An online Bayesian filtering framework for Gaussian process regression: Application to global surface temperature analysis
作者：
Highlights：
• A novel Bayesian filtering for GP regression, compared to other GP variants.
• It reduces computation while improving accuracy for large data sets.
• GP-based state space model processes data efficiently in a sequential manner.
• Our online learning mechanism is a novel venue for parameter optimization in GP.
• An efficient and accurate expert system for global surface temperature analysis.
摘要
•A novel Bayesian filtering for GP regression, compared to other GP variants.•It reduces computation while improving accuracy for large data sets.•GP-based state space model processes data efficiently in a sequential manner.•Our online learning mechanism is a novel venue for parameter optimization in GP.•An efficient and accurate expert system for global surface temperature analysis.
论文关键词：Gaussian process regression,Marginalized particle filter,Online parameter learning,Global surface temperature analysis
论文评审过程：Received 26 November 2015, Revised 9 September 2016, Accepted 10 September 2016, Available online 28 September 2016, Version of Record 6 October 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.09.018
