Search

The accurate identification of marine oil spills and their emulsions is of great significance for emergency response to oil spill pollution. The selection of characteristic bands with strong separability helps to realize the rapid calculation of data on aircraft or in orbit, which will improve the timeliness of oil spill emergency monitoring. At the same time, the combination of spectral and spatial features can improve the accuracy of oil spill monitoring. Two ground-based experiments were designed to collect measured airborne hyperspectral data of crude oil and its emulsions, for which the multiscale superpixel level group clustering framework (MSGCF) was used to select spectral feature bands with strong separability. In addition, the double-branch dual-attention (DBDA) model was applied to identify crude oil and its emulsions. Compared with the recognition results based on original hyperspectral images, using the feature bands determined by MSGCF improved the recognition accuracy, and greatly shortened the running time. Moreover, the characteristic bands for quantifying the volume concentration of water-in-oil emulsions were determined, and a quantitative inversion model was constructed and applied to the AVIRIS image of the deepwater horizon oil spill event in 2010. This study verified the effectiveness of feature bands in identifying oil spill pollution types and quantifying concentration, laying foundation for rapid identification and quantification of marine oil spills and their emulsions on aircraft or in orbit. [ABSTRACT FROM AUTHOR]

Monitoring marine oil pollution holds both practical and scientific significance. Synthetic Aperture Radar (SAR) is an active microwave remote sensing technique capable of all-weather and all-day with fine spatial resolution. However, under low wind conditions, rain cells and young ice are examples of look-alikes affect the accuracy of oil spill detection. Polarimetric SAR assumes a crucial role in this context, as it can extract abundant polarimetric features by polarimetric target decomposition. Drawing inspiration from this advancement, an improved polarimetric feature named relative feature based on Cloude-Pottier target decomposition was proposed. The Jeffries-Matusita distance indicates the substantial potential of the relative feature in detecting oil spills. The improved polarimetric feature within U-Net, FCN-8s, and DeepLabv3+ResNet-18 for oil spill detection using polarization SAR images. Experiment results demonstrated that the relative feature has superior performance compared to other polarimetric features and obtained the highest accuracy and dice within U-Net compared to the other two models. These findings introduce promising concepts for achieving rapid and precise detection of oil spills in future applications. [ABSTRACT FROM AUTHOR]

Oil spills on the sea surface have caused serious harm to the marine ecological environment and coastal environment. Oil film thickness (OFT) is an important parameter for estimating oil spills amount, and accurate quantification of OFT is of great significance for rapid response and risk assessment of oil spills. In recent years, thermal infrared remote sensing has been gradually applied to quantify the OFT. In this paper, the outdoor oil spill simulation experiments were designed, and the bright temperature (BT) data of different OFTs were obtained for 24 consecutive hours in summer and autumn. On the basis of the correlation analysis of OFT and bright temperature difference (BTD) between oil and water, the traditional regression fitting model, classical machine learning model, ensemble learning model, and deep learning model were applied to the inversion of OFT. At the same time, inversion results of the four models were compared and analyzed. In addition, the best OFT inversion time using thermal infrared was studied based on 24-h thermal infrared data. Additionally, the inversion results were compared with the measured results; the optimal OFT range detectable using thermal infrared was explored. The experimental results show that: (1) Compared with ensemble learning model, traditional regression fitting model, and classical machine learning model, Convolutional Neural Network (CNN) has the advantages of high stability while maintaining high-precision inversion, and can be used as the preferred model for oil film thickness inversion; (2) The optimal time for OFT detection is around 10:00 to 13:00 of the day, and is not affected by seasonal changes; (3) During the day, thermal infrared has good detection ability for OFT greater than 0.4 mm, and weak detection ability for thinner oil films; (4) At night, thermal infrared has certain detection ability for relatively thick oil film, but the accuracy is lower than that in the daytime. [ABSTRACT FROM AUTHOR]

