AI-BASED IMAGE RECOGNITION FRAMEWORK FOR EFFICIENT CORAL BLEACHING ASSESSMENT

Abstract

Coral reefs are vital ecosystems that support biodiversity and coastal economies but are increasingly threatened by climate change, overfishing, and pollution. Traditional coral health assessments, while effective, are time-consuming and labor-intensive, limiting their scalability. This study introduces an AI-powered image recognition framework utilizing Convolutional Neural Networks (CNNs) and transfer learning to automate coral bleaching detection with improved accuracy and efficiency. By integrating machine learning experimentation and expert validation, the system ensures reliable classification of coral health conditions, enhancing monitoring capabilities. Evaluation results demonstrate significant improvements in assessment speed, scalability, and reliability, surpassing manual methods. The framework not only streamlines monitoring but also enables real-time data collection for better conservation strategies. Its adaptability supports large-scale environmental applications, offering a scalable tool for proactive reef management. Future advancements could enhance model precision and incorporate predictive analytics, further strengthening AI’s role in marine conservation and ecosystem sustainability.