Machine learning applications to Kronian magnetospheric reconnection classification

Abstract

The products of magnetic reconnection in Saturn’s magnetotail are identified in magnetometer3 observations primarily through characteristic deviations in the north-south component of the4 magnetic field. These magnetic deflections are caused by travelling plasma structures created5 during reconnection rapidly passing over the observing spacecraft. Identification of these6 signatures have long been performed by eye, and more recently through semi-automated7 methods, however these methods are often limited through a required human verification step.8 Here, we present a fully automated, supervised learning, feed forward neural network model9 to identify evidence of reconnection in the Kronian magnetosphere with the three magnetic10 field components observed by the Cassini spacecraft in Kronocentric radial-theta-phi (KRTP)11 coordinates as input. This model is constructed from a catalogue of reconnection events which12 covers three years of observations with a total of 2093 classified events, categorized into13 plasmoids, travelling compression regions and dipolarizations. This neural network model is14 capable of rapidly identifying reconnection events in large time-span Cassini datasets, tested15 against the full year 2010 with a high level of accuracy (87%), true skill score (0.76), and Heidke16 skill score (0.73). From this model, a full cataloguing and examination of magnetic reconnection17 events in the Kronian magnetosphere across Cassini’s near Saturn lifetime is now possible

More information

Identifiers

ORCID for Tadhg Garton: orcid.org/0000-0002-3031-2991

Catalogue record

Export record