Decision tree application for model built-up land fragmentation in urban areas

Abstract

Land fragmentation can define as the “situation where one area/unit is composed of a large number of parcels that are too small for their rational utilization” [5]. Land fragmentation affects sustainable development through its multiple impacts on environmental, economic, and social costs [13]. Effective land use management and policy decisions are always based on understanding, modeling, and predicting land-use changes in cities [9]. Therefore, the land fragmentation process should systematically investigate to provide a wide-ranging set of land use indicators to support sustainable development [12]. Built-up land fragmentation is the fragmentation or division of the built-up plots or units within the built-up land-use area horizontally. The objective of this study is to frame a Decision Tree (DT) model to identify the non-linear relationships between the Level of Built-up Land Fragmentation (LBLF) and its influencing factors in urban areas. The sub-objective is to quantify the LBLF in the Western Province, Sri Lanka. The study scope limits to LBLF and Decision Tree (DT) non-linear classifier. The study further quantifies the LBLF from 2000 to 2010 in Western Province, Sri Lanka as an initiation to frame the DT model.