Abstract
Oil pollution of oceans from various sources is a devastating environmental problem and immediate detection of oil spills is crucial. Remote sensing techniques have provided an unprecedented opportunity for early oil spill detection and classification with an easy, quick, and cheap approach. Moreover, Fully Polarimetric Synthetic Aperture Radar (PolSAR) data with unique capabilities and informative features is an immense data source for oil spill detection on large scales. The objective of the present study is to utilize PolSAR data not only for oil spill detection, but also to classify the detected oil spill in the ocean into four classes: thick oil, thin oil, oil/water mixture, and clear water. In this study, numerous polarimetric decomposition parameters and texture features are extracted from the PolSAR image. A two-phase feature selection method, manually selection based on oil and water surface backscattering behavior and an optimization algorithm, has been employed on the extracted features to select the optimum feature set. The selected feature set has been used to classify the PolSAR image into oil and water classes. Moreover, the high sensitivity and discriminative power of the validation PolSAR dataset, UAVSAR L-band quad-pol data, is exploited by classifying the image into four classes. Remarkable acquired classification accuracies of 90.21% and 85.41% and Kappa coefficient of 0.8052 and 0.7905 for two-class and four-class classifications, respectively, demonstrate the robustness and high potential of the proposed methodology for oil spill detection and classification.
Similar content being viewed by others
References
Alpers W, Brandt P, Lazar A, Dagorne D, Sow B, Faye S, Hansen MW, Rubido A, Poulain P-M, Brehmer P (2013) A small-scale oceanic eddy off the coast of West Africa studied by multi-sensor satellite and surface drifter data. Remote Sens Environ 129:132–143. doi: https://doi.org/10.1016/j.rse.2012.10.032
Alpers W, Holt B, Zeng K (2017) Oil spill detection by imaging radars: Challenges and pitfalls. Remote Sens Environ 201:133–147. doi:https://doi.org/10.1016/j.rse.2017.09.002
Barnes RM (1988) Roll-invariant decompositions for the polarization covariance matrix. In: Proceedings of the Polarimetry Technology Workshop, Alabama, 16–18 August 1988
Brekke C, Solberg AH (2005) Oil spill detection by satellite remote sensing. Remote Sens Environ 95(1):1–13. doi:https://doi.org/10.1016/j.rse.2004.11.015
Bouchemakh L, Smara Y, Boutarfa S, Hamadache Z (2008) A comparative study of speckle filtering in polarimetric radar SAR images. In: 3rd International Conference on Information and Communication Technologies: From Theory to Applications, Damascus, pp 1–6
Buono A, Nunziata F, de Macedo CR, Velotto D, Migliaccio M (2018) A sensitivity analysis of the standard deviation of the copolarized phase difference for sea oil slick observation. IEEE T Geosci Remote 57(4):2022–2030. doi:https://doi.org/10.1109/TGRS.2018.2870738
Buono A, Nunziata F, Migliaccio M, Li X (2016) Polarimetric analysis of compact-polarimetry SAR architectures for sea oil slick observation. IEEE T Geosci Remote 54(10):5862–5874. doi:https://doi.org/10.1109/TGRS.2016.2574561
Camps-Valls G, Bruzzone L (2005) Kernel-based methods for hyperspectral image classification. IEEE T Geosci Remote 43(6):1351–1362. doi:https://doi.org/10.1109/TGRS.2005.846154
Clausi DA (2001) Comparison and fusion of co-occurrence, Gabor and MRF texture features for classification of SAR sea-ice imagery. Atmos Ocean 39(3):183–194
Cloude SR (1985) Target decomposition theorems in radar scattering. Electron Lett 21(1):22–24. doi:https://doi.org/10.1049/el:19850018
Cloude SR, Pottier E (1997) An entropy based classification scheme for land applications of polarimetric SAR. IEEE T Geosci Remote 35(1):68–78. doi:https://doi.org/10.1109/36.551935
