Back to search

Cal Poly

Developing a Humpback Whale Vocalization Detector Using Machine Learning Models

Abstract

dc:description.abstract

Humpback whale songs are notoriously complex. Identification of humpback whale song units requires bioacousticians to tediously listen, analyze, and annotate collected sound data. Even sparse data requires listening to the entirety of the collected acoustic data. In this study, three hours of audio containing over one-thousand humpback whale song units was collected in Monterey Bay, California. Prior studies have seen success using convolutional neural networks by performing image classification on hundreds of hours worth of spectrograms. Our study uses traditional machine learning models, as they are less computationally demanding, and require less data. We use time splitting and Mel-frequency cepstrum to transform complex, continuous sound data into a set of trainable, numerical coefficients. We capture the complexity of humpback songs by creating observations based on the evolution of a song, called context windows. We apply two non-parametric machine learning models, k-nearest neighbors, and random forests, to our created observations. Results are tested in two manners, per-context-window and per-vocalization. Context windows with more time steps avoid overfitting, produces better per-window metrics, and is more successful at identifying individual calls in a high presence dataset. Model selection, parameter tuning, and context window adjusting yield observation-based F1 scores up to 0.824, and identify over 98% of vocalizations.

Degree

thesis:*
Name thesis:degree_name
MS in Statistics
Discipline thesis:degree_discipline
Statistics

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Kantorowski, Lucas
Contributors dc:contributor
  • Kelly Bodwin
  • Statistics
  • College of Science and Mathematics

Subjects

dc:subject × 11

Identifiers

dc:identifier.*
Repository record dc:identifier
https://digitalcommons.calpoly.edu/theses/3311

Chain of custody

source
Harvested from
Cal Poly
Base URL
digitalcommons.calpoly.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Kantorowski, Lucas. Developing a Humpback Whale Vocalization Detector Using Machine Learning Models. https://digitalcommons.calpoly.edu/theses/3311