• Kosaraju Chaitanya
• Meghana Reddy Boddapati
• Geetha Chiranji
• Navya Sri Koppuravuri
• Abhinaya Induri

Harmful algal blooms (HABs) threaten water quality, human health, and marine ecosystems worldwide, with traditional detection methods being labour-intensive and time-consuming. Deep learning models, particularly ResNet, have shown significant potential in automating and enhancing the efficiency of HAB detection. Research utilizing ResNet-50 and ResNet-101 for classifying harmful algae species from microscopic and satellite images has demonstrated superior performance, achieving higher precision than conventional models. ResNet's effectiveness in early detection is crucial for monitoring algae bloom dynamics and spatial distribution, contributing to better environmental management. Additionally, an Edge-based Segmentation with Significant Feature Set (EbS-SFS) approach further improves detection accuracy and reduces false predictions, advancing deep learning's role in mitigating the impact of HABs on water resources and ecosystem health.

Harmful Algal blooms,ResNet,Convolution neural networks,Edge based Segmentation, environment monitoring.

"EDGE BASED IMAGE SEGMENTATION FOR HARMFUL ALGAL BLOOMS DETECTION USING RESNET", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 10, page no.252-260, October-2024, Available :http://www.jetir.org/papers/JETIRGN06029.pdf

"EDGE BASED IMAGE SEGMENTATION FOR HARMFUL ALGAL BLOOMS DETECTION USING RESNET", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 10, page no. pp252-260, October-2024, Available at : http://www.jetir.org/papers/JETIRGN06029.pdf