• Varshini
• Sudarshan K
• Sanvi S Shetty
• Swathi
• Harshini P K

Coral reefs cover less than 0.2% of the ocean floor, but don’t let their small size fool you—they’re some of the most important ecosystems in the sea. Not only do they support over a third of all marine life, but they also provide huge ecological and economic benefits to us humans. Unfortunately, pollution, climate change, and unsustainable human activity are posing an increasing threat to these ecosystems. Conventional techniques for assessing the health of reefs are frequently laborious, necessitate professional advice, and are difficult to scale. Recent advances in remote sensing and AI are transforming how we monitor coral reefs. By leveraging deep learning models like CNNs, transfer learning (VGG19, DenseNet-169), object detection (YOLOv8), and SVMs, researchers can now classify reef images, segment underwater scenes, and analyze satellite data with impressive accuracy. These tools are proving especially powerful for tracking coral bleaching, assessing reef health, and detecting long-term changes in reef coverage—helping us protect these vital ecosystems more effectively than ever before. Even in remote marine environments, real-time, affordable reef monitoring is made possible by the combination of image enhancement methods, geolocation information, and optimisation for low-power edge devices like the Jetson Nano. There are still obstacles to be addressed, such as standardising the metrics used to measure coral reef health (such as the Coral Reef Health Index), increasing the variety of training datasets, and taking into account ecological elements that are invisible in photos, like fish biomass. In order to make coral reef conservation initiatives more scalable and sustainable, this review addresses the present advantages and disadvantages of AI-driven approaches to coral reef monitoring and suggests future directions, such as hybrid modelling, combining various data sources, and creating lightweight solutions.

Coral Reef Monitoring, Deep Learning, (CNNs) Convolutional Neural Networks, Transfer Learning, VGG19, DenseNet-169, YOLOv8, Support Vector Machines (SVMs), Remote Sensing, Semantic Segmentation, Detection of Coral Bleaching, Image Enhancement, Edge Computing, Jetson Nano, Coral Reef Health Index (CRHI), Protection of the Environment, Underwater Image Analysis, Marine Biodiversity, and Multimodal Data Fusion.

"A REVIEW ON DIAGNOSTIC AND SURVEILLANCE TECHNIQUES FOR CORAL ECOSYSTEM HEALTH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.113-117, July-2025, Available :http://www.jetir.org/papers/JETIRGX06021.pdf

"A REVIEW ON DIAGNOSTIC AND SURVEILLANCE TECHNIQUES FOR CORAL ECOSYSTEM HEALTH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp113-117, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06021.pdf