AstroAI Workshop 2025
Lidiya Ahmed
Machine Learning for Faraday Cup Calibration and Optimization of Ion Parameter Estimation
Presenter: Lidiya Ahmed
Title: Machine Learning for Faraday Cup Calibration and Optimization of Ion Parameter Estimation
Date/Time: Monday, July 7th, 3:30 - 5:00 PM
Abstract: We propose a novel scheme for analyzing particle detector measurements when a well-calibrated, similarly instrumented spacecraft is present in a similar orbit. The method uses dynamic time warping (DTW) to prepare ground truth from measurements provided by a reference spacecraft. An artificial neural network (ANN) is then trained to reproduce this ground truth from measurements at the target spacecraft. Unlike previous approaches, this procedure is insensitive to calibration errors in the target data stream, as the neural network may be trained from poorly calibrated particle spectra or even directly from low-level data in engineering units. We demonstrate a proof-of-concept by training an ANN to estimate solar wind proton densities, temperatures, and speeds from the DSCOVR PlasMag Faraday Cup, using Wind SWE as a reference. We discuss applications for Parker Solar Probe, Helioswarm, and other missions.