EXtreme Gradient Boosting over Decision Trees (XGBoost or XGBDT) is a powerful tool to model a wide range of processes. We propose a new approach to create a global total electron content model, using machine-learning-based techniques, in particular, gradient boosting. The model is based on the Global Ionospheric Maps computed by Universitat Politècnica de Catalunya with a tomographic-kriging combined technique (UQRG). To reduce the problem complexity, we used empirical orthogonal functions (EOFs). The created model involves the first 16 spatial EOFs. For training and validation we used the 1998–2016 data sets, and the 2017 data as a test data set. To drive the model, we used the following features: (1) geomagnetic activity indexes (Kp, Ap, AE, AU, AL) and solar activity indexes (R, F10.7); (2) derivative values from these indexes such as the mean value and standard deviations within the last 12 h, last 11 days, and last 40 days; (3) day of the year (DOY); (4) averaged EOFs for given Kp and UT, and those for a given DOY and UT. The validation data set revealed the following hyperparameters for XGBoost learning: number of trees is 100, tree depth is 6, and learning rate is 0.1. Comparisons with the NeQuick2, Klobuchar, and GEMTEC models show that machine learning achieves higher accuracy for the 2017 test data set. The global averaged root-mean-square errors and mean absolute percentage errors were about 2.5 TECU and 19% for the nonlinear GIMLi-XGBDT model, about 4 TECU and 30–40% for NeQuick2, GEMTEC, and the linear model GIMLi-LM, and about 5.2 TECU and 73% for the Klobuchar model. A 4-fully-connected-layer artificial neural network provided a higher error (3.28 TECU and 27.7%) as compared to GIMLi-XGBDT. For all models mentioned, the error peaked in the equatorial anomaly region. The solar activity increase does not affect the error of the nonlinear GIMLi-XGBDT model. However, an increase in geomagnetic activity strongly affects that model.

决策树上的极端梯度提升（XGBoost或XGBDT）是一种功能强大的工具，可以对各种流程进行建模。我们提出了一种新方法，该方法使用基于机器学习的技术（尤其是梯度增强）来创建全局总电子含量模型。该模型基于加泰罗尼亚大学政治学院使用断层-克里格组合技术（UQRG）计算的全球电离层地图。为了减少问题的复杂性，我们使用了经验正交函数（EOF）。创建的模型涉及前16个空间EOF。为了进行培训和验证，我们使用了1998-2016年的数据集和2017年的数据作为测试数据集。为了驱动该模型，我们使用了以下特征：（1）地磁活动指数（Kp，Ap，AE，AU，AL）和太阳活动指数（R，F10.7）；（2）这些指标的衍生值，例如最近12小时，最近11天和最近40天之内的平均值和标准偏差；（3）一年中的某一天（DOY）；（4）给定Kp和UT以及给定DOY和UT的平均EOF。验证数据集显示了XGBoost学习的以下超参数：树的数量为100，树的深度为6，学习速率为0.1。与NeQuick2，Klobuchar和GEMTEC模型的比较显示，机器学习在2017年测试数据集中实现了更高的准确性。对于非线性GIMLi-XGBDT模型，全局平均均方根误差和平均绝对百分比误差分别约为2.5 TECU和19％，对于NeQuick2，GEMTEC和线性模型GIMLi-LM，约为4 TECU和30–40％，约5.2 TECU，而Klobuchar模型约占73％。与GIMLi-XGBDT相比，四层全连接层人工神经网络提供了更高的误差（3.28 TECU和27.7％）。对于所有提到的模型，误差在赤道异常区域达到峰值。太阳活动的增加不会影响非线性GIMLi-XGBDT模型的误差。但是，地磁活动的增加会强烈影响该模型。