Heard about GIS (Geographic Information System), GIScience, Spatial Data Science, Geospatial information and technologies? Wondering what it is all about?
Let’s start with some background info.
GIS – Geographic Information System is a system that enables you to create, edit, organise, work with and analyse spatial information. It is a very powerful tool that not only lets you interact with data but also perform complex multi-dimensional analyses. Although many GIS appear to be button pressing software packages, they do also contain scripting and programming components; enabling you to customise analyses, process large and complex datasets, and perform a variety of geocomputational processes or tasks. Many GIS did look and operate in much the same way as R today and were originally command line. These have evolved and continue to evolve into the sophisticated software packages available today, many of which operate in the cloud.
GIScience – Geographic Information Science is the scientific discipline that studies data structures and computational techniques to capture, represent, process, and analyze geographic information.
Spatial Data Science – Spatial Data Science (SDS) is a subset of Data Science that focuses on the special characteristics of spatial data and allows analysts to extract deeper insight from different types of data using a comprehensive set of analytical methods and spatial algorithms that range from traditional spatial analysis methods (measurement, topological, network & location type analyses, surface analyses or spatial statistical analyses) to data science methods that include machine learning and deep learning techniques.
Other terms that you may have heard or seen used
Geomatics – is an applied science concerned with the collection, integration, management, and analysis of geospatial information.
Summary
So to summarise, spatial data science uses a mix of spatial analysis, statistical analysis, data science and machine learning/AI methods to visualize, explore and analyse spatial information. These methods can also be used to model different phenomena or help us make predictions so that we can better understand different aspects of the world around us.
Any insights gained from the data visualisation, exploration or analysis can be used to build knowledge about how a system may work (the ecology of the system) or to make data-driven decisions or figure out solutions. The added bonus of adding different geographies (e.g. transportation, political, environment, socio-economic, social, cultural, etc.) is that it is possible to put the data into context which can help in understanding similarities, differences or relationships.
© 2023-present GeoSpatialSense. All Rights Reserved
GeoSpatialSense 