I'm using AGD 10.1 and playing around with some workflows for automating interpolation in a Python script. For a series of EBK models, I was using the Incremental Spatial Autocorrelation tool to calculate a distance band, and setting the MajorSemiaxis of my search neighborhood in a template XML file. I happen to notice that the EBK tool auto-populated the same value when I ran it in ArcMap.
Does GA use Incremental Spatial Autocorrelation behind the scenes to create a default values for a search neighborhood?
If so, does it do this for all interpolation tools (IDW, EBK, etc.)?
Sorry if this is documented somewhere. I couldn't find an answer on my own.
No, we do not use Incremental Spatial Autocorrelation for the search radius. In the EBK geoprocessing tool, the search radius is defaulted to one quarter of the diagonal extent of the input points (as is every other Geostatistical Analyst interpolation tool that uses a searching neighborhood). However, since it also uses minimum/maximum neighbors, the search radius isn't actually very important. It will search as far as it needs to in order to get the minimum number of neighbors, then it will stop when it either hits the maximum number of neighbors or the end of the search radius.
Also, I'm not sure why you need template layers for EBK. Using template layers is our suggested way of automating kriging (except EBK) because there is no kriging geoprocessing tool in Geostatistical Analyst. But since EBK has a gp tool, there's no reason to use template layers.
No, we do not use Incremental Spatial Autocorrelation for the search radius. In the EBK geoprocessing tool, the search radius is defaulted to one quarter of the diagonal extent of the input points (as is every other Geostatistical Analyst interpolation tool that uses a searching neighborhood). However, since it also uses minimum/maximum neighbors, the search radius isn't actually very important. It will search as far as it needs to in order to get the minimum number of neighbors, then it will stop when it either hits the maximum number of neighbors or the end of the search radius.
Also, I'm not sure why you need template layers for EBK. Using template layers is our suggested way of automating kriging (except EBK) because there is no kriging geoprocessing tool in Geostatistical Analyst. But since EBK has a gp tool, there's no reason to use template layers.
Thanks Eric. I'm not sure why I chose to use templates originally; this is a project I've put down and picked up several times. Luckily it's a trivial update on my end.
