The Dynamic Time Warping As a Means to Assess Modeled Solar Wind Time Series
crossref(2021)
摘要
In this work, the Dynamic Time Warping (DTW) technique is presented as an alternative method to assess the performance of modeled solar wind time series at Earth (or at any other point in the heliosphere). This method can quantify how similar two time series are by providing a temporal alignment between them, in an optimal way and under certain restrictions. It eventually estimates the optimal alignment between an observed and a modeled series, which we call the warping path, by providing a single number, the so-called DTW cost. A description on the reasons why DTW should be applied as a metric for the assessment of solar wind time series, is presented. Furthermore, examples on how exactly the technique is applied to our modeled solar wind datasets with EUHFORIA, are shown and discussed.This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 870437 (SafeSpace).
更多查看译文
关键词
Dynamic Time Warping,Time Series Forecasting,Dimensionality Reduction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要