Marine oil spills can cause serious damage to marine ecosystems and biological species, and the pollution is difficult to repair in the short term. Accurate oil type identification and oil thickness quantification are of great significance for marine oil spill emergency response and damage assessment. In recent years, hyperspectral remote sensing technology has become an effective means to monitor marine oil spills. The spectral and spatial features of oil spill images at different levels are different. To accurately identify oil spill types and quantify oil film thickness, and perform better extraction of spectral and spatial features, a multilevel spatial and spectral feature extraction network is proposed in this study. First, the graph convolutional neural network and graph attentional neural network models were used to extract spectral and spatial features in non-Euclidean space, respectively, and then the designed modules based on 2D expansion convolution, depth convolution, and point convolution were applied to extract feature information in Euclidean space; after that, a multilevel feature fusion method was developed to fuse the obtained spatial and spectral features in Euclidean space in a complementary way to obtain multilevel features. Finally, the multilevel features were fused at the feature level to obtain the oil spill information. The experimental results show that compared with CGCNN, SSRN, and A2S2KResNet algorithms, the accuracy of oil type identification and oil film thickness classification of the proposed method in this paper is improved by 12.82%, 0.06%, and 0.08% and 2.23%, 0.69%, and 0.47%, respectively, which proves that the method in this paper can effectively extract oil spill information and identify different oil spill types and different oil film thicknesses. [ABSTRACT FROM AUTHOR]

Marine oil spills are among the most significant sources of marine pollution. Synthetic aperture radar (SAR) has been used to improve oil spill observations because of its advantages in oil spill detection and identification. However, speckle noise, weak boundaries, and intensity inhomogeneity often exist in the oil spill regions of SAR imagery, which will seriously affect the accurate identification of oil spills. To enhance marine oil spill segmentation of SAR images, a fast, edge-preserving framework based on the distance-regularized level set evolution (DRLSE) model was proposed. Specifically, a bilateral filter penalty term is designed and incorporated into the DRLSE energy function (BF-DRLSE) to preserve the edges of oil spills, and an adaptive initial box boundary was selected for the DRLSE model to reduce the operation time complexity. Two sets of RadarSat-2 SAR data were used to test the proposed method. The experimental results indicate that the bilateral filtering scheme incorporated into the energy function during level set evolution improved the stability of level set evolution. Compared with other methods, the proposed improved BF-DRLSE algorithm displayed a higher overall segmentation accuracy (97.83%). In addition, using an appropriate initial box boundary for the DRLSE method accelerated the global search process, improved the accuracy of oil spill segmentation, and reduced computational time. Therefore, the results suggest that the proposed framework is effective and applicable for marine oil spill segmentation. [ABSTRACT FROM AUTHOR]

In the oil industry, oil spills occur due to offshore rig explosions, ship collisions, and other reasons. It is crucial to accurately and rapidly identify oil spills to protect marine ecosystems. Synthetic aperture radar (SAR) can all-weather and all-time work and provide a wealth of polarization information for identification of oil spills based on semantic segmentation model. However, the performance of classifiers in the semantic segmentation model has become a significant challenge to improving recognition ability. To solve this problem, an improved semantic segmentation model named DRSNet was proposed, which uses ResNet-50 as the backbone in DeepLabv3+ and support vector machines (SVM) as the classifier. The experiment was conducted using ten polarimetric features from SAR images and results demonstrate that the DRSNet performs best compared to other semantic segmentation models. Current work provides a valuable tool to enhance maritime emergency management capabilities. • Ten key polarimetric features are used for oil spill detection. • ResNet-50 as the backbone in encoder of DeepLabv3+, can get more feature map extraction. • SVM as the classifier can trained by the more sufficiently feature map to identify oil spill pixels. [ABSTRACT FROM AUTHOR]

Oil spill pollution at sea causes significant damage to marine ecosystems. Quad-polarimetric Synthetic Aperture Radar (SAR) has become an essential technology since it can provide polarization features for marine oil spill detection. Using deep learning models based on polarimetric features, oil spill detection can be achieved. However, there is insufficient feature extraction due to model depth, small reception field lend due to loss of target information, and fixed hyperparameter for models. The effect of oil spill detection is still incomplete or misclassified. To solve the above problems, we propose an improved deep learning model named BO-DRNet. The model can obtain a more sufficiently and fuller feature by ResNet-18 as the backbone in encoder of DeepLabv3+, and Bayesian Optimization (BO) was used to optimize the model's hyperparameters. Experiments were conducted based on ten prominent polarimetric features were extracted from three quad-polarimetric SAR images obtained by RADARSAT-2. Experimental results show that compared with other deep learning models, BO-DRNet performs best with a mean accuracy of 74.69% and a mean dice of 0.8551. This paper provides a valuable tool to manage upcoming disasters effectively. [ABSTRACT FROM AUTHOR]