Clustering of Household Plots Using Self-organizing Maps

The paper provides a methodology for typing household plots in a settlement in the Astrakhan region of the Russian Federation, implemented through cluster analysis based on the Self-Organizing Maps (SOMs). As a result, three clusters were formed: a small cluster of 125 large households (C1), a small cluster of 370 medium-sized households (C2), and a large cluster of 1879 small households (C3); the silhouette coefficient was 0.56. Using the SOM map graph, the three largest households assigned to Cluster C1 were identified. The specialization of Cluster C1 is primarily livestock-raising and consists of cattle breeding (the share is 78.9%); this cluster is also distinguished by the presence of 100% of the settlement’s pastures (all pastures belong to the households of this cluster), the breeding of 98% of goats, and 91.7% sheep. The specialization of Cluster C2 for breeding dairy cattle has been established (the share of livestock was 43.9% of the total household plot’s livestock of the settlement). Cluster C3 is distinguished by a large area of perennial crops (the share is 79.4%), specialization in breeding pigs (the share in the settlement is 76.6%), and poultry (72.9%).