Detection and Classification of Sporadic E Using Convolutional Neural Networks

Detection and Classification of Sporadic E Using Convolutional Neural Networks
复制标题

DOI:
10.1029/2023sw003669
复制
发表时间:
2024-01
期刊:
Space Weather
影响因子:
--
通讯作者:
J. A. Ellis;D. J. Emmons;M. Cohen
J. A. Ellis;D. J. Emmons;M. Cohen
中科院分区:
其他
文献类型:
--
作者:
J. A. Ellis;D. J. Emmons;M. Cohen

文献摘要

相似文献

在这项工作中,开发了卷积神经网络 (CNN) 来检测和表征零星 E (Es),证明了对当前方法的改进。这包括一个二元分类模型来确定 Es 是否存在,然后是一个回归模型来估计 Es 普通模式临界频率 (foEs)、强度的代理以及 Es 层出现的高度 (hEs)。 2008 年至 2022 年期间六个全球导航卫星系统 (GNSS) 无线电掩星 (RO) 任务的信噪比 (SNR) 和多余相位剖面被用作模型的输入。强度 (foEs) 和高度 (hEs) 值是从地面数字探空仪的全球网络获得的,并在训练期间用作“地面实况”或目标变量。将两个数据集对应后,总共有36,521个样本可用于模型的训练和测试。 foEs CNN 二元分类模型的准确率达到 74%,F1 分数为 0.70。当已知 Es 存在时,估计 foEs 和 hEs 时,平均绝对误差 (MAE) 分别为 0.63 MHz 和 5.81 km,均方根误差 (RMSE) 分别为 0.95 MHz 和 7.89 km。当将分类和回归模型组合在一起用于未知 Es 是否存在的实际应用时,实现了 foEs MAE 和 RMSE 分别为 0.97 和 1.65 MHz。我们实施了其他三种技术来进行零星 E 表征,并发现 CNN 模型似乎表现更好。
In this work, convolutional neural networks (CNN) are developed to detect and characterize sporadic E (Es), demonstrating an improvement over current methods. This includes a binary classification model to determine if Es is present, followed by a regression model to estimate the Es ordinary mode critical frequency (foEs), a proxy for the intensity, along with the height at which the Es layer occurs (hEs). Signal‐to‐noise ratio (SNR) and excess phase profiles from six Global Navigation Satellite System (GNSS) radio occultation (RO) missions during the years 2008–2022 are used as the inputs of the model. Intensity (foEs) and the height (hEs) values are obtained from the global network of ground‐based Digisonde ionosondes and are used as the “ground truth,” or target variables, during training. After corresponding the two data sets, a total of 36,521 samples are available for training and testing the models. The foEs CNN binary classification model achieved an accuracy of 74% and F1‐score of 0.70. Mean absolute errors (MAE) of 0.63 MHz and 5.81 km along with root‐mean squared errors (RMSE) of 0.95 MHz and 7.89 km were attained for estimating foEs and hEs, respectively, when it was known that Es was present. When combining the classification and regression models together for use in practical applications where it is unknown if Es is present, an foEs MAE and RMSE of 0.97 and 1.65 MHz, respectively, were realized. We implemented three other techniques for sporadic E characterization, and found that the CNN model appears to perform better.