A Machine Learning hourly analysis on the relation the Ionosphere and Schumann Resonance Frequency

The Schumann Resonances arise from the constructive interference of dozens of near-simultaneous lightning strikes every second, mostly located in the tropics. Characterizing the Schumann Resonance signal variation is a complex task due to the number of variables affecting the electromagnetic composition of the ionosphere and the Earth. We describe a novel approach for investigating the behavior of this variation by focusing on specific hours of the day. This study further explores this preliminary influence by means of a machine learning framework composed of six conceptually different algorithms. Fourteen external variables, related to the ionosphere condition, are considered as the predictors for the monthly Schumann Resonance frequency variation along five years of real data, for each of the first six modes and separated by the hour of the day. The results provide a clear evidence of the importance of selecting a particular hour to observe the influence of the Ionosphere parameters on the Schumann Resonance frequency variation.

• Schumann resonance frequency is predicted by Ionospheric variables.
• Six Schumann Resonance modes are compared using Machine Learning.
• The relation between Schumann Resonance and ionosphere depends on the hour of the day.
• Six Machine Learning approaches explain Schumann Resonance frequency Variations.
• The result can further explore the usage of Machine Learning in Schumann Resonance data.