We develop a mixed long short‐term memory (LSTM) regression model to predict the maximum solar flare intensity within a 24‐hr time window 0–24, 6–30, 12–36, and 24–48 hr ahead of time using 6, 12, 24, and 48 hr of data (predictors) for each Helioseismic and Magnetic Imager (HMI) Active Region Patch (HARP). The model makes use of (1) the Space‐Weather HMI Active Region Patch (SHARP) parameters as predictors and (2) the exact flare intensities instead of class labels recorded in the Geostationary Operational Environmental Satellites (GOES) data set, which serves as the source of the response variables. Compared to solar flare classification, the model offers us more detailed information about the exact maximum flux level, that is, intensity, for each occurrence of a flare. We also consider classification models built on top of the regression model and obtain better results in solar flare classifications as compared to Chen et al. (2019, https://doi.org/10.1029/2019SW002214). Our results suggest that the most efficient time period for predicting the solar activity is within 24 hr before the prediction time using the SHARP parameters and the LSTM model.

中文翻译：

---

基于机器学习模型的太阳耀斑强度预测

我们开发了一个混合的长期短期记忆（LSTM）回归模型，以预测在24小时的时间范围内提前0-24、6-30、12-36和24-48小时内使用6的最大太阳耀斑强度。每个地震和磁成像仪（HMI）有源区域补丁（HARP）的第12、24和48小时数据（预测值）。该模型利用（1）太空-天气HMI活动区域补丁（SHARP）参数作为预测因子，以及（2）精确的耀斑强度，而不是记录在对地静止作战环境卫星（GOES）数据集中的类别标签。响应变量的来源。与太阳耀斑分类相比，该模型为我们提供了有关每次耀斑的确切最大通量水平（即强度）的更详细信息。我们还考虑了基于回归模型的分类模型，与Chen等人相比，在太阳耀斑分类中获得了更好的结果。（2019，https://doi.org/10.1029/2019SW002214）。我们的结果表明，使用SHARP参数和LSTM模型预测太阳活动的最有效时间是在预测时间之前的24小时内。