Clustering the ecological footprint of nations using Kohonen’s self-organizing maps

Per capita ecological footprint (EF) is one of the most widely recognized measures of environmental sustainability. It seeks to quantify the Earth’s biological capacity required to support human activity. Self-organizing maps (SOM) is a machine learning method that can be used to explore patterns in large and complex datasets for linear and non-linear patterns. This study uses SOM to model and cluster the EF of 140 nations. The results show that major variables affecting a nation’s EF are related to the nation’s world system position (WSP), GDP, urbanization level, export as a percent of the GDP, services intensity, and literacy rate. The study also shows that SOM models are capable of improving clustering quality while extracting valuable information from multidimensional environmental data.