Shape-based Feature Engineering for Solar Flare Prediction
This work provides an incremental improvement in solar flare prediction accuracy, which can help mitigate the impact of these events on human activities.
The paper introduces a suite of novel shape-based features extracted from magnetogram images using computational topology and geometry. When evaluated with a multi-layer perceptron, these features outperformed traditional physics-based attributes for solar flare prediction, and their combination further improved forecasting.
Solar flares are caused by magnetic eruptions in active regions (ARs) on the surface of the sun. These events can have significant impacts on human activity, many of which can be mitigated with enough advance warning from good forecasts. To date, machine learning-based flare-prediction methods have employed physics-based attributes of the AR images as features; more recently, there has been some work that uses features deduced automatically by deep learning methods (such as convolutional neural networks). We describe a suite of novel shape-based features extracted from magnetogram images of the Sun using the tools of computational topology and computational geometry. We evaluate these features in the context of a multi-layer perceptron (MLP) neural network and compare their performance against the traditional physics-based attributes. We show that these abstract shape-based features outperform the features chosen by the human experts, and that a combination of the two feature sets improves the forecasting capability even further.