Geospatial Modeling
Geospatial modeling techniques are designed to discover patterns in data that include a geospatial (map) component. The Geospatial Modeling Wizard provides methods for analyzing geospatial data with and without a time component.
- Find associations based on event and geospatial data (Geospatial Associations Rules)
- Using geospatial association rules, you can find patterns in data based on both the spatial and non-spatial properties. For example, you might identify patterns in crime data by location and demographic attributes. From these patterns, you can build rules that predict where certain types of crimes are likely to occur.
- Make predictions using time series and geospatial data (Spatio-Temporal Prediction)
- Spatial temporal prediction uses data that contains location data, input fields for prediction (predictors), one or more time fields, and a target field. Each location has numerous rows in the data that represent the values of each predictor and the target at each time interval.
Using the Geospatial Modeling Wizard
This feature requires the Statistics Base option.
- From the menus choose:
- Follow the steps in the wizard.
Examples
Detailed examples are available in the help system.
- Geospatial association rules:
- Spatial temporal prediction: