Decision Tree Algorithm for Detection of Spatial Processes in Landscape Transformation

The conversion of landscapes by human activities results in widespread changes in landscape spatial structure. Regardless of the type of land conversion, there appears to be a limited number of common spatial configurations that result from such land transformation processes. Some of these configurations are considered optimal or more desirable than others. Based on pattern geometry, we define ten processes responsible for pattern change: aggregation, attrition, creation, deformation, dissection, enlargement, fragmentation, perforation, shift, and shrinkage. A novelty in this contribution is the inclusion of transformation processes causing expansion of the land cover of interest. Consequently, we propose a decision tree algorithm that enables detection of these processes, based on three parameters that have to be determined before and after the transformation of the landscape: area, perimeter length, and number of patches of the focal landscape class. As an example, the decision tree algorithm is applied to determine the transformation processes of three divergent land cover change scenarios: deciduous woodland degradation in Cadiz Township (Wisconsin, USA) 1831–1950, canopy gap formation in a terra firme rain forest at the Tiputini Biodiversity Station (Amazonian Ecuador) 1997–1998, and forest regrowth in Petersham Township (Massachusetts, USA) 1830–1985. The examples signal the importance of the temporal resolution of the data, since long-term pattern conversions can be subdivided in stadia in which particular pattern components are altered by specific transformation processes.