Upwelling Detection in AVHRR Sea Surface Temperature (SST) Images using Neural-Network Framework

2018 9th International Symposium on Signal, Image, Video and Communications (ISIVC)

et al. 2018

In this paper we aim to present a new methodology to derive rigorous SST-based coastal upwelling index for the purpose of conducting a saisonal variablity of upwelling area along the Moroccan Atlantic coast. The method is based on the scientific knowledge of upwelling area and its spatial distribution provided by expert oceanographers.The latter consists in automatically identify and extract the region covered by the upwelling waters in the costal ocean of Morocco using the Fuzzy c-means algorithm and finding regions of homogeneous pixels. Then Region Growing process is used to filter out the remaining noisy structures in the offshort waters. The methodology is used to provide a satistical view of the spatial and temporal variability of the Moroccan upwelling activity. The relevance of the proposed Coastal Upwelling Index (CUI) is evaluated by an oceanographer using 86 8-days sea surface temperature images and it is shown to be superior to that of the standard upwelling index.

Section: B Identification Of the Sst Maxmentioning

confidence: 99%

An improved method for accurate computation of coastal upwelling index using Sea Surface Temperature Images

Aouni

2018 9th International Symposium on Signal, Image, Video and Communications (ISIVC)

et al. 2018

“…They are, for example, the histogram-based separation [3], where the bimodality of SST histogram is interpreted to represent two populations of water masses (cold and warm waters), and the neural networks approach [7], which classifies SST images using a feed-forward backpropagation neural network in order to find regions of homogeneous and uniform temperatures. Another class of methods deals directly with the temperature values in SST images by using the fuzzy clustering techniques [5,6,8].…”

Section: Introductionmentioning

confidence: 99%

On Detectability of Moroccan Coastal Upwelling in Sea Surface Temperature Satellite Images

Advances in Visual Computing

Daoudi

et al. 2014

Abstract. This work aims at automatically identify the upwelling areas in coastal ocean of Morocco using the Sea Surface Temperature (SST) satellite images. This has been done by using the fuzzy clustering technique. The proposed approach is started with the application of Gustafson-Kessel clustering algorithm in order to detect groups in each SST image with homogenous and non-overlapping temperature, resulting in a c-partitioned labeled image. Cluster validity indices are used to select the c-partition that best reproduces the shape of upwelling areas. An area opening technique is developed that is used to filter out the residuals noise and fine structures in offshore waters not belonging to the upwelling regions. The developed algorithm is applied and adjusted over a database of 70 SST images from years 2007 and 2008, covering the southern part of Moroccan atlantic coast. The system was evaluated by an oceanographer and provided acceptable results for a wide variety of oceanographic conditions.

“…A number of automated techniques have been proposed to detect the upwelling areas in oceanographic satellite images. Some of the most popular approaches include the use of the histogram-based separation (Nieto, Demarcq, and McClatchie 2005), which relies on the fact that upwelling fronts are usually regarded as boundaries between two water masses of constant temperature; neural networks (Chaudhari, Balasubramanian, and Gangopadhyay 2008), where the SST image is trained based on k-means segmentation results and a quantitative criterion is developed to test the existence of upwelling in each segmented image; hybrid method (Marcello, Marques, and Eugenio 2005), that has also been developed to identify the area covered upwelling waters, using region of interest histogram and region-growing process.…”

Section: Introductionmentioning

confidence: 99%

Automatic detection of Moroccan coastal upwelling zones using sea surface temperature images

International Journal of Remote Sensing

Daoudi

et al. 2018

An efficient unsupervised method is developed for automatic segmentation of the area covered by upwelling waters in the coastal ocean of Morocco using the Sea Surface Temperature (SST) satellite images. The proposed approach first uses the two popular unsupervised clustering techniques, k-means and fuzzy c-means (FCM), to provide different possible classifications to each SST image. Then several cluster validity indices are combined in order to determine the optimal number of clusters, followed by a cluster fusion scheme, which merges consecutive clusters to produce a first segmentation of upwelling area. The region-growing algorithm is then used to filter noisy residuals and to extract the final upwelling region. The performance of our algorithm is compared to a popular algorithm used to detect upwelling regions and is validated by an oceanographer over a database of 92 SST images covering each week of the years 2006 and 2007. The results show that our proposed method outperforms the latter algorithm, in terms of segmentation accuracy and computational efficiency.