Shape-based Feature Engineering for Solar Flare Prediction-猫眼课题宝

DOI：

10.1609/aaai.v35i17.17795

发表时间：

2020-12

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

V. Deshmukh;T. Berger;J. Meiss;E. Bradley

太阳耀斑是由太阳表面活动区(ARs)的磁喷发引起的。这些事件可能会对人类活动产生重大影响，其中许多事件可以通过良好的预报发出足够的预警来缓解。到目前为止，基于机器学习的耀斑预测方法使用的是AR图像的基于物理的属性作为特征；最近，也有一些工作使用深度学习方法(如卷积神经网络)自动推导出的特征。我们使用计算拓扑学和计算几何学的工具，描述了一组从太阳磁图图像中提取的新的基于形状的特征。我们在多层感知器(MLP)神经网络的背景下评估了这些特征，并将它们的性能与传统的基于物理的属性进行了比较。我们发现，这些抽象的基于形状的特征比人类专家选择的特征更好，并且这两个特征集的组合进一步提高了预测能力。

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.

Shape-based Feature Engineering for Solar Flare Prediction

文献摘要

相似文献