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 μm), NIR (0.790–0.891 μm), SWIR1 (1.557–1.717 μm), and SWIR2 (1.960–2.162 μm) 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. [Display omitted] •The visible 0.453–0.520 μm and infrared 0.790–2.162 μm spectral ranges are of major importance in oil detection.•A ML model with nonlinearity characteristics generates good approximations in the detection of oil.•Different oil concentrations from public spectral response data help make estimations in optical imaging.•There is an inverse correlation between oil concentration and spectral reflectance acquired by an optical sensor.