Computational methods to leverage topological features occurring in signals and images are currently one of the most innovative trends in applied mathematics. In this paper a pipeline of topological machine learning is applied to the challenging task of classifying four specific marine mesoscale patterns from remote sensing data, i.e., Sea Surface Temperature maps of the southwestern region of the Iberian Peninsula. Our preliminary study achieves an accuracy of 56% in the 4-label classification. Such results are encouraging, especially considering that the data are affected by noise and that there are low-quality/missing data. Also, the paper devises directions for future improvements.
Understanding the marine environment dynamics to accordingly design computational predictive tools, represents a factor of paramount relevance to implement suitable policy plans. In this framework, mesoscale marine events are important to study and understand since human related activities, such as commercial fishery, strongly depend on this type of phenomena. Indeed, the dynamics of water masses affect the local habitats due to nutrient and organic substance transport, interfering with the fauna and flora development processes. Mesoscale events can be classified based on the presence of specific hydrodynamics features, such as water filaments, counter-currents or meanders originating from upwelling wind action stress. In this paper, a novel method to study these phenomena is proposed, based on the analysis of Sea Surface Temperature imagery captured by satellite missions (METOP, MODIS Terra/Aqua). Dedicated algorithms are presented, with the goal to detect and identify different observed scenarios based on the extraction and analysis of discriminating quantitative features. Promising results returned by the application of the proposed method to data captured within the maritime region in front of the southwestern Iberian coasts are presented.
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.