Kernels for the Investigation of Localized Spatiotemporal Transitions of Drought with Support Vector Machines

We present and discuss several spatiotemporal kernels designed to mine real-life and simulated data in support of drought prediction. We implement and empirically validate these kernels for Support Vector machines. Issues related to the nature of geographic data such as autocorrelation and directionality are investigated.

• Type: Conference
• Year: 2008
• Where: ICDM
• Authors: Matthew W. Collier, Amy McGovern
• Keywords: Data Mining, Drought Prediction, ICDM 2008, Spatiotemporal Kernels, Support Vector Machines