Timing of the solar wind propagation delay between L1 and Earth based on machine learning

TL;DR

This paper introduces a machine learning method using decision trees to accurately predict the solar wind propagation delay from L1 to Earth, improving upon traditional models and aiding space weather impact timing.

Contribution

The study develops a novel machine learning approach that outperforms existing physical models in predicting solar wind delays using minimal input data.

Findings

ML model achieves RMSE of 4.5 minutes

Outperforms flat and vector delay models by 50% and 15%

Simplifies prediction process with single ACE data point input

Abstract

Erroneous GNSS positioning, failures in spacecraft operations and power outages due to geomagnetically induced currents are severe threats originating from space weather. Having knowledge of potential impacts on modern society in advance is key for many end-user applications. This covers not only the timing of severe geomagnetic storms but also predictions of substorm onsets at polar latitudes. In this study we aim at contributing to the timing problem of space weather impacts and propose a new method to predict the solar wind propagation delay between Lagrangian point L1 and the Earth based on machine learning, specifically decision tree models. The propagation delay is measured from the identification of interplanetary discontinuities detected by the Advanced Composition Explorer (ACE) and their subsequent sudden commencements in the magnetosphere recorded by ground-based magnetometers. A database of the propagation delay has been constructed on this principle including 380 interplanetary shocks. The feature set consists of six features, the three components of each the solar wind speed and position of ACE around L1. The machine learning results are compared to the flat propagation delay and the method based on the normal vector of solar wind discontinuities (vector delay). The ML model achieves an RMSE of 4.5 min with respect to the measured solar wind propagation delay and also outperforms the physical flat and vector delay models by 50 \% and 15 \% respectively. To increase the confidence in the predictions of the trained GB model, we perform a performance validation, provide feature importance and analyse the feature impact on the model output with Shapley values. The major advantage of the machine learning approach is its simplicity when it comes to its application. After training, input from only one ACE datapoint have to be fed into the algorithm for a prediction.