Spatial analysis is a process that starts by asking a question. Getting the question right is the key to working out what tools to use and what analysis to employ toward deriving a meaningful answer. Being able to better understand your data should help you to make appropriate decisions about your analysis –and anticipate how your choices will affect the results.
The web is now a source of vast amounts of data, and spatial analysis offers the means by which this data becomes valuable. As the value of analysis and spatial data gains adoption, methods and models for how to use analysis are becoming more widely available. Academics, professionals, communities, and individuals are all sharing their analytical techniques. These spatial data analysis practices cut across many disciplines. The applications are endless, and embracing a multidisciplinary approach to spatial analysis can bring significant rewards.
Geographic information system (GIS) analysis helps you to make informed decisions, but it doesn’t make the decisions for you. Doing that requires your expertise. For example, you learn that multiscale web maps can require analysis to be done at multiple scales since, for many aggregated datasets, the results are only relevant for the scale at which the analysis is performed. You’ll also need to learn to interpret results carefully – you should have an idea of the expected results and carefully check the analysis if the conclusions differ significantly.
As more communities see the power that analyzing their data with location brings, GIS technology is being pushed to new levels. Data from disparate sources is being combined, and new information is revealing new patterns and insights. Even the concept of geographic space is undergoing a challenge, as we map data using both physical and social geographies. Web maps bring spatial data and the notion of spatial analysis to everyone. The idea that location matters is no longer just the geographer’s doctrine; its value has been widely recognized and embraced. Geography matters.
How is Spatial Analysis Used?
Ask questions, derive answers
Spatial analysis is used by people around the world to derive new information and make informed decisions. The organizations that use spatial analysis in their work are wide-ranging—local and state governments, national agencies, businesses of all stripes, utility companies, colleges and universities, NGOs—the list goes on. Here are just a few examples.
Transportation: The Portland Bureau of Transportation uses spatial analysis to reveal the pattern of accidents and their relationship to traffic corridors.
Water quality: NOAA developed an analysis methodology that uses land cover as an indicator of water quality.
Public health: This series of maps shows mosquito hotspots week by week. The information helps East Flagler Mosquito Control District in Florida target its suppression efforts.
Urban planning: Kenton County, Kentucky, uses spatial analysis to map walkability in various communities and to identify gaps in sidewalk connectivity.
Conservation: WWF mapped extreme weather events, rainfall, and drought in Brazil over three decades. The trends and patterns help identify areas for future conservation projects.
Agriculture: This app from World Resources Institute lets government agencies and private companies find sites that are suitable for sustainable palm oil production in Indonesia.
Spatial Data and Spatial Analysis
Most data and measurements can be associated with locations and, therefore, can be placed on the map. Using spatial data you know both what is present and where it is. The real world can be represented as discrete data, stored by its exact geographic location (called “feature data”), or continuous data represented by regular grids (called “raster data”). Of course, the nature of what you’re analyzing influences how it is best represented. The natural environment (elevation, temperature, precipitation) is often represented using raster grids; whereas, the built environment (roads, buildings) and administrative data (countries, census areas) tend to be represented as vector data. Further information that describes what is at each location can be attached; these are often referred to as “attributes.”
In GIS each dataset is managed as a layer and can be graphically combined using analytical operators. By combining layers using operators and displays, GIS enables you to work with these layers to explore questions and find answers.
In addition to locational and attribute information, spatial data inherently contains geometric and topological properties. Geometric properties include position and measurements, such as length, direction, area, and volume. Topological properties represent spatial relationships such as connectivity, inclusion, and adjacency. Using these spatial properties, you can ask even more types of questions of your data and gain new insights.
Excerpted from The ArcGIS Book: 10 Big Ideas about Applying Geography to Your World, Christian Harder, Editor. Copyright 2015 Esri. Reprinted with permission.
Subscribe to Data Informed for the latest information and news on big data and analytics for the enterprise.