New Findings From Explainable SYM‐H Forecasting Using Gradient Boosting Machines
New Findings From Explainable SYM‐H Forecasting Using Gradient Boosting Machines
复制标题
DOI：
10.1029/2021sw002928
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Daniel Iong;Yang Chen;G. Tóth;S. Zou;Tuija Pulkkinen;Jiaen Ren;E. Camporeale;T. Gombosi
中科院分区：
文献类型：
--
作者：
Daniel Iong;Yang Chen;G. Tóth;S. Zou;Tuija Pulkkinen;Jiaen Ren;E. Camporeale;T. Gombosi
在这项工作中，我们开发了梯度增强机（GBM），用于使用太阳风和行星际磁场（IMF）参数，导出参数和过去SYM-H值的不同组合提前数小时预测SYM-H指数。使用Shapley加法解释值来量化每个输入对GBM SYM-H指数预测的贡献，我们表明我们的预测与物理理解一致，同时也提供了对太阳风和地球环电流之间复杂关系的洞察。特别是，我们发现，功能的贡献取决于风暴阶段。我们还通过在相同的数据上训练、验证和测试GBM和神经网络来预测SYM-H指数，从而对之前的出版物中提出的GBM和神经网络进行直接比较。我们发现，GBM在均方根误差方面比最好的黑盒神经网络方案和Burton方程有统计学上的显着改善。
In this work, we develop gradient boosting machines (GBMs) for forecasting the SYM‐H index multiple hours ahead using different combinations of solar wind and interplanetary magnetic field (IMF) parameters, derived parameters, and past SYM‐H values. Using Shapley Additive Explanation values to quantify the contributions from each input to predictions of the SYM‐H index from GBMs, we show that our predictions are consistent with physical understanding while also providing insight into the complex relationship between the solar wind and Earth's ring current. In particular, we found that feature contributions vary depending on the storm phase. We also perform a direct comparison between GBMs and neural networks presented in prior publications for forecasting the SYM‐H index by training, validating, and testing them on the same data. We find that the GBMs yield a statistically significant improvement in root mean squared error over the best published black‐box neural network schemes and the Burton equation.