Thinking spatial

Abstract

The systems community in both academia and industry has tremendous success in building widely used general purpose systems for various types of data and applications. Examples include database systems, big data systems, data streaming systems, and machine learning systems. The vast majority of these systems are ill equipped in terms of supporting spatial data. The main reason is that system builders mostly think of spatial data as just one more type of data. Any spatial support can be considered as an afterthought problem that can be supported via on-top functions or spatial cartridges that can be added to the already built systems. This article advocates that spatial data and applications need to be natively supported in special purpose systems, where spatial data is considered as a first class citizen, while spatial operations are built inside the engine rather than on-top of it. System builders should consider spatial data while building their systems. The article gives examples of five categories of systems, namely, database systems, big data systems, machine learning systems, recommender systems, and social network systems, that would benefit tremendously, in terms of both accuracy and performance, when considering spatial data as an integral part of the system engine.