The Atlantic coast of Morocco, being part of the Easter Boundaries Upwelling Ecosystem, is characterized by high biological productivity and seasonally variable upwelling all year around. In this work, we develop new deep learning tools to monitor the Moroccan upwelling from biological and physical satellite images. The proposed method consists of a convolutional neural network (CNN) based on an encoder-decoder built on the U-Net structure, to localize the upwelling regions. Furthermore, we provide a new indices based on the analysis of sea surface temperature (SST) and chlorophyll-a (chl-a) images to give an overall view of the upwelling variability from both the biological and physical sides at once. The new proposed indices are based on the proposed segmentation method, which makes it possible to monitor the upwelling dynamics from both satellite observations. The elaborated procedure is applied over a database of weekly SST and chl-a images covering the period from 2000 to 2019, and the results are used to analyze its fluctuations between seasonal and interannual variations in the region.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.