Adaptive Kernel Smoothing Regression for Spatio-Temporal Environmental Datasets

This paper describes a method for performing kernel smoothing regression in an incremental, adaptive manner. A simple and fast combination of incremental vector quantization with kernel smoothing regression using adaptive bandwidth is shown to be effective for online modeling of environmental datasets. The method is illustrated on openly available datasets corresponding to the Tropical Atmosphere Ocean array and the Helsinki Commission hydrographic database for the Baltic Sea.