Abstract
We present a comparison of the largest collection of classifiers considered until now in the literature, composed by 428 methods belonging to 41 very different families. This collection, much larger than the one in our previous work (Fernández-Delgado et al. in J Mach Learn Res 15:3133–3181, 2014), includes 320 ensembles (varying the base and meta-classifiers), alongside with Support Vector Machines, Bayesian, Neural Networks, Discriminant Analysis, Multivariate Adaptive Regression Splines, Random Forests, Decision Trees and many others. The classifier comparison is developed on the detection of oil spills on Synthetic Aperture Radar (SAR) images taken from satellites. The SAR images have revealed very useful to surveillance maritime agencies for the detection of regular offshore operational discharges, which, despite is commonly accepted, is one of the biggest causes of hydrocarbon marine pollution, instead of tanker and oil platform catastrophes. After a segmentation of the SAR images to select oil spill candidates, classifiers use the features extracted from these candidates to discard frequent and expensives look-alikes (false positives), caused by natural phenomena. Testing experiments revealed that the RotationForest ensemble of MultilayerPerceptron base classifiers, applying Kernel PCA on the original data, achieves the best accuracy and Cohen \(\kappa\) (87.1 % and 71.0 %, respectively) with a low frequency of false positives (5.13 %).
Access this article
Rent this article via DeepDyve
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig1_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig2_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig3_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig4_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig5_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig6_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig7_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig8_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig9_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig10_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig11_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig12_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig13_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig14_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-016-2415-4/MediaObjects/521_2016_2415_Fig15_HTML.gif)
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Notes
Henceforth, we will abbreviate e.g., “number of folds” or “number of neurons,” among others, as #folds or #neurons, respectively.
References
Asariotis R, Benamara H, Finkenbrink H, Hoffmann J, Jalmurzina A, Premti A, Valentine V, Youssef F (2012) Review of maritime transport, 2012. Technical report, United Nations Conference on Trade and Development, United Nations
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Breiman L, Friedman J, Olshen R, Stone CJ (1984) Classification and regression trees. Wadsworth and Brooks, Belmont
Brekke C, Solberg AHS (2008) Classifiers and confidence estimation for oil spill detection in ENVISAT ASAR images. IEEE Geosci Remote Sens Lett 5(1):65–69
Carletta J (1996) Assessing agreement on classification tasks: the kappa statistic. Comput Linguist 22(2):249–254
Chang C, Lin C (2014) LibSVM: a library for Support Vector Machines. http://www.csie.ntu.edu.tw/~cjlin/libsvm
Chawla N, Bowyer K, Hall L, Kegelmeyer W (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357
Cleary J, Trigg L (1995) K*: an instance-based learner using an entropic distance measure. In: 12th International conference on machine learning, pp 108–114
Del Frate F, Petrocchi A, Lichtenegger J, Calabresi G (2000) Neural networks for oil spill detection using ERS-SAR data. IEEE Trans Geosci Remote Sens 38(5):2282–2287
Ding B, Gentleman R (2005) Classification using generalized partial least squares. J Comput Graph Stat 14(2):280–298
Dobson A (1990) An introduction to generalized linear models. Chapman and Hall, London
ESA (1998) Oil pollution monitoring, in ERS and its applications: Marine. Technical report, European Space Agency
Fan R, Chang K, Hsieh C, Wang X, Lin C (2008) LIBLINEAR: a library for large linear classification. J Mach Learn Res 9:1871–1874
Fernández-Delgado M, Cernadas E, Barro S, Amorim D (2014) Do we need hundreds of classifiers to solve real world classification problems? J Mach Learn Res 15:3133–3181
Fernández-Delgado M, Cernadas E, Barro S, Ribeiro J, Neves J (2014) Direct Kernel Perceptron (DKP): ultra-fast kernel ELM-based classification with non-iterative closed-form weight calculation. Neural Netw 50:60–71
Fingas M, Brown C (2014) Review of oil spill remote sensing. Mar Pollut Bull 83(1):9–23
Flusser J, Zitova B, Suk T (2009) Affine moment invariants. In: Moments and moment invariants in pattern recognition, chap. 3. Wiley, London, pp 49–112
Frank E, Witten I (1999) Generating accurate rule sets without global optimization. In: International conference on machine learning, pp 144–151
Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: International conference on machine learning. Morgan Kaufmann, Los Altos, pp 148–156
Friedman J (1991) Multivariate adaptive regression splines. Ann Stat 19(1):1–141
Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 95(2):337–407
Garcia-Pineda O, Zimmer B, Howard M, Pichel W, XiaoFeng L, MacDonald IR (2009) Using SAR images to delineate ocean oil slicks with a texture-classifying neural network algorithm (TCNNA). Can J Remote Sens 35(5):411–421
Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten I (2009) The Weka data mining software: an update. SIGKDD Explor Newsl 11(1):10–18
He H, Garcia E (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 1263–1284
Hersbach H, Stoffelen A, de Haan S (2007) An improved C-band scatterometer ocean geophysical model function: CMOD5. J Geophys Res 112(C3):C03–006
Hovland HA, Johannessen JA, Digranes G (1994) Slick detection in SAR images. In: Proceedings of IGARSS ’94–1994 IEEE international geoscience and remote sensing symposium. IEEE, pp 2038–2040
Hu MK (1962) Visual pattern recognition by moment invariants. IRE Trans Inf Theory 8(2):179–187
Huang G (2014) http://www.extreme-learning-machines.org
Jackson C, Apel J (eds) (2005) Synthetic aperture Radar Marine User’s manual, 1st edn. U.S. Department of Commerce: National Oceanic and Atmospheric Administration. http://www.sarusersmanual.com (Retrieved May 2012)
Joachims T (1999) Making large-scale SVM learning practical advances in Kernel methods—support vector learning. MIT-Press, Cambridge
Keramitsoglou I, Cartalis C, Kiranoudis CT (2006) Automatic identification of oil spills on satellite images. Environ Model Softw 21(5):640–652
Kittler J, Hatef M, Duin R, Matas J (1998) On combining classifiers. IEEE Trans Pattern Anal Mach Intell 20:226–239
Kuhn M, Johnson K (2013) Applied predictive modeling. Springer, Berlin
Liu P, Zhao C, Li X, He M, Pichel W (2010) Identification of ocean oil spills in SAR imagery based on fuzzy logic algorithm. Int J Remote Sens 31(17–18):4819–4833
Mera D, Cotos JM, Varela-Pet J, Garcia-Pineda O (2012) Adaptive thresholding algorithm based on SAR images and wind data to segment oil spills along the northwest coast of the Iberian Peninsula. Mar Pollut Bull 64(10):2090–2096
Mera D, Cotos JM, Varela-Pet J, Rodrguez PG, Caro A (2014) Automatic decision support system based on SAR data for oil spill detection. Comput Geosci 72:184–191
Mercier G, Girard-Ardhuin F (2006) Partially supervised oil-slick detection by SAR imagery using kernel expansion. IEEE Trans Geosci Remote Sens 44(10):2839–2846
Migliaccio M, Tranfaglia M, Ermakov SA (2005) A physical approach for the observation of oil spills in SAR images. IEEE J Ocean Eng 30(3):496–507
Nissen S (2014) FANN: fast artificial neural networks, v. 2.1.0. http://leenissen.dk/fann/wp
Pavlakis P, Tarchi D, Sieber A (2001) On the monitoring of illicit vessel discharges using spaceborne sar remote sensing—a reconnaissance study in the Mediterranean sea. Ann Telecommun 56(11):700–718
Platt J (1998) Fast training of support vector machines using sequential minimal optimization. In: Scholkopf B, Burges C, Smola A (eds) Advances in Kernel methods—support vector learning. MIT Press, Cambridge, pp 185–208
Ripley BD (1996) Pattern recognition and neural networks. Cambridge University Press, Cambridge
Rodríguez J, Kuncheva L, Alonso C (2006) Rotation Forest: a new classifier ensemble method. IEEE Trans Pattern Anal Mach Intell 28(10):1619–1630
Scholkopf B, Smola A, Muller KR (1998) Nonlinear component analysis as a Kernel eigenvalue problem. Neural Comput 1299–1319
Singha S, Bellerby TJ, Trieschmann O (2013) Satellite oil spill detection using artificial neural networks. IEEE J Sel Top Appl Earth Obs Remote Sens 6(6):2355–2363
Solberg AHS, Brekke C, Husoy PO (2007) Oil spill detection in Radarsat and Envisat SAR images. IEEE Trans Geosci Remote Sens 45(3):746–755
Specht D (1990) Probabilistic neural networks. Neural Netw 3(1):109–118
Suykens J, Vandewalle J (1999) Least Squares support vector machine classifiers. Neural Process Lett 9(3):293–300
Topouzelis K, Karathanassi V, Pavlakis P, Rokos D (2007) Detection and discrimination between oil spills and look-alike phenomena through neural networks. ISPRS J Photogramm Remote Sens 62(4):264–270
Topouzelis K, Psyllos A (2012) Oil spill feature selection and classification using decision tree forest on SAR image data. ISPRS J Photogramm Remote Sens 68:135–143
Wang Z, Shao Y, Wu T (2014) Proximal parametric-margin support vector classifier and its applications. Neural Comput Appl 24:755–764
Webb G (2000) Multiboosting: a technique for combining boosting and wagging. Mach Learn 40(2):159–196
Wolpert D (1992) Stacked generalization. Neural Netw 5:241–259
Youden W (1950) Index for rating diagnostic tests. Cancer 3:32–35
Acknowledgments
Work developed with the help and data provided by SASEMAR, and the financial support of the Deputación da Coruña and the Spanish Ministry of Science and Innovation (MICINN) under Projects TIN2011-22935 and TIN2012-32262.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mera, D., Fernández-Delgado, M., Cotos, J.M. et al. Comparison of a massive and diverse collection of ensembles and other classifiers for oil spill detection in SAR satellite images. Neural Comput & Applic 28 (Suppl 1), 1101–1117 (2017). https://doi.org/10.1007/s00521-016-2415-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2415-4