Back to search

University of British Columbia

Predictive modelling of beaver habitats using machine learning

Abstract

dc:description

Beavers inhabit and alter freshwater ecosystems through the construction of beaver dams, lodges, ponds and canals. Beaver-controlled stream systems exhibit increased sediment and water storage, creating pools and important habitats for fish and invertebrates. However, determining historic and or suitable beaver habitats poses a challenge due to factors such as trapping, land use disturbances, and climate change. As interest in restoring riverine and stream ecosystems grows, the reintroduction of beavers and construction of beaver dam analogs—man-made structures designed to mimic natural beaver dams—are increasingly being used to rehabilitate impaired riverine habitats. A mapping approach that identifies suitable topographic and environmental conditions associated with successful beaver habitats would therefore be a useful guide for future freshwater ecosystem restoration efforts. In this study, beaver dam locations were identified and used to train a random forest machine learning model to assess stream, wetland and river beaver habitat suitability. The model uses provincially available topographic, biological, and hydrologic variables to test their importance for predicting the presence or absence of beaver dams. This procedure produced a measure of habitat suitability with an accuracy score of 97%. The research discussed here can contribute to informed decision-making regarding the reintroduction of beavers and the restoration of stream systems, promoting ecological balance and enhancing the natural state of riverine ecosystems.

Degree

thesis:*
Name thesis:degree_name
Master of Science - MSc
Level thesis:degree_level
master's
Discipline thesis:degree_discipline
Geography
Grantor dc:publisher
University of British Columbia
Year dc:date
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Matechuk, Landen
Contributors dc:contributor
  • Hassan, Marwan A.

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/88940

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Matechuk, Landen. Predictive modelling of beaver habitats using machine learning. master's thesis, University of British Columbia, 2024. http://hdl.handle.net/2429/88940