This map is a visualization derived from more than 22,000 abstracts submitted to the Annual Meetings of the Association of American Geographers during a ten-year period from 1993 to 2002. The methodology is centered around the representation of each document as an n-dimensional vector of terms. These vectors are used to construct a neural network model of the geographic knowledge domain using a Self-Organizing Map (SOM). The neural network model is then transformed into two types of information: (1) a landscape in which elevation indicates the degree to which a single, focused topic is addressed; and (2) multilevel text labels associated with regions in the visualization. The final rendering was executed in standard geographic information systems (GIS) software.