基于高斯过程的日长变化预报  

The Prediction of Length-of-day Variations Based on Gaussian Processes

作　　者：雷雨[1,2,3] 赵丹宁[1,3] 高玉平[1,2] 蔡宏兵[1,2] 

机构地区：[1]中国科学院国家授时中心,西安710600 [2]中国科学院时间频率基准重点实验室,西安710600 [3]中国科学院大学,北京100049

出　　处：《天文学报》2015年第1期53-62,共10页Acta Astronomica Sinica

基　　金：国家自然科学基金项目(10573019)资助

摘　　要：由于日长(length-of-day,LOD)变化具有复杂的时变特性,传统线性模型如最小二乘外推模型、时间序列分析模型等的预报效果往往不甚理想,所以将一种新型的机器学习算法—高斯过程(Gaussian processes,GP)方法用于LOD变化预报,并将预报结果同利用反向传播神经网络(back propagation neural networks,BPNN)和广义回归神经网络(general regression neural networks,GRNN)的预报结果以及地球定向参数预报比较竞赛(Earth Orientation Parameters Prediction Comparison Campaign,EOP PCC)的预报结果进行对比.结果表明,GP用于LOD变化预报是高效可行的.Due to the complicated time-varying characteristics of the length-of-day （LOD） variations, the accuracies of traditional strategies for the prediction of the LOD variations such as the least squares extrapolation model, the time-series analysis model, and so on, have not met the requirements for real-time and high-precision applications. In this paper, a new machine learning algorithm -- the Gaussian process （GP） model is employed to forecast the LOD variations. Its prediction precisions are analyzed and compared with those of the back propagation neural networks （BPNN）, general regression neural networks （GRNN） models, and the Earth Orientation Parameters Prediction Comparison Campaign （EOP PCC）. The results demonstrate that the application of the GP model to the prediction of the LOD variations is efficient and feasible.

关 键 词：天体测量 时间 方法:数据分析 

分 类 号：P127[天文地球—天体测量]