Abnormal events detection using deep neural networks: application to extreme sea surface temperature detection in the Red Sea
Type
ArticleKAUST Department
Applied Mathematics and Computational Science ProgramComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Earth Fluid Modeling and Prediction Group
Earth Science and Engineering Program
King Abdullah Univ. of Science and Technology
Physical Science and Engineering (PSE) Division
Date
2019-03-13Permanent link to this record
http://hdl.handle.net/10754/652843
Metadata
Show full item recordAbstract
We present a method based on deep learning for detecting and localizing abnormal/extreme events in sea surface temperature (SST) of the Red Sea images using training samples of normal events only. The method operates in two stages; the first one involves features extraction from each patch of the SST input image using the first two convolutional layers extracted from a pretrained convolutional neural network. In the second stage, two methods are used for training the model from the normal training data. The first method uses one-class support vector machine (1-SVM) classifier that allows a fast and robust abnormal detection in the presence of outliers in the training dataset. In the second method, a Gaussian model is defined on the Mahalanobis distances between all normal training data. Experimental tests are conducted on satellite-derived SST data of the Red Sea spanning for a period of 31 years (1985-2015). Our results suggest that the Gaussian model of Mahalanobis distances outperformed 1-SVM by providing better performance in terms of sensitivity and specificity.Citation
Hittawe MM, Afzal S, Jamil T, Snoussi H, Hoteit I, et al. (2019) Abnormal events detection using deep neural networks: application to extreme sea surface temperature detection in the Red Sea. Journal of Electronic Imaging 28: 1. Available: http://dx.doi.org/10.1117/1.JEI.28.2.021012.Publisher
SPIE-Intl Soc Optical EngJournal
Journal of Electronic Imagingae974a485f413a2113503eed53cd6c53
10.1117/1.JEI.28.2.021012