Abstract
Harmful algal blooms, particularly those caused by cyanobacteria (blue-green algae) and green algae, pose an increasing risk to aquatic ecosystems and public health. This risk is intensified by climate change and nutrient pollution. This study presents a methodology for in situ monitoring and assessment of algal contamination in surface waters, combining UV/Vis and fluorescence spectroscopy with a fuzzy pattern classifier for consideration of uncertainties. The system incorporates detailed data pre-processing to minimise measurement uncertainty and uses full-spectrum feature extraction to enhance classification accuracy. To assess the methodology under both controlled and real-world conditions, a mobile submersible probe was tested alongside a laboratory setup. The results demonstrate a high degree of agreement between the two systems, showing particular sensitivity to biological signals, such as the presence of algae. The assessment method successfully identified cyanobacterial and green algal contamination, and its predictions aligned with external observations, such as official warnings and environmental changes. By explicitly accounting for measurement uncertainty and employing a comprehensive spectral analysis approach, the system offers robust and adaptable monitoring capabilities. These findings highlight the potential for scalable, field-deployable solutions for the early detection of harmful algal blooms.