EO Spatio-Temporal Patterns Extraction

Abstract

Since the very beginning of satellite remote sensing the methods and applications the Satellite Image Time Series (SITS) are the main nature of Earth Observation. Presently, with the regular observations and free and open access of the Copernicus data the impact of SITS is largely amplified. The challenges of the EO Big Data are critically accentuated due to joint volume explosion, high acquisition velocity and sensor variety. The presentation emphases on novel Artificial Intelligence (AI) paradigms focuses to convert the SITS in valuable EO products with impact in new applications for understanding of the Erath cover spatio-temporal processes over long periods of time. AI for EO is largely an interdisciplinary field and involves the convergence of very different methods. The lecture overviews and discuss specific topics for SITS regarding the orbit, mission, sensor constellations, intelligent agents, machine learning, deep learning, data indexing, data bases, and DNN.