Learning Spatial Decision Trees for Land Cover Mapping

Given learning samples from a raster dataset, spatial decision tree learning aims to find a decision tree classifier that minimizes classification errors as well as salt-and-pepper noise. The problem has important societal applications such as land cover classification for natural resource management. However, the problem is challenging due to the fact that learning samples show spatial autocorrelation in class labels, instead of being independently identically distributed. Related work relies on local tests (i.e., testing feature information of a location) and cannot adequately model the spatial autocorrelation effect, resulting in salt-and-pepper noise. In contrast, in my recent papers, we proposed a focal-test-based spatial decision tree (FTSDT), in which the tree traversal direction of a sample is based on both local and focal (neighborhood) information. We introduced a focal test approach with adaptive neighborhoods that avoids over-smoothing in wedge-shaped areas. We also conducted computational refinement on the FTSDT training algorithm by reusing focal values across candidate thresholds. Theoretical analysis shows that the refined training algorithm is correct and more scalable. Experiment results on real world datasets show that new FTSDT with adaptive neighborhoods improves classification accuracy, and that our computational refinement significantly reduces training time.