Earth Observation Big Data Challenges the AI change of paradigm

Abstract

Earth Observation Big Data Challenges: the AI change of paradigm The volume and variety of valuable Earth Observation (EO) images as well as non-EO related data is rapidly growing. The deluge of EO images of Terabytes per day needs to be converted into meaningful information, largely impacting the socio-economic-environmental triangle. An important particularity of EO images should be considered, is their “instrument” nature, i.e. in addition to the spatial information, they are sensing physical parameters, and they are mainly sensing outside of the visual spectrum. Machine and deep learning methods are mainly used for image classification or objects segmentation, EO require hybrid AI methods encompassing from mathematical models for the satellite orbit, the physics of electromagnetic propagation and scattering, signal processing, machine learning, or knowledge representation. The new specific AI methods for EO are designed to leverage advances in physical parameters extraction.