Statistics and Its Interface

Volume 10 (2017)

Number 1

SSA analysis and forecasting of records for Earth temperature and ice extents

Pages: 151 – 163

DOI: https://dx.doi.org/10.4310/SII.2017.v10.n1.a14

Authors

Andrey Pepelyshev (School of Mathematics, Cardiff University, Cardiff, Wales, United Kingdom)

Anatoly Zhigljavsky (School of Mathematics, Cardiff University, Cardiff, Wales, United Kingdom; and Lobachevsky State University of Nizhni Novgorod, Russia)

Abstract

In this paper, we continued the research started in [6]. We applied the so-called Singular Spectrum Analysis (SSA) to forecast the Earth temperature records, to examine cross-correlations between these records, the Arctic and Antarctic sea ice extents and the Oceanic Nino Index (ONI). We have concluded that the pattern observed in the last 15 years for the Earth temperatures is not going to change much, found very high cross-correlations between a lagged ONI index and some Earth temperature series and noticed several significant cross-correlations between the ONI index and the sea ice extent anomalies; these cross-correlations do not seem to be well-known to the specialists on Earth climate.

Keywords

singular spectrum analysis, stability of forecasts, long-horizon forecasting, retrospective forecasts, SSA vector forecasting

2010 Mathematics Subject Classification

62M20

Full Text (PDF format)

Published 27 September 2016