Assessment of Algal Diversity in Kalahandi District of Odisha Through AI-Driven Smart Technology

Freshwater algae are vital indicators of aquatic ecosystem health, reflecting nutrient status, pollution levels, and overall ecological balance. This study investigates the diversity and spatial distribution of algal genera across 25 freshwater bodies in six blocks of Kalahandi District, Odisha. Traditional taxonomic identification was conducted through field sampling and microscopic analysis, resulting in the classification of 35 algal genera spanning both lentic and lotic water habitats. To scale and enhance this biodiversity assessment, we employed machine learning models to classify habitat types, predict the presence of dominant genera such as Navicula and Oscillatoria, and uncover ecological clusters using unsupervised algorithms. Supervised models like Random Forest achieved up to 87% accuracy in habitat prediction, while K-means clustering revealed clear spatial biodiversity groupings. This AI-driven framework offers a robust and replicable tool for freshwater ecosystem monitoring, particularly in under-resourced rural environments.