Real-Time Machine Learning Enabled Low-Cost Magnetometer System

TL;DR

This paper presents a low-cost, real-time machine learning system for baseline correction of magnetometer data to improve geomagnetic disturbance forecasting related to space weather hazards.

Contribution

It introduces a novel ML-enabled magnetometer system that performs real-time baseline correction and GIC prediction, enhancing space weather monitoring capabilities.

Findings

ML models achieve high prediction accuracy in real-time

Localized peaks of dBH/dt are validated with binary event analysis

System reduces costs and improves response time for geomagnetic monitoring

Abstract

Geomagnetically Induced Currents (GICs) are one of the most hazardous effects of space weather. The rate of change in ground horizontal magnetic component dBH/dt is used as a proxy measure for GIC. In order to monitor and predict dBH/dt, ground-based fluxgate magnetometers are used. However, baseline correction is crucial before such magnetometer data can be utilized. In this paper, a low-cost Machine Learning (ML) enabled magnetometer system has been implemented to perform realtime baseline correction of magnetometer data. The predicted geomagnetic components are then used to derive a forecast for dBH/dt. Two different ML models were deployed, and their real-time and offline prediction accuracy were examined. The localized peaks of the predicted dBH/dt are further validated using binary event analysis.