Essential Site Maintenance: Authorea-powered sites will be updated circa 15:00-17:00 Eastern on Tuesday 5 November.
There should be no interruption to normal services, but please contact us at [email protected] in case you face any issues.

loading page

Physics-informed Neural Networks for the Improvement of Platform Magnetometer Measurements
  • +1
  • Kevin Styp-Rekowski,
  • Ingo Michaelis,
  • Monika Korte,
  • Claudia Stolle
Kevin Styp-Rekowski
TU Berlin

Corresponding Author:[email protected]

Author Profile
Ingo Michaelis
GFZ German Research Centre For Geosciences
Author Profile
Monika Korte
GFZ German Research Center for Geosciences
Author Profile
Claudia Stolle
Leibniz Institut of Atmospheric Physics at the University of Rostock
Author Profile

Abstract

Space-based measurements of the Earth's magnetic field with a good spatiotemporal coverage are needed to understand the complex system of our surrounding geomagnetic field. High-precision magnetic field satellite missions form the backbone for sophisticated research, but they are limited in their coverage. Many satellites carry so-called platform magnetometers that are part of their attitude and orbit control systems. These can be re-calibrated by considering different behaviors of the satellite system, hence reducing their relatively high initial noise originating from their rough calibration. These platform magnetometer data obtained from non-dedicated satellite missions complement the high-precision data by additional coverage in space, time, and magnetic local times. In this work, we present an extension to our previous Machine Learning approach for the automatic in-situ calibration of platform magnetometers. We introduce a new physics-informed layer incorporating the Biot-Savart formula for dipoles that can efficiently correct artificial disturbances due to electric current-induced magnetic fields evoked by the satellite itself. We demonstrate how magnetic dipoles can be co-estimated in a neural network for the calibration of platform magnetometers and thus enhance the Machine Learning-based approach to follow known physical principles. Here we describe the derivation and assessment of re-calibrated datasets for two satellite missions, GOCE and GRACE-FO, which are made publicly available. We achieved a mean residual of about 7 nT and 4 nT for low- and mid-latitudes, respectively.