TEM data completion method based on DCGAN model

Abstract

In the transient electromagnetic method (TEM) exploration, due to the complex acquisition environment, the original data has serious interference, and the entire data segment and the entire point are missing. During data processing, the missing and cut-off data due to interference are difficult to complete based on reliable geophysical models. In response to this problem, this paper establishes a deep convolutional generative countermeasure network model (DCGAN) for TEM data completion based on the generative countermeasure network (GAN). The model uses GAN network as the framework, embedding deep convolutional neural network modules, that is, using deep deconvolution and convolution layers to replace the fully connected layer in the GAN model to fully extract the spatial features of TEM data. In order to test the performance of the model, the test set is divided into two categories: random missing and overall missing. On this basis, increase the number of deleted data, control the missing rate in the test data set to 10%, 20%, 30%, 40%, and 50%, and gradually carry out the test. Finally, the test results are compared with the current mainstream data completion method GAN. The results show that the overall effect of the DCGAN model in TEM data completion is higher than that of GAN. At the same time, when the randomly missing data is less than or equal to 40% and the continuous missing data is less than or equal to 30%, the R2 of the DCGAN model is above 0.85, which can maintain good performance. Through random missing, continuous missing data completion and step-by-step experiments with different missing rates, the model can ensure the accuracy of the completion while clarifying the scope of application, which has certain practical application value.