Magnetic Field Data Calibration with Transformer Model Using Physical Constraints: A Scalable Method for Satellite Missions, Illustrated by Tianwen-1

However, magnetometer data often suffer from disturbances caused by satellite dynamics, onboard instrument interference, and environmental noise. For instance, changes in satellite orientation can lead to anomalies in magnetic field measurements due to interference from electric currents within the satellite's instruments. These disturbances necessitate careful data correction to ensure the accuracy and reliability of measurements. Traditional correction methods rely heavily on human expertise and are rooted in well established physical and mathematical principles. While these methods have proven effective, they are inherently limited by their long processing times and delays in real time prediction [7] [6] [4] [2] [1]. In contrast, machine learning models, though rarely applied in this field, offer strong predictive capabilities and the potential for faster computations. This study seeks to address these limitations by combining the strengths of traditional correction methods with the adaptability and efficiency of machine learning models, thereby improving timeliness while ensuring both physical consistency and improved real time performance. This study bridges the gap between data driven models and physics based understanding by integrating Maxwell's equations into the neural network architecture as physical information. The key innovations are: 1 arXiv:2501.00020v3