• Mithra N
• Deepak Kumar M
• Hariraj K
• Lizenya S
• Jaazieliah R

Fish shoal detection is a crucial aspect of marine ecology, fisheries management, and underwater surveillance. This study proposes a machine learning-based approach utilizing the Random Forest Classifier for predicting fish shoal sites and habitats and the XGBoost Regressor for estimating the number of fish shoals from sonar images. The dataset is sourced and preprocessed using Roboflow, and the models are trained to achieve high accuracy in classification and regression tasks. The MERN stack is used to develop a web-based application that visualizes predictions, providing an interactive interface for researchers and marine biologists. Experimental results demonstrate the efficiency of the proposed models in accurately identifying fish shoal locations and population estimates under varying underwater conditions. The findings of this study contribute to the advancement of AI-driven solutions for aquatic monitoring and conservation efforts.

Fish Shoal Detection, Random Forest Classifier, XGBoost Regressor, Machine Learning, Sonar Imaging, Roboflow, Marine Ecology, AI in Fisheries, Web-based Visualization, Underwater Surveillance.

"AI-Driven Detection and Tracking of Fish Shoals", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.a495-a505, July-2025, Available :http://www.jetir.org/papers/JETIR2507052.pdf

"AI-Driven Detection and Tracking of Fish Shoals", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. ppa495-a505, July-2025, Available at : http://www.jetir.org/papers/JETIR2507052.pdf