Abstract
Spatial association mining, as one of important techniques for spatial data mining, is used to discover interesting relationship patterns among spatial features based on spatial proximity from a large spatial database. Explosive growth in georeferenced data has emphasized the need to develop computationally efficient methods for analyzing big spatial data. Parallel and distributed computing is effective and mostly-used strategy for speeding up large scale dataset algorithms. This work presents parallel spatial association mining on the Spark RDD framework - a specially-designed in-memory parallel computing model to support iterative algorithms. The initial experiment result shows that the Spark-based algorithm has significantly improved performance than the method with MapReduce in spatial association pattern mining.