-
Abstract: Accurate detection of an oil spill is of great significance for rapid response to oil spill accidents. Multispectral images have the advantages of high spatial resolution, short revisit period, and wide imaging width, which is suitable for large-scale oil spill monitoring. However, in wide remote sensing images, the number of oil spill samples is generally far less than that of seawater samples. Moreover, the sea surface state tends to be heterogeneous over a large area, which makes the identification of oil spills more difficult because of various sea conditions and sunglint. To address this problem, we used the F-Score as a measure of the distance between forecast value and true value, proposed the Class-Balanced F loss function (CBF loss function) that comprehensively considers the precision and recall, and rebalances the loss according to the actual sample numbers of various classes. Using the CBF loss function, we constructed convolution neural networks (CBF-CNN) for oil spill detection. Based on the image acquired by the Coastal Zone Imager (CZI) of the Haiyang-1C (HY-1C) satellite in the Andaman Sea (study area 1), we carried out parameter adjustment experiments. In contrast to experiments of different loss functions, the F1-Score of the detection result of oil emulsions is 0.87, which is 0.03–0.07 higher than cross-entropy, hinge, and focal loss functions, and the F1-Score of the detection result of oil slicks is 0.94, which is 0.01–0.09 higher than those three loss functions. In comparison with the experiment of different methods, the F1-Score of CBF-CNN for the detection result of oil emulsions is 0.05–0.12 higher than that of the deep neural networks, supports vector machine and random forests models, and the F1-Score of the detection result of oil slicks is 0.15–0.22 higher than that of the three methods. To verify the applicability of the CBF-CNN model in different observation scenes, we used the image obtained by HY-1C CZI in the Karimata Strait to carry out experiments, which include two studies areas (study area 2 and study area 3). The experimental results show that the F1-Score of CBF-CNN for the detection result of oil emulsions is 0.88, which is 0.16–0.24 higher than that of other methods, and the F1-Score of the detection result of oil slicks is 0.96–0.97, which is 0.06–0.23 higher than that of other methods. Based on all the above experiments, we come to the conclusions that the CBF loss function can restrain the influence of oil spill and seawater sample imbalance on oil spill detection of CNN model thus improving the detection accuracy of oil spills, and our CBF-CNN model is suitable for the detection of oil spills in an area with weak sunglint and can be applied to different scenarios of CZI images.
-
Key words:
- oil spills /
- CNN /
- classification /
- loss function /
- sunglint /
- detection
-
Figure 1. Study area 1. a. Geographical location of study area 1; b. the true color RGB image of study area 1; c. the angle between the viewing direction and the direction of mirror reflection (
${\mathit{\theta }}_{\rm{m}}$ ) of study area 1; d. the spectra of oil emulsions, oil slicks, and seawater.Table 1. Main technical specifications of the Haiyang-1C Coastal Zone Imager
Band/nm Central
wavelength/nmSpatial
resolution/mSignal-noise
radio/dB420–500 460 50 410 520–600 560 50 300 610–690 650 50 248 760–890 825 50 240 Table 2. Parameters of different models
Models Parameters CBF-CNN Epoch: 100; Batch size: 450; Optimizer: Adam; Loss function: CBF; Learning rate: 0.001; Spatial neighborhood-scale: 11×11 CNN Epoch: 100; Batch size: 450; Optimizer: Adam; Loss function: cross entropy; Learning rate: 0.001; Spatial neighborhood-scale: 11×11 DNN Hidden layer sizes: 50; Activation: ReLU; Optimizer: Adam; Learning rate: 0.2; Epoch: SVM Kernel: RBF; C: 700; Gamma: 0.25; Degree: 3 RF The number of the trees: 90; The minimum number of samples on leaf: 50; The maximum number of elements: 5 Table 3. Confusion matrices of different methods
Methods Class Seawater Oil emulsions Oil slicks CBF loss-CNN seawater 699 123 1 1 667 oil emulsion 170 8 704 1 576 oil slick 2 857 849 54 021 DNN seawater 700 303 25 463 oil emulsion 527 7 943 1 980 oil slick 23 060 869 33 798 SVM seawater 682 360 97 18 334 oil emulsion 281 8 054 2 115 oil slick 9 689 1 124 46 914 RF seawater 688 620 1 898 10 273 oil emulsion 198 8 387 1 865 oil slick 10 726 1 664 45 337 Table 4. Statistics of training data and test data
Class Oil emulsions Oil slicks Background Total Train 288 369 12 485 13 142 Test 924 1 000 31 311 33 235 Total 1 212 1 369 43 796 46 377 Table 5. Parameters of different models
Models Parameters CBF-CNN Epoch: 100; Batch size: 450; Optimizer: Adam; Loss function: CBF; Learning rate: 0.001; Spatial neighborhood-scale: 11×11 DNN Hidden layer sizes: (100, 50); Activation: ReLU; Optimizer: Adam; Learning rate: 0.2; Epoch: 200 SVM Kernel: RBF; C: 500; Gamma: 0.5; Degree: 3 RF The number of the trees: 100; The minimum number of samples on leaf: 50; The maximum number of elements: 5 Table 6. Statistics of train data and test data
Class Oil slicks Background Total Training 4 111 10 584 14 695 Test 7 790 17 782 25 572 Total 11 901 28 366 40 267 Table 7. Parameters of different models
Models Parameters CBF-CNN Epoch: 100; Batch size: 450; Optimizer: Adam; Loss function: CBF; Learning rate: 0.001; Spatial neighborhood-scale: 11×11 DNN Hidden layer sizes: (100, 70); Activation: ReLU; Optimizer: Adam; Learning rate: 0.2; Epoch: 200 SVM Kernel: RBF; C: 800; Gamma: 0.35; Degree: 3 RF The number of the trees: 80; The minimum number of samples on leaf: 20; The maximum number of elements: 3 Table 8. Detection performance of different methods for oil slicks
Methods Precision Recall F1-Score CBF-CNN 0.94 0.97 0.96 DNN 0.69 0.84 0.76 SVM 0.66 0.86 0.75 RF 0.70 0.76 0.73 -
[1] Abbriano R M, Carranza M M, Hogle S L, et al. 2011. Deepwater horizon oil spill: a review of the planktonic response. Oceanography, 24(3): 294–301. doi: 10.5670/oceanog.2011.80 [2] Adamo M, De Carolis G, De Pasquale V, et al. 2009. Detection and tracking of oil slicks on sun-glittered visible and near infrared satellite imagery. International Journal of Remote Sensing, 30(24): 6403–6427. doi: 10.1080/01431160902865772 [3] Breiman L. 2001. Random forests. Machine Learning, 45(1): 5–32. doi: 10.1023/A:1010933404324 [4] Chen Weitao, Li Xianju, He Haixia, et al. 2018. A review of fine-scale land use and land cover classification in open-pit mining areas by remote sensing techniques. Remote Sensing, 10(1): 15 [5] Corucci L, Nardelli F, Cococcioni M. 2010. Oil spill classification from multi-spectral satellite images: exploring different machine learning techniques. In: Proceedings of SPIE 7825, Remote Sensing of the Ocean, Sea Ice, and Large Water Regions 2010. Toulouse: SPIE, 782509 [6] Cui Yin, Jia Menglin, Lin T Y, et al. 2019. Class-balanced loss based on effective number of samples. In: Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA: IEEE [7] Esbaugh A J, Mager E M, Stieglitz J D. et al 2016. The effects of weathering and chemical dispersion on Deepwater Horizon crude oil toxicity to mahi-mahi (Coryphaena hippurus) early life stages. Science of The Total Environment, 543: 644–651. doi: 10.1016/j.scitotenv.2015.11.068 [8] Feng Lian, Hou Xuejiao, Li Junsheng, et al. 2018. Exploring the potential of Rayleigh-corrected reflectance in coastal and inland water applications: a simple aerosol correction method and its merits. ISPRS Journal of Photogrammetry and Remote Sensing, 146: 52–64. doi: 10.1016/j.isprsjprs.2018.08.020 [9] Hu Chuanmin. 2009. A novel ocean color index to detect floating algae in the global oceans. Remote Sensing of Environment, 113(10): 2118–2129. doi: 10.1016/j.rse.2009.05.012 [10] Hu Chuanmin, Li Xiaofeng, Pichel W G, et al. 2009. Detection of natural oil slicks in the NW Gulf of Mexico using MODIS imagery. Geophysical Research Letters, 36(1): L01604 [11] Hu Chuanmin, Lu Yingcheng, Sun Shaojie, et al. 2021. Optical remote sensing of oil spills in the ocean: what is really possible?. Journal of Remote Sensing, 2021: 9141902 [12] Ioffe S, Szegedy C. 2015. Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning. Lille: ACM, 448–456 [13] Jiang Zongchen, Ma Yi. 2020. Accurate extraction of offshore raft aquaculture areas based on a 3D-CNN model. International Journal of Remote Sensing, 41(14): 5457–5458. doi: 10.1080/01431161.2020.1737340 [14] Jiang Zongchen, Ma Yi, Yang Junfang. 2020. Inversion of the thickness of crude oil film based on an OG-CNN Model. Journal of Marine Science and Engineering, 8(9): 653. doi: 10.3390/jmse8090653 [15] Kingma D, Ba J. 2015. Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations. San Diego, CA: arXiv.org [16] Kolokoussis P, Karathanassi V. 2018. Oil spill detection and mapping using sentinel 2 imagery. Journal of Marine Science and Engineering, 6(1): 4. doi: 10.3390/jmse6010004 [17] LeCun Y, Bengio Y. 1995. Convolutional networks for images, speech, and time series. In: Arbib M A, ed. The Handbook of Brain Theory and Neural Networks. Cambridge: MIT Press [18] Lin T Y, Goyal P, Girshick R, et al. 2017. Focal loss for dense object detection. In: Proceedings of 2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2999–3007 [19] Lu Yingcheng, Li Xiang, Tian Qingjiu, et al. 2013. Progress in marine oil spill optical remote sensing: detected targets, spectral response characteristics, and theories. Marine Geodesy, 36(3): 334–346. doi: 10.1080/01490419.2013.793633 [20] Lu Yingcheng, Shi Jing, Hu Chuanmin, et al. 2020. Optical interpretation of oil emulsions in the ocean–Part II: Applications to multi-band coarse-resolution imagery. Remote Sensing of Environment, 242: 111778. doi: 10.1016/j.rse.2020.111778 [21] Lu Yingcheng, Sun Shaojie, Zhang Minwei, et al. 2016. Refinement of the critical angle calculation for the contrast reversal of oil slicks under sunglint. Journal of Geophysical Research: Oceans, 121(1): 148–161. doi: 10.1002/2015JC011001 [22] Lu Jinshu, Xu Zhenfeng, Xu Song, et al. 2015. Experimental and numerical investigations on reliability of air barrier on oil containment in flowing water. Marine Pollution Bulletin, 95(1): 200–206. doi: 10.1016/j.marpolbul.2015.04.020 [23] Michel J, Owens E H, Zengel S, et al. 2013. Extent and degree of shoreline oiling: Deepwater horizon oil spill, Gulf of Mexico, USA. PLoS ONE, 8(6): e65087. doi: 10.1371/journal.pone.0065087 [24] Niclòs R, Doña C, Valor E, et al. 2013. Thermal-infrared spectral and angular characterization of crude oil and seawater emissivities for oil slick identification. IEEE Transactions on Geoscience and Remote Sensing, 52(9): 5387–5395 [25] Serra-Sogas N, O’Hara P D, Canessa R, et al. 2008. Visualization of spatial patterns and temporal trends for aerial surveillance of illegal oil discharges in western Canadian marine waters. Marine Pollution Bulletin, 56(5): 825–833. doi: 10.1016/j.marpolbul.2008.02.005 [26] Shen Yafeng, Liu Jianqiang, Ding Jing, et al. 2020. HY-1C COCTS and CZI observation of marine oil spills in the South China Sea. Journal of Remote Sensing, 24(8): 933–944 [27] Sun Shaojie, Lu Yingcheng, Liu Yongxue, et al. 2018. Tracking an oil tanker collision and spilled oils in the East China Sea using multisensor day and night satellite imagery. Geophysical Research Letters, 45(7): 3212–3220. doi: 10.1002/2018GL077433 [28] Tong Cheng, Mu Bing, Liu Rongjie, et al. 2019. Atmospheric correction algorithm for HY-1C CZI over turbid waters. Journal of Coastal Research, 90(SI): 156–163 [29] Wen Yansha, Wang Mengqiu, Lu Yingcheng, et al. 2018. An alternative approach to determine critical angle of contrast reversal and surface roughness of oil slicks under sunglint. International Journal of Digital Earth, 11(9): 972–979. doi: 10.1080/17538947.2018.1470687 [30] Yang Junfang, Wan Jianhua, Ma Yi, et al. 2019. Oil spill hyperspectral remote sensing detection based on DCNN with multi-scale features. Journal of Coastal Research, 90(SI): 332–339 [31] Yekeen S T, Balogun A L, Yusof K B W. 2020. A novel deep learning instance segmentation model for automated marine oil spill detection. ISPRS Journal of Photogrammetry and Remote Sensing, 167: 190–200. doi: 10.1016/j.isprsjprs.2020.07.011 [32] Yin Liping, Zhang Min, Zhang Yuanling, et al. 2018. The long-term prediction of the oil-contaminated water from the Sanchi collision in the East China Sea. Acta Oceanologica Sinica, 37(3): 69–72. doi: 10.1007/s13131-018-1193-5 [33] Zhu Xueyuan, Li Ying, Zhang Qiang, et al. 2019. Oil film classification using deep learning-based hyperspectral remote sensing technology. ISPRS International Journal of Geo-Information, 8(4): 181. doi: 10.3390/ijgi8040181