Probabilistic Solar Proxy Forecasting With Neural Network Ensembles
Probabilistic Solar Proxy Forecasting With Neural Network Ensembles
复制标题
DOI：
10.1029/2023sw003675
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Joshua D. Daniell;P. Mehta
中科院分区：
文献类型：
--
作者：
Joshua D. Daniell;P. Mehta
空间天气指数通常用于推动热层密度的预测，热层密度通过大气阻力影响低地球轨道（LEO）上的物体。一个常用的空间天气代用指标F10.7 cm与太阳极紫外线（EUV）能量沉积到热层中有很好的相关性。目前，美国空军与空间环境技术公司（SET）签订了合同，该公司使用线性算法预测F10.7厘米。在这项工作中，我们介绍了使用具有多层感知器（MLP）和长短期记忆（LSTM）的神经网络集成来改进SET预测的方法。我们仅根据历史F10.7cm值进行预测。我们研究数据处理方法（向后平均和回顾）以及多步和动态预测。这项工作表明了流行的持久性和操作SET模型时，使用集成方法的改进。在这项工作中发现的最佳模型是使用多步或多步和动态预测相结合的集成方法。几乎所有的方法都提供了改进，最好的模型在持久性方面的相对MSE提高了48%到59%。其他相对误差指标被证明大大改善时，合奏方法。我们还能够利用集合方法来提供预测值的分布;允许对预测不确定性进行调查。我们的工作发现，在太阳活动水平升高和高水平时，模型的预测偏差较小。不确定性也通过使用校准误差分数度量（CES）进行了研究，我们最好的合奏达到类似的CES作为其他工作。
Space weather indices are used commonly to drive forecasts of thermosphere density, which affects objects in low‐Earth orbit (LEO) through atmospheric drag. One commonly used space weather proxy, F10.7cm, correlates well with solar extreme ultra‐violet (EUV) energy deposition into the thermosphere. Currently, the USAF contracts Space Environment Technologies (SET), which uses a linear algorithm to forecast F10.7cm. In this work, we introduce methods using neural network ensembles with multi‐layer perceptrons (MLPs) and long‐short term memory (LSTMs) to improve on the SET predictions. We make predictions only from historical F10.7cm values. We investigate data manipulation methods (backwards averaging and lookback) as well as multi step and dynamic forecasting. This work shows an improvement over the popular persistence and the operational SET model when using ensemble methods. The best models found in this work are ensemble approaches using multi step or a combination of multi step and dynamic predictions. Nearly all approaches offer an improvement, with the best models improving between 48% and 59% on relative MSE with respect to persistence. Other relative error metrics were shown to improve greatly when ensembles methods were used. We were also able to leverage the ensemble approach to provide a distribution of predicted values; allowing an investigation into forecast uncertainty. Our work found models that produced less biased predictions at elevated and high solar activity levels. Uncertainty was also investigated through the use of a calibration error score metric (CES), our best ensemble reached similar CES as other work.