Author

Ning Li

Date of Award

December 2024

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Earth System Science & Policy

First Advisor

Haochi Zheng

Abstract

Honey bees are essential for honey production and pollination services, but their colonies have been declining despite increasing demand. This decline may be due to various factors, including habitat loss, altered land use, climate shifts, and pesticide exposure. In order to assess the quantity and quality of habitats for honey bees and determine their availability and suitability for supporting bee colonies, it is crucial to identify the spatial location of registered apiary sites being used. However, such data is not available, which makes it a challenge for researchers in the field to further advance honey bee-related investigations. In my study, I developed a fast and effective way to detect apiaries with remote images using deep learning networks, such as You Only Look Once (YOLO) and Faster Region-based Convolutional Neural Network (Faster R-CNN). The approach fully utilized the publicly available, web-enabled imagery for detecting apiary sites across a large region. The result of my study can expand data capacity and provide valuable information to resource managers for better managing honey bees and other pollinator habitats.

Share

COinS