Data from: Avian Sentinels Neural Nest: AI-Powered Bird Monitoring System for Real-Time Detection and Species Identification

Traditional bird deterrent methods, such as scarecrows, loud noise emitters, and netting, can become less effective over time due to bird habituation. This study presents an AI-driven avian monitoring system, integrating advanced deep learning models and real-time environmental sensing as a baseline for potential adaptive deterrent mechanisms to manage bird populations in aquaculture environments. The proposed system leverages high-resolution imaging, motion tracking, and environmental sensors to identify species and analyze behavioral patterns. The AI-powered classification is driven by the developed Avian Eye Net, a specialized neural network optimized for avian species detection and classification, ensuring high precision in real-time monitoring. The AI framework utilizes a multi-stage image processing pipeline, starting with region of interest (ROI) extraction using adaptive image segmentation. Image metadata is then processed through AI-based feature extraction and context-aware metadata parsing, which fuses structured data with neural network outputs. The final dataset is compiled into structured formats, exporting key parameters—including image filename, date, time, location, detected species, and population count—to a ready to analyze data file for further analysis. This structured approach enhances system efficiency, providing real-time, high-fidelity bird population monitoring. Experimental results demonstrate a classification accuracy of 97.2%, with a precision rate of 95.8% and a recall rate of 96.4% for avian species identification for three important species associated with aquaculture farms. In the future, the system’s integration with Internet of Things (IoT) devices may enable the deployment of non-invasive deterrent measures—such as LED lighting, ultrasonic sound waves, and airflow manipulation—to mitigate avian interference with aquaculture operations. This IoT with AI-powered approach enhances sustainable aquaculture management by ensuring minimal disruption to avian species while optimizing fish farm productivity.

The dataset contains a subset of images used to build the species identification and quantification models, highlighting the main predatory birds in the area: great blue heron, egret, and Canada goose. Also included in classification are humans. Meta-data annotation from camera trap images is also included in the code and extraction from the images.