Franceschetti G, Iodice A, Riccio D, Ruello G, Siviero R (2002) SAR raw signal simulation of oil slicks in ocean environments. IEEE T Geosci Remote 40(9):1935–1949. doi:https://doi.org/10.1109/TGRS.2002.803798
Freeman A, Durden SL (1998) A three-component scattering model for polarimetric SAR data. IEEE T Geosci Remote 36(3):963–973. doi:https://doi.org/10.1109/36.673687
Gambardella A, Giacinto G, Migliaccio M, Montali A (2010) One-class classification for oil spill detection. Pattern Anal Appl 13(3):349–366. doi:https://doi.org/10.1007/s10044-009-0164-z
Holland JH (1975) Adaptation in natural and artificial systems. MIT Press, Massachusetts, 228 p
Holm WA, Barnes RM (1988) On radar polarization mixed target state decomposition techniques. In: Proceedings of the 1988 IEEE National Radar Conference, Ann Arbor, pp 249–254
Jha MN, Levy J, Gao Y (2008) Advances in remote sensing for oil spill disaster management: state-of-the-art sensors technology for oil spill surveillance. Sensors 8(1):236–255. doi:https://doi.org/10.3390/s8010236
Jones CE, Minchew B, Holt B, Hensley S (2013) Studies of the deepwater horizon oil spill with the UAVSAR radar. In: Liu Y, MacFadyen A, Ji Z-G, Weisberg RH (eds) Monitoring and modeling the deepwater horizon oil spill: A record breaking enterprise. American Geophysical Union, Washington DC, pp 33–50
Huynen JR (1970) Phenomenological theory of radar targets. Drukkerij Bronder-Offset, Rotterdam, 219 p
Kim TS, Park KA, Li X, Lee M, Hong S, Lyu SJ, Nam S (2015) Detection of the Hebei Spirit oil spill on SAR imagery and its temporal evolution in a coastal region of the Yellow Sea. Adv Space Res 56(6):1079–1093 doi:https://doi.org/10.1016/j.asr.2015.05.040
Kumar LJV, Kishore JK, Rao PK (2014) Decomposition methods for detection of oil spills based on RISAT-1 SAR images. Int J Remote Sens Geosci 3(4):1–10
Lee JS, Schuler DL, Ainsworth TL (2003) A review of polarization orientation estimation from polarimetric SAR data. In: Chen CH (ed) Frontiers of remote sensing information processing. World Scientific Publisher, Hackensack, 614 p
Li J, Ansari N (2001) Enhanced Birkhoff-von Neumann decomposition algorithm for input queued switches. IEE P-Commun 148(6):339–342 doi:https://doi.org/10.1049/ip-com:20010618
Li Y, Zhang Y, Yuan Z, Guo H, Pan H, Guo J (2018) Marine oil spill detection based on the comprehensive use of polarimetric SAR data. Sustainability 10(12):4408. doi:https://doi.org/10.3390/su10124408
Licciardi G, Avezzano RG, Del Frate F, Schiavon G, Chanussot J (2014) A novel approach to polarimetric SAR data processing based on Nonlinear PCA. Pattern Recogn 47(5):1953–1967 doi:https://doi.org/10.1016/j.patcog.2013.11.009
MacDonald IR, Garcia-Pineda O, Beet A, Daneshgar Asl-S, Feng L, Graettinger G Leifer I (2015) Natural and unnatural oil slicks in the Gulf of Mexico. J Geophys Res-Oceans 120(12):8364–8380. doi:https://doi.org/10.1002/2015JC011062
Migliaccio M, Ferrara G, Gambardella A, Nunziata F, Sorrentino A (2007) A physically consistent speckle model for marine SLC SAR images. IEEE J Oceanic Eng 32(4):839–847. doi: https://doi.org/10.1109/JOE.2007.903985
Migliaccio M, Huang L, Buono A (2019) SAR speckle dependence on ocean surface wind field. IEEE T Geosci Remote 57(8):5447–5455. doi:https://doi.org/10.1109/TGRS.2019.2899491
Migliaccio M, Nunziata F (2014) On the exploitation of polarimetric SAR data to map damping properties of the Deepwater Horizon oil spill. Int J Remote Sens 35(10):3499–3519. doi:https://doi.org/10.1080/01431161.2014.905730
Migliaccio M, Nunziata F, Buono A (2015) SAR polarimetry for sea oil slick observation. Int J Remote Sens 36(12):3243–3273. doi:https://doi.org/10.1080/01431161.2015.1057301
Migliaccio M, Nunziata F, Gambardella A (2009) On the co-polarized phase difference for oil spill observation. Int J Remote Sens 30(6):1587–1602. doi: https://doi.org/10.1080/01431160802520741
Minchew B (2012) Determining the mixing of oil and sea water using polarimetric synthetic aperture radar. Geophysl Res Lett 39(16):L16607. doi:https://doi.org/10.1029/2012GL052304
Minchew B, Jones CE, Holt B (2012) Polarimetric analysis of backscatter from the Deepwater Horizon oil spill using L-band synthetic aperture radar. IEEE T Geosci Remote 50(10):3812–3830. doi:https://doi.org/10.1109/TGRS.2012.2185804
Moreira A, Prats-Iraola P, Younis M, Krieger G, Hajnsek I, Papathanassiou KP (2013) A tutorial on synthetic aperture radar. IEEE T Geosci Remote Mag 1(1):6–l3. doi:https://doi.org/10.1109/MGRS.2013.2248301
Nunziata F, Buono A, Migliaccio M (2018) COSMO—SkyMed synthetic aperture radar data to observe the deepwater horizon oil spill. Sustainability 10(10):3599. doi:https://doi.org/10.3390/su10103599
Rahnemoonfar M, Dhakal S (2016) Automatic oil spill detection on quad polarimetric UAVSAR imagery. In: Polarization: Measurement, analysis, and remote sensing XII, 985310, Baltimore, 17–21 April 2016
Saito N, Yamada H, Yamaguchi Y (2018) Study on land classification of PolSAR data by using support vector machine. In: 2018 IEEE international workshop on electromagnetics: Applications and student innovation competition, pp 1–2
Salehi M, Sahebi MR, Maghsoudi Y (2013) Improving the accuracy of urban land cover classification using Radarsat-2 PolSAR data. IEEE J Sel Top Appl 7(4):1394–1401. doi:https://doi.org/10.1109/JSTARS.2013.2273074
Santana-Cedrés D, Gomez L, Trujillo A, Alemán-Flores M, Deriche R, Alvarez L (2019) Supervised classification of fully PolSAR images using active contour models. IEEE Geosci Remote S 16:1165–1169. doi:https://doi.org/10.1109/LGRS.2019.2892524
Shahsavarhaghighi S, Sahebi MR, Valdanzoej MJ, Haddadi GA (2013) A comparison of IEM and SPM model for oil spill detection using inversion technique and radar data. J Indian Soc Remote Sens 41(2):425–131. doi:https://doi.org/10.1007/s12524-012-0217-4
Skrunes S, Brekke C, Eltoft T (2013) Characterization of marine surface slicks by Radarsat-2 multipolarization features. IEEE T Geosci Remote 52(9):5302–5319. doi:https://doi.org/10.1109/TGRS.2013.2287916
Suresh G, Melsheimer C, Körber JH, Bohrmann G (2015) Automatic estimation of oil seep locations in synthetic aperture radar images. IEEE T Geosci Remote 53(8):4218–4230. doi:https://doi.org/10.1109/TGRS.2015.2393375
Tong S, Liu X, Chen Q, Zhang Z, Xie G (2019) Multi-feature based ocean oil spill detection for polarimetric SAR data using random forest and the self-similarity parameter. Remote Sens 11(4):451. doi:https://doi.org/10.3390/rs11040451
Van Zyl JJ (1989) Unsupervised classification of scattering behavior using radar polarimetry data. IEEE T Geosci Remote 27(1):36–45. doi:https://doi.org/10.1109/36.20273
Wang G, Li J, Zhang B, Cai Z, Zhang F, Shen Q (2017) Synthetic aperture radar detection and characteristic analysis of cyanobacterial scum in Lake Taihu. J Appl Remote Sens 11(1):012006. doi: https://doi.org/10.1117/1.JRS.11.012006
Yamaguchi Y, Moriyama T, Ishido M, Yamada H (2005) Four-component scattering model for polarimetric SAR image decomposition. IEEE T Geosci Remote 43(8):1699–1706
Yapa PD, Wimalaratne MR, Dissanayake AL, DeGraff Jr JA (2012) How does oil and gas behave when released in deepwater? J Hydro-Environ Res 6(4):275–285. doi:https://doi.org/10.1016/j.jher.2012.05.002
Zou Q, Ni L, Zhang T, Wang Q (2015) Deep learning based feature selection for remote sensing scene classification. IEEE Geosci Remote S 12(11):2321–2325. doi:https://doi.org/10.1109/LGRS.2015.2475299
Acknowledgements
The authors would like to thank the NASA Jet Propulsion Laboratory (JPL) and the California Institute of Technology (Caltech) for making the UAVSAR data available for this study.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Hassani, B., Sahebi, M.R. & Asiyabi, R.M. Oil Spill Four-Class Classification Using UAVSAR Polarimetric Data. Ocean Sci. J. 55, 433–443 (2020). https://doi.org/10.1007/s12601-020-0023-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12601-020-0023-9