Creating a Density Surface Model Using the Kernel Method
When using the Kernel Method, the cell values in a density surface model are a function of fitting a bell-shaped surface, called a kernel, over each point. Over the center of the data point, the kernel has a value of 1. As the surface of the kernel progresses towards the outer edge of the search neighborhood, the value gradually decreases to a value of 0. The Kernel Method calculates the density values by adding the kernel surfaces together where they overlap the center of each cell. The sum of the kernel surfaces is then divided by the area of the search neighborhood. From the Density toolbox under Spatial Analyst Tools, open the Kernel Density tool.
For the Input Point Features, choose your drunk driving incidents data. Save the Output raster to your working folder. For the Output cell size, enter 30. The smaller the cell size, the smoother the surface will look. However, the file size will also be more substantial. In this example, 30 meters is a good balance given the size of Los Angeles County. Next, to the Search Radius, enter the Observed Mean Distance value from the results of your Average Nearest Neighbor tool. Next to Area units, change the unit of measurement to SQUARE METERS. This setting will ensure that the units match the results of the Average Nearest Neighbor tool. Leave all other settings as default and click OK.
A new density surface model is added to the Table of Contents. As in the previous step, ArcMap used a default blue color scheme. The layer is symbolized using the Equal Interval classification method and nine classes.
Using the same procedures when changing the symbology for the simple density surface, change the color ramp to Cold to Hot Diverging. The results will be a hot-spot map of incidents related to drinking and driving over the past 30 days based on the Kernel Density method.