An overview of the Space Time Pattern Mining toolbox

The Space Time Pattern Mining toolbox contains statistical tools for analyzing data distributions and patterns in the context of both space and time. It includes a toolset that can be helpful for visualizing the data stored in the space-time netCDF cube in both 2D and 3D and filling missing values in your data prior to cube creation.

The Create Space Time Cube By Aggregating Points , Create Space Time Cube From Defined Locations, and Create Space Time Cube From Multidimensional Raster Layer tools take datasets and build a multidimensional cube data structure (netCDF) for analysis. the Emerging Hot Spot Analysis tool takes the cube as input and identifies statistically significant hot and cold spot trends over time. You can use the Emerging Hot Spot Analysis tool to analyze crime or disease outbreak data to locate new, intensifying, persistent, or sporadic hot spot patterns at different time-step intervals. The Local Outlier Analysis tool takes the cube as input to identify statistically significant clusters of high or low values as well as outliers that have values that are statistically different than their neighbors in space and time. The Time Series Clustering tool partitions the locations in a space-time cube into distinct clusters in which members of each cluster have similar time series characteristics.


Create Space Time Cube By Aggregating Points

Summarizes a set of points into a netCDF data structure by aggregating them into space-time bins. Within each bin, the points are counted, and specified attributes are aggregated. For all bin locations, the trend for counts and summary field values are evaluated.

Create Space Time Cube From Defined Locations

Takes panel data or station data (defined locations where geography does not change but attributes are changing over time) and structures it into a netCDF data format by creating space-time bins. For all locations, the trend for variables or summary fields is evaluated.

Create Space Time Cube From Multidimensional Raster Layer

Creates a space-time cube from a multidimensional raster layer and structures the data into space-time bins for efficient space-time analysis and visualization.

Emerging Hot Spot Analysis

Identifies trends in the clustering of point densities (counts) or values in a space-time cube created using either the Create Space Time Cube By Aggregating Points, Create Space Time Cube From Defined Locations or Create Space Time Cube from Multidimensional Raster Layer tool. Categories include new, consecutive, intensifying, persistent, diminishing, sporadic, oscillating, and historical hot and cold spots.

Local Outlier Analysis

Identifies statistically significant clusters and outliers in the context of both space and time. This tool is a space-time implementation of the Anselin Local Moran's I statistic.

Time Series Clustering

Partitions a collection of time series, stored in a space-time cube, based on the similarity of time series characteristics. Time series can be clustered based on three criteria: having similar values across time, tending to increase and decrease at the same time, and having similar repeating patterns. The output of this tool is a 2D map displaying each location in the cube symbolized by cluster membership and messages. The output also includes charts containing information about the representative time series signature for each cluster.


Time Series Forecasting toolset

The tools in the Time Series Forecasting toolset allow you to forecast and estimate future values of a space-time cube as well as evaluate and compare different forecast models at each location in a space-time cube. Various time series forecasting models can be are available, including simple curve fitting, exponential smoothing, and a forest-based method.

Utilities toolset

These utility scripts allow you to complete your dataset prior to the creation of a space-time cube or to explore the variables stored in the space-time cube. The Fill Missing Values tool minimizes the impact of missing data (nulls) on subsequent analyses. The visualization tools can be used to understand the structure of the cube, how the cube aggregation process works, and also to visualize patterns over time at specific locations of interest. These tools are designed to be used in conjunction with the other tools in the Space Time Pattern Mining toolbox.

Additional resources

The Spatial Statistics Resources page contains a list of resources to help you use the spatial statistics tools, including the following:

  • Tutorials
  • Videos
  • Free web seminars
  • Books, articles, and white papers
  • Sample scripts and case studies

Related topics

In this topic
  1. Additional resources