The AIMag Project: Using Machine Learning to Predict Crustal Magnetic Anomaly Values

A detailed model of the Earth’s total magnetic field is important for acquiring the means for GPS-alternative, magnetic anomaly-based navigation. The Earth’s total magnetic field is an amalgam of 5 mechanisms: the geodynamo generated by the rotation of the Earth’s molten iron core, the fields induced by the flows of electric current in the atmosphere and oceans, the disturbance of the ionosphere by solar wind, and local anomalies attributable to ferromagnetic minerals present in the crust; the lattermost compose the crustal magnetic field. The EMAG2v3 dataset comprises a compilation of satellite, shipborne, and airborne magnetic measurements differenced from the Comprehensive Model (CM4) to yield a 2-minute grid of magnetic anomalies. The current work analyzes this dataset for use as a training set in a convolutional neural network (CNN) intended to predict crustal magnetism in areas without measurements, particularly for use in GPS-denied regions. For this purpose, global topography and bathymetry data, gravitational field data (EGM08), and the Magnetic Field Model (MF7) have been preprocessed as CNN inputs.