Applications in GIS - Module 1 - Crime Analysis

In the first module for Applications in GIS we were introduced to some mapping techniques employed in crime analysis. These techniques are used to determine hotspots in criminal activity that can be utilized to determine crime rates, identify crime patterns, and compare the reliability of hotspot mapping to predict future crime.

For this module, we were required to create maps using crime data, specifically focusing on homicides in Chicago in 2017 and 2018. Below are three distinct maps illustrating the distribution of homicides in 2017. These maps included: a grid overlay thematic map highlighting areas with the highest 20% of homicides in Chicago, a kernel density map showcasing areas with homicides occurring at three times the mean average, and a local Moran's I map delineating areas aggregated by meaningful boundaries.

Part of the assignment included providing a hypothetical policy recommendation to a police chief on which hotspot map would be the best for predicting future homicides. I would suggest using the Kernel Density map because it would allow for a concentration of resources in areas with the highest density of homicides and has an almost optimal prediction rate. With Kernel Density, one could pinpoint areas with triple the mean homicide rate, whereas with the grid overlay, one could only identify areas in the top 20%. Although Local Moran I's clusters high values within aggregated boundaries, the area might appear broad on the map and could limit police time and resource availability.

Overall, this was a great learning experience that exemplified how GIS principles and technology can be applied to help solve real-world problems. I'm looking forward to learning more GIS applications in the coming modules.