Describing multi-layer spatial patterns using an integrated co-occurrence matrix (INCOMA)
Maps of landscape types (LTs) are useful abstractions that facilitate land resources management. However, their creation is difficult as local landscapes arise from a fusion of patterns of many natural themes. This paper introduces the integrated co-occurrence matrix (INCOMA) – a signature for numerical representation of multi-thematic categorical patterns. The region tessellated into local landscapes can be represented by INCOMA, which allows for the identification of LTs using standard clustering techniques. The concept of INCOMA is described, and its application is demonstrated by an unsupervised mapping of LTs in Europe based on combined patterns of land cover, landforms, and soils.