Spatiotemporal Relational Random Forests

Abstract—We introduce and validate Spatiotemporal Relational Random Forests, which are random forests created with spatiotemporal relational probability trees. We build on the documented success of random forests by bringing spatiotemporal capabilities to the trees, enabling them to identify critical spatial, temporal, and spatiotemporal features in the data. We validate our results on simulated data and realworld convectively-induced turbulence data from a commercial airline flying in the continental United States. Keywords-Spatiotemporal data mining, Relational learning, Random forests, Turbulence

• Type: Conference
• Year: 2009
• Where: ICDM
• Authors: Timothy A. Supinie, Amy McGovern, John Williams, Jennifer Abernathy
• Keywords: Data Mining, ICDM 2009, Random Forests, Relational Random Forests, Spatiotemporal Relational Probability