Oil Spilling Detection at Marine Environment using Automatic Identification System (AIS) and Satellite Datasets

Abstract

Oil spills in marine environments pose serious threats to ecosystems, public health, and maritime economies. This paper presents a dual-layered automated detection framework that integrates Automatic Identification System (AIS) data with satellite remote sensing to enable early detection and reporting of oil spills. The system uses Isolation Forest for unsupervised detection of vessel anomalies and a Support Vector Machine (SVM) model for classifying potential spills from satellite imagery. This combined approach enhances the speed and accuracy of detection while supporting real-time monitoring through a user-friendly web interface.