Abstract
This paper presents a machine learning time-series approach to predicting the geomagnetic field at hourly resolution. The analysis uses hourly data corresponding to the horizontal component of the geomagnetic field from the Resolute Geomagnetic Observatory in Canada’s polar zone (74.690° N, 265.105° E ). Data from Jan 1, 1982, through Dec 31, 1999, is used to estimate the model. The model is evaluated from Jan 1, 2002, to Dec 31, 2005. The results indicate that the geomagnetic field’s hourly average can be predicted with moderate accuracy.
Keywords