Unsupervised Fuzzy Clustering for the Segmentation and Annotation of Upwelling Regions in Sea Surface Temperature Images

The Anomalous Pattern algorithm is explored as an initialization strategy to the Fuzzy

K

-Means (FCM), with the sequential extraction of clusters, that simultaneously allows the determination of the number of clusters. The composed algorithm, Anomalous Pattern Fuzzy Clustering (AP-FCM), is applied in the segmentation of Sea Surface Temperature (SST) images for the identification of Coastal Upwelling.

A set of features are constructed from the AP-FCM clustering segmentation taking into account domain knowledge and a threshold procedure is defined in order to identify the transition cluster whose frontline is automatically annotated on SST images to separate the upwelling regions from the background.

Two independent data samples in a total of 61 SST images covering large diversity of upwelling situations are analysed. Results show that by tuning the AP-FCM stop conditions it fits a good number of clusters providing an effective segmentation of the SST images whose spatial visualization of fuzzy membership closely reproduces the original images. Comparing the AP-FCM with the FCM using several validation indices shows the advantage of the AP-FCM avoiding under or over-segmented images. Quantitative assessment of the segmentations is accomplished through ROC analysis. Compared to FCM, the number of iterations of the AP-FCM is significantly decreased.

The automatic annotation of upwelling frontlines from the AP-FCM segmentation overcomes the subjective visual inspection made by the Oceanographers.