to assess environmental variable relationships, and Ordinary Least Square Multivariable Linear Regression models were used to filter environmental confounders to determine species and behavioral effects on IR detectability. Results indicate that species and behaviors yield different IR grades. These findings are vital for training automatic detection algorithms, thereby enhancing real-time mitigation efforts for critically endangered species.

Comments

Free and open access to this work is made available to the UMass Boston community by ScholarWorks at UMass Boston. Those not on campus and those without a UMass Boston campus username and password may gain access to this work through Interlibrary Loan. If you have a UMass Boston campus username and password and would like to download this work from off-campus, click on the “Off-Campus Users” button.

Download

Additional Files

LHowes Infrared Detectability of Whale Species and Behaviors to Enhance Automatic Detection for Real-Time Vessel Strike Avoidance.pdf (1926 kB)

  Contact Author

Share

COinS