Hotspot occurrences classification using decision tree method: Case study in the Rokan Hilir, Riau Province, Indonesia

Application of geospatial and data mining techniques in forest fires research have resulted interesting and useful information in decision making related to the forest fires management. This paper presents a result of the study in applying the C4.5 algorithm on a forest fire dataset in the Rokan Hilir district, Riau Province, Indonesia. The dataset consists of hotspot occurrence locations, human activity factors, and land cover types. Human activity factors include city center locations, roads network and rivers network. The results were a decision tree which contains 18 leaves and 26 nodes with accuracy about 63.17%. Most of positive examples (the area with hotspot occurrences) and negative examples (no hotspot occurrences in the area) that are incorrectly classified by the model are located near rivers and roads.