Prediction of Oil Spills using Machine Learning Algorithm

Abstract

The detection of oil spills in water is a frequently researched area, but most of the research is based on very large patches of crude oil on offshore areas. The present novel framework is detecting oil spills inside a port environment, using the convolutional neural network algorithm the framework is split into a training part and an operational part. In the training part, the present process can automatically annotating RGB images and matching them with the IR images in order to create a dataset. The infrared imaging camera is crucial to be able to detect oil spills during nighttime, using various features and architectures are tested in the training process to find the best combination for the convolution neural network(CNN) algorithm. In the operational part, a real-time, onboard unmanned aerial vehicle(UAV) oil spill detection method is proposed using the pre-trained network and a low power interference device. This framework shows promise for quickly and accurately detecting oil spills in port environments, helping to minimize their impact on the environment. Key Words: RGB, Infrared images(IR), Unmanned Aerial Vehicles(UAV), Convolution Neural Network(CNN).