Geography ETDs

Publication Date

Fall 11-10-2025

Abstract

Crowdsourced biodiversity data provide an accessible foundation for large-scale ecological monitoring, but class imbalance limits automated species identification, particularly for rare taxa. This research explores the use of synthetic training data generated from 3D models of carabid beetle museum specimens to improve detection and classification performance for underrepresented species in crowdsourced datasets. High-resolution 3D models were created to simulate variation in lighting, orientation, and background. These synthetic images were incorporated into convolutional neural network training datasets at varying synthetic-to-real ratios to assess their impact on classification accuracy. Models were evaluated using controlled pitfall-trap imagery to examine the influence of scene and specimen variability. Results show that synthetic augmentation can improve classification performance for rare taxa, though gains are not consistent across all classes. This work offers a scalable approach to enhancing automated biodiversity monitoring and highlights the potential of museum collections to support timely conservation and ecological decision-making.

Degree Name

Geography

Department Name

Geography

Level of Degree

Doctoral

First Committee Member (Chair)

Dr. Christopher Lippitt

Second Committee Member

Dr. Thomas Turner

Third Committee Member

Dr. Liping Yang

Fourth Committee Member

Dr. Michaela Buenemann

Document Type

Dissertation

Language

English

Keywords

Photogrammetry, Computer Vision, Machine Learning, Beetles

Download

Share

COinS