Earth Observation satellites are the only source that provides a continuous and consistent set of information about the Earth’s land and oceans. These satellites produce massive amounts of data, but only a fraction of that data is effectively used for scientific research and operational applications. This talk will discuss how to improve the extraction of information from big Earth Observation data sets. We will argue for a new type of knowledge platform for organization, access, processing and analysis of geographical data, based on the emerging technology of array databases. We will describe array databases, the differences between array databases and map-reduce architectures for big scientific data. We will also describe ongoing work by the research teams at IFGI and INPE to transform generic array databases into big Earth Observation data processing systems.