Large-Scale Detection and Categorization of Oil Spills from SAR Images with Deep Learning

• Published in: Remote sensing (Basel, Switzerland) Vol. 12; no. 14; p. 2260
• Main Authors: Bianchi, Filippo Maria, Espeseth, Martine M., Borch, Njål
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-07-2020; MDPI
• Subjects: Classification; Datasets; Deep learning; Design improvements; Fysikk: 430; Image detection; Image processing; Image segmentation; Matematikk og Naturvitenskap: 400; Mathematics and natural science: 400; Mineral oils; Neural networks; object detection; Oil spills; Physics: 430; Pollution detection; Radar imaging; Remote sensing; SAR; Semantics; Sensors; Synthetic aperture radar; VDP; Visualization; Barents Sea; North Sea
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs12142260

We propose a deep-learning framework to detect and categorize oil spills in synthetic aperture radar (SAR) images at a large scale. Through a carefully designed neural network model for image segmentation trained on an extensive dataset, we obtain state-of-the-art performance in oil spill detection, achieving results that are comparable to results produced by human operators. We also introduce a classification task, which is novel in the context of oil spill detection in SAR. Specifically, after being detected, each oil spill is also classified according to different categories of its shape and texture characteristics. The classification results provide valuable insights for improving the design of services for oil spill monitoring by world-leading providers. Finally, we present our operational pipeline and a visualization tool for large-scale data, which allows detection and analysis of the historical occurrence of oil spills worldwide.