Automatic detection of marine oil spills from polarimetric SAR images using deep Convolutional neural network model

• A deep learning-based model is presented for automatic identification of oil spill on sea surface using SAR images. • An PolSAR dataset with multi-scenario oil spill samples is constructed. • Polarimetric scattering information in Sentinel-1 SAR data are fully utilized by the detection model. • Time-series detection of an oil spill incident in the Gulf of Mexico is conducted. Oil Spills (OS) exert serious threats to marine ecosystems, hence quick and accurate monitoring of OS is of great significance. In recent years, the Synthetic Aperture Radar (SAR) remote sensing technique has been used to monitor OS because of its wide coverage and operating in any weather conditions. However, many studies only resort to manual interpretation when morning OS by SAR images, making the interpretation process low efficiency. In this study, an intelligent method is presented for detecting OS from dual-polarized SAR images using a Deep Convolutional Neural Network (DCNN) based method. Firstly, we designed the OS detection model OSDTAU-Net based on the TransU-Net architecture, which achieves a balance between global perception and local focus by introducing the Transformer and Attention Gate mechanisms into the classical U-Net model. Secondly, we construct the Oil Spill PolSAR dataset from Sentinel-1 satellite images, which further enhances the detection capability of the model through multi-feature fusion of polarimetric information. The experimental results validate that the proposed OS detection model surpasses traditional supervised classification and classic semantic segmentation algorithms, achieving an overall accuracy of 97.09% and F1 score of 89.54%. Furthermore, using the proposed model, we successfully identified two oil spill incidents in the northern Gulf of Mexico. The generated oil spill distribution maps exhibit better continuity and closely align with the actual conditions.