Data augmentation and its application in distributed acoustic sensing data denoising

Abstract

As a data-driven approach, the performance of deep learning models depends largely on the quantity and quality of the training datasets, which greatly limits the application of deep learning to tasks with small datasets. Unfortunately, sometimes we need to use limited small datasets to complete our tasks, such as DAS data denoising. However, using a small dataset to train the network may cause over-fitting, resulting in poor network generalization. To solve this problem, we propose an approach based on the combination of a generative adversarial network and a deep convolutional neural network. First, we used a small noise dataset to train a generative adversarial network to generate synthetic noise samples, and then used these synthetic noise samples to augment the noise dataset. Next, we used the augmented noise dataset and the signal dataset obtained through forward modeling to construct a synthetic training set. Finally, a denoising network based on a convolutional neural network was trained on the constructed synthetic training set. Experimental results show that the augmented dataset can effectively improve the denoising performance and generalization ability of the network, and the denoising network trained on the augmented dataset can more effectively reduce various kinds of noise in the DAS data.