Author(s): Quynh-Nga Trinh
Linked Author(s):
Keywords: Cyanobacteria detection AI-driven monitoring YOLO V11 algal blooms water quality management object detection harmful algal blooms environmental monitoring
Abstract: The proliferation of harmful algal blooms, predominantly caused by cyanobacteria, poses significant threats to aquatic ecosystems and public health. Effective and accurate identification of cyanobacteria on water surfaces is essential for proactive water quality management. In this study, we present an AI-driven framework leveraging deep learning algorithms for the detection of cyanobacteria, emphasizing real-time surface-level algal identification without delving into cell-level enumeration. By integrating object detection techniques with advanced performance metrics, the proposed system enhances the precision and efficiency of monitoring algal blooms in natural water bodies.
Year: 2025