Late-time transient electromagnetic (TEM) data contain deep subsurface information and are important for resolving deeper electrical structures. However, due to their relatively small signal amplitudes, TEM responses later in time are often dominated by ambient noises. Therefore, noise removal is critical to the application of TEM data in imaging electrical structures at depth. De-noising techniques for TEM data have been developed rapidly in recent years. Although strong efforts have been made to improving the quality of the TEM responses, it is still a challenge to effectively extract the signals due to unpredictable and irregular noises. In this study, we develop a new type of neural network architecture by combining the Long Short-Term Memory (LSTM) network with the autoencoder structure to suppress noise in TEM signals. The resulting LSTM-autoencoders yield excellent performance on synthetic datasets including horizontal components of the electric field and vertical component of the magnetic field generated by different sources such as dipole, loop and grounded line sources. The relative errors between the de-noised datasets and the corresponding noise-free transients are below 1 per cent for most of the sampling points. Notable improvement in the resistivity structure inversion result is achieved using the TEM data de-noised by the LSTM-autoencoder in comparison with several widely-used neural networks, especially for later-arriving signals that are important for constraining deeper structures. We demonstrate the effectiveness and general applicability of the LSTM-autoencoder by de-noising experiments using synthetic one-dimensional (1-D) and three-dimensional (3-D) TEM signals as well as field datasets. The field data from a fixed loop survey using multiple receivers are greatly improved after de-noising by the LSTM-autoencoder, resulting in more consistent inversion models with significantly increased exploration depth. The LSTM-autoencoder is capable of enhancing the quality of the TEM signals at later times, which enables us to better resolve deeper electrical structures.

中文翻译：

---

基于长时记忆自动编码器的瞬态电磁数据降噪

后期瞬变电磁（TEM）数据包含深层的地下信息，对于解析深层的电气结构非常重要。但是，由于它们的信号幅度相对较小，因此时间上较晚的TEM响应通常受环境噪声的影响。因此，噪声消除对于在深层成像电子结构中应用TEM数据至关重要。近年来，用于TEM数据的去噪技术发展迅速。尽管已经为改善TEM响应的质量做出了巨大的努力，但是由于不可预测的不规则噪声，有效地提取信号仍然是一个挑战。在这项研究中，我们通过将长短期记忆（LSTM）网络与自动编码器结构相结合来开发新型的神经网络架构，以抑制TEM信号中的噪声。最终的LSTM自动编码器在合成数据集上表现出出色的性能，该合成数据集包括由偶极子，环路和接地线源等不同源产生的电场的水平分量和磁场的垂直分量。对于大多数采样点，去噪数据集和相应的无噪声瞬态之间的相对误差低于1％。与几种广泛使用的神经网络相比，使用由LSTM自动编码器消噪的TEM数据可实现电阻率结构反演结果的显着改善，特别是对于对约束更深结构至关重要的后期到达信号。我们通过使用合成的一维（1-D）和三维（3-D）TEM信号以及现场数据集进行的去噪实验，证明了LSTM自动编码器的有效性和普遍适用性。通过LSTM自动编码器进行除噪后，使用多个接收器进行的固定环路勘测的现场数据得到了极大的改善，从而产生了更加一致的反演模型，并大大增加了勘探深度。LSTM自动编码器能够在以后的时间提高TEM信号的质量，这使我们能够更好地解析更深的电气结构。