Shown below is the Kernel density map of a Insurance Claims dataset aggregated by count:
ESDA has numerous use cases as it allows you see how each feature in your data relates to its spatial location on a geospatial Map. Here we have 'drivers age' from the same dataset on our geospatial Map:
Some DataRobot use cases can be explored via our Pathfinder tool, although I did not find any geospatial ones at present from a quick search. However, we do have some examples in the community which leverage Location AI and geospatial data.