Similarity-Informed Self-Learning and Its Application on Seismic Image Denoising

Seismic image denoising is essential to enhance the signal-to-noise ratio (SNR) of seismic images and facilitate seismic processing and geological structure interpretation. With the development of deep learning (DL), several DL-based models have been proposed for seismic image denoising. However, the commonly used supervised DL-based denoising models require noise-free data as training labels, yet noise-free data are often difficult to be obtained in field application scenarios. By considering the similarity of seismic images, we propose a similarity-informed self-learning (SISL) to address seismic image denoising in the absence of noise-free seismic images. To accurately preserve valid seismic signals when constructing training pairs, we develop a specialized workflow, termed the similar image sampler. In this way, we can fully use the self-similarity of noisy seismic images to build training pairs and then train a denoising model. Moreover, to effectively attenuate random noise, we propose a hybrid loss function with a regularization constraint to availably retain valid seismic events. After comparing with the traditional denoising methods and several state-of-the-art unsupervised DL models, the experimental results from synthetic and field data quantitatively and qualitatively demonstrate the effectiveness and the stability of the proposed SISL model for seