Inverte-Quest: Empowering Field Research Through Mobile Photo Identification
Document Type
Conference Proceeding
Publication Date
4-2025
Abstract
Aquatic invertebrates serve as critical bioindicators of freshwater ecosystem health, yet their accurate field identification remains a significant challenge for researchers and students. We are pleased to introduce Inverte-Quest, a mobile application designed to facilitate the identification and recording of invertebrates through in-situ photo identification. This application utilizes advanced deep neural networks, incorporating SAM AI for image masking alongside ResNet PyTorch for species classification. Our database features 13 commonly encountered freshwater invertebrate species, including mayflies (Baetidae, Caenidae), caddisflies (Cheumatopsyche, Hydropsyche), and beetles (Berosus, Elmidae). Images are securely stored in Pinata cloud storage and processed using various parameters, such as wingspan, tail length, and eye characteristics. Through the integration of mobile technology and machine learning, Inverte-Quest provides an accessible platform for aquatic invertebrate identification, supporting both research efficiency and educational initiatives in freshwater ecosystem monitoring.
Recommended Citation
Kahlon, Jaspal Singh and Lozano, Mariana, "Inverte-Quest: Empowering Field Research Through Mobile Photo Identification" (2025). Student Research Symposium 2025. 56.
https://digitalcommons.tamusa.edu/srs_2025/56
Comments
Poster Session 2
5:30-7:00 p.m.
BLH Lobby