arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.05288astro-ph.SR
收藏

模拟实时太阳耀斑预测的性能趋势研究:训练窗口、数据量与太阳活动周期的影响

Investigating Performance Trends of Simulated Real-time Solar Flare Predictions: The Impacts of Training Windows, Data Volumes, and the Solar Cycle

Griffin T. Goodwin, Viacheslav M. Sadykov, Petrus C. Martens

AI总结:

本研究利用GSU的SWAN-SF基准数据集,模拟运行环境下的机器学习耀斑预测,发现20个月训练窗口下各窗口类型性能相当,且误报率与太阳X射线背景通量正相关,表明太阳活动周期影响显著。

摘要:

本研究探讨了在模拟运行环境中部署的基于机器学习的耀斑预测模型的行为。利用佐治亚州立大学的太阳耀斑空间天气分析基准数据集(Angryk et al. 2020a,b),我们考察了训练方法和太阳活动周期对决策树、支持向量机和多层感知机性能的影响。我们使用三种时间训练窗口实现分类器:固定窗口、滚动窗口和扩展窗口。固定窗口使用在首次预测实例之前可用的单一数据集训练模型,该数据集在整个太阳活动周期内保持不变。滚动窗口使用预测实例之前固定时间间隔的数据训练模型,该时间间隔随太阳活动周期移动。最后,扩展窗口使用预测实例之前所有可用数据训练模型。对于每种窗口,测试了不同数量的输入特征(1、5、10、25、50、120)和时间尺寸(5、8、11、14、17、20个月)。令我们惊讶的是,对于20个月的窗口,无论窗口类型、特征数量和所选分类器如何,技能分数均相当。此外,缩小此窗口的尺寸仅略微降低了固定窗口和滚动窗口的性能。这意味着,在给定足够数据的情况下,可以选择固定窗口而非其他窗口类型,从而无需重新训练模型。最后,发现模型的误报率与太阳X射线背景通量之间存在中等强度的正相关。这表明太阳活动周期阶段对预测有相当大的影响。

英文摘要:

This study explores the behavior of machine learning-based flare forecasting models deployed in a simulated operational environment. Using Georgia State University's Space Weather Analytics for Solar Flares benchmark dataset (Angryk et al. 2020a,b), we examine the impacts of training methodology and the solar cycle on decision tree, support vector machine, and multilayer perceptron performance. We implement our classifiers using three temporal training windows: stationary, rolling, and expanding. The stationary window trains models using a single set of data available before the first forecasting instance, which remains constant throughout the solar cycle. The rolling window trains models using data from a constant time interval before the forecasting instance, which moves with the solar cycle. Finally, the expanding window trains models using all available data before the forecasting instance. For each window, a number of input features (1, 5, 10, 25, 50, 120) and temporal sizes (5, 8, 11, 14, 17, 20 months) were tested. To our surprise, we found that for a 20-month window, skill scores were comparable regardless of the window type, feature count, and classifier selected. Furthermore, reducing the size of this window only marginally decreased stationary and rolling window performance. This implies that, given enough data, a stationary window can be chosen over other window types, eliminating the need for model retraining. Lastly, a moderately strong positive correlation was found to exist between a model's false positive rate and the solar X-ray background flux. This suggests that the solar cycle phase has a considerable influence on forecasting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