Space weather events may cause damage to several fields, including aviation, satellites, oil and gas industries, and electrical systems, leading to economic and commercial losses. Solar flares are one of the most significant events, and refer to sudden radiation releases that can affect the Earth's atmosphere within a few hours or minutes. Therefore, it is worth designing high-performance systems for forecasting such events. Although in the literature there are many approaches for flare forecasting, there is still a lack of consensus concerning the techniques used for designing these systems. Seeking to establish some standardization while designing flare predictors, in this study we propose a novel methodology for designing such predictors, further validated with extreme gradient boosting tree classifiers and time series. This methodology relies on the following well-defined machine learning based pipeline: (i) univariate feature selection; (ii) randomized hyper-parameter optimization; (iii) imbalanced data treatment; (iv) adjustment of cut-off point of classifiers; and (v) evaluation under operational settings. To verify our methodology effectiveness, we designed and evaluated three proof-of-concept models for forecasting $\geq C$ class flares up to 72 hours ahead. Compared to baseline models, those models were able to significantly increase their scores of true skill statistics (TSS) under operational forecasting scenarios by 0.37 (predicting flares in the next 24 hours), 0.13 (predicting flares within 24-48 hours), and 0.36 (predicting flares within 48-72 hours). Besides increasing TSS, the methodology also led to significant increases in the area under the ROC curve, corroborating that we improved the positive and negative recalls of classifiers while decreasing the number of false alarms.

中文翻译：

---

使用时间序列和极端梯度增强集合进行太阳耀斑预测

空间天气事件可能会对多个领域造成损害，包括航空、卫星、石油和天然气工业以及电力系统，从而导致经济和商业损失。太阳耀斑是最重要的事件之一，是指可能在几小时或几分钟内影响地球大气层的突然辐射释放。因此，值得设计用于预测此类事件的高性能系统。尽管在文献中有许多耀斑预测方法，但对于用于设计这些系统的技术仍然缺乏共识。为了在设计耀斑预测器时建立一些标准化，在本研究中，我们提出了一种设计此类预测器的新方法，并通过极端梯度提升树分类器和时间序列进一步验证。这种方法依赖于以下明确定义的基于机器学习的管道：(i) 单变量特征选择；(ii) 随机超参数优化；(iii) 数据处理不平衡；(iv) 调整分类器的截止点；(v) 操作环境下的评估。为了验证我们的方法有效性，我们设计并评估了三个概念验证模型，用于预测最多 72 小时前的 $\geq C$ 级耀斑。与基线模型相比，这些模型能够在操作预测情景下将真实技能统计 (TSS) 的分数显着提高 0.37（预测未来 24 小时内的耀斑）、0.13（预测 24-48 小时内的耀斑）和 0.36 （在 48-72 小时内预测耀斑）。除了增加 TSS，