Forecasting geomagnetic indices represents a key point to develop warning systems for the mitigation of possible effects of severe geomagnetic storms on critical ground infrastructures. Here we focus on SYM‐H index, a proxy of the axially symmetric magnetic field disturbance at low and middle latitudes on the Earth's surface. To forecast SYM‐H, we built two artificial neural network (ANN) models and trained both of them on two different sets of input parameters including interplanetary magnetic field components and magnitude and differing for the presence or not of previous SYM‐H values. These ANN models differ in architecture being based on two conceptually different neural networks: the long short‐term memory (LSTM) and the convolutional neural network (CNN). Both networks are trained, validated, and tested on a total of 42 geomagnetic storms among the most intense that occurred between 1998 and 2018. Performance comparison of the two ANN models shows that (1) both are able to well forecast SYM‐H index 1 h in advance, with an accuracy of more than 95% in terms of the coefficient of determination R²; (2) the model based on LSTM is slightly more accurate than that based on CNN when including SYM‐H index at previous steps among the inputs; and (3) the model based on CNN has interesting potentialities being more accurate than that based on LSTM when not including SYM‐H index among the inputs. Predictions made including SYM‐H index among the inputs provide a root mean squared error on average 42% lower than that of predictions made without SYM‐H.

中文翻译：

---

SYM‐H指数预测：长期短期记忆与卷积神经网络的比较

预测地磁指数是开发预警系统的关键点，以减轻严重的地磁风暴对关键地面基础设施的可能影响。在这里，我们关注SYM‐H指数，它是地球表面中低纬度处的轴对称磁场扰动的代理。为了预测SYM‐H，我们建立了两个人工神经网络（ANN）模型，并在两组不同的输入参数（包括行星际磁场分量和幅度）上对它们进行了训练，并且对是否存在先前的SYM‐H进行了训练价值观。这些ANN模型基于两个概念上不同的神经网络在架构上有所不同：长短期记忆（LSTM）和卷积神经网络（CNN）。在1998年至2018年之间发生的最强烈的地震中，对这两个网络进行了总共42次地磁风暴的培训，验证和测试。两个ANN模型的性能比较表明（1）两者都能很好地预测SYM‐H指数1预先为h，在确定系数R ²方面的准确度大于95％；（2）当包含SYM‐H时，基于LSTM的模型比基于CNN的模型更为准确输入中先前步骤的索引；（3）当在输入中不包括SYM-H指数时，基于CNN的模型具有比基于LSTM的模型更准确的潜在潜力。输入中包含SYM-H指数的预测比没有SYM-H的预测的均方根误差平均低42％。