Sea Surface Temperature Modeling using Radial Basis Function Networks With a Dynamically Weighted Particle Filter

Abstract

The sea surface temperature (SST) is an important factor of the earth climate system. A deep understanding of SST is essential for climate monitoring and prediction. In general, SST follows a nonlinear pattern in both time and location and can be modeled by a dynamic system which changes with time and location. In this article, we propose a radial basis function network-based dynamic model which is able to catch the nonlinearity of the data and propose to use the dynamically weighted particle filter to estimate the parameters of the dynamic model. We analyze the SST observed in the Caribbean Islands area after a hurricane using the proposed dynamic model. Comparing to the traditional grid-based approach that requires a supercomputer due to its high computational demand, our approach requires much less CPU time and makes real-time forecasting of SST doable on a personal computer. Supplementary materials for this article are available online.

Keywords:

• Bayesian nonparametric regression
• Dynamic model
• Dynamically weighted importance sampling
• Radial basis function networks

Acknowledgments

The authors thank the editor, associated editor, and referees for their constructive comments/suggestions that led to significant improvement of this article. Liang’s research was supported in part by grants from the National Science Foundation (DMS-1007457 and DMS-1106494) and the award (KUS-C1-016-04) made by King Abdullah University of Science and Technology (KAUST). Mallick’s research was supported by the award number KUS-CI-016-04 made by KAUST.