We present deep learning models for cross polar cap potential (CPCP) by applying multilayer perceptron (MLP) and long short‐term memory (LSTM) networks to estimate CPCP based on Super Dual Auroral Radar Network (SuperDARN) measurements. Three statistical parameters are proposed, which are root‐mean‐square error (RMSE), mean absolute error and linear correlation coefficient (LC), to validate and test the models by measuring their performance on an independent data set that was withheld from the training data set. In addition, we compare the models with previous work. The results show that the deep learning models can successfully reproduce the CPCP values with much lower RMSE (8.41 kV for MLP and 7.20 kV for LSTM) and mean absolute error (7.22 kV for MLP and 6.28 kV for LSTM) and higher LC (0.84 for MLP and 0.90 for LSTM) than do the other models, which have RMSE larger than 10 kV and LC lower than 0.75. The deep learning models can also express the CPCP nonlinear properties (saturation effect) accurately. This study demonstrates that deep learning techniques can enhance the ability to predict CPCP.

中文翻译：

---

估计SuperDARN跨极帽电势的深度学习模型

我们通过应用多层感知器（MLP）和长短期记忆（LSTM）网络来基于超双极光雷达网络（SuperDARN）测量来估算CPCP，从而提供了跨极极电势（CPCP）的深度学习模型。提出了三个统计参数，分别是均方根误差（RMSE），平均绝对误差和线性相关系数（LC），以通过在训练中保留的独立数据集上测量模型的性能来验证和测试模型数据集。此外，我们将模型与以前的工作进行了比较。结果表明，深度学习模型可以成功地以更低的RMSE（MLP为8.41 kV，LSTM为7.20 kV）和平均绝对误差（MLP为7.22 kV，LSTM为6.28 kV）和更高的LC（C为0.84）重现CPCP值MLP，LSTM为0.90），RMSE大于10 kV，LC小于0.75。深度学习模型还可以准确表达CPCP非线性属性（饱和效应）。这项研究表明深度学习技术可以增强预测CPCP的能力。