Mining satellite data for extracting chlorophyll a spatio-temporal patterns in the Mediterranean Sea. (April 2022)

• Record Type: Journal Article
• Authors: Mattei, F.; Scardi, M.
• Is Part Of: Environmental modelling & software. Volume 150(2022)
• Publication Date: 2022-04
• Subjects: Chlorophyll a -- Remote sensing -- Time series analysis -- Data imputation -- Dynamic time warping -- Self-organizing maps; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2022.105353
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: Understanding the evolution of natural systems spatio-temporal dynamics is paramount in modern ecology. We focused on highlighting and analysing temporal and spatial dynamics of remotely-sensed chlorophyll a concentration. This pigment is linked with phytoplankton production, which in turn play a pivotal role in marine environment. Satellite platforms offer a synoptic view of surface chlorophyll a concentration for the last two decades. Coupling this source of information with statistical and Machine Learning techniques could help highlighting eventual patterns. We merged the Mediterranean chlorophyll a satellite data for the last two decades into a single dataset. We tested several techniques for reconstructing missing data and performed a general analysis. Finally, we implemented a Dynamic Time Warping Self-Organizing Map algorithm to cluster our series showing that an elastic distance measure outperforms a non-elastic one. The proposed satellite data management and analysis provided insights on spatio-temporal chlorophyll a dynamics in the Mediterranean Basin. Highlights: Spatio-temporal dynamics of Mediterranean chlorophyll a . Extracting spatio-temporal patterns from satellite data. Data imputation of univariate and spatially related time series. DTW-SOM for time series clustering.