Oil spills: Detection and concentration estimation in satellite imagery, a machine learning approach

The method's development to detect oil-spills, and concentration monitoring of marine environments, are essential in emergency response. To develop a classification model, this work was based on the spectral response of surfaces using reflectance data, and machine learning (ML) techniques, with the objective of detecting oil in Landsat imagery. Additionally, different concentration oil data were used to obtain a concentration-estimation model. In the classification, K-Nearest Neighbor (KNN) obtained the best approximations in oil detection using Blue (0.453-0.520 mu m), NIR (0.790-0.891 mu m), SWIR1 (1.557-1.717 mu m), and SWIR2 (1.960-2.162 mu m) bands for 2010 spill images. In the concentration model, the mean absolute error (MAE) was 1.41 and 3.34, for training and validation data. When testing the concentration-estimation model in images where oil was detected, the concentration-estimation obtained was between 40 and 60 %. This demonstrates the potential use of ML techniques and spectral response data to detect and estimate the concentration of oil-spills.

Automated summary

This study developed a model for oil-spill detection and concentration estimation based on spectral response data and machine learning techniques, showing potential applications in detecting and estimating oil spills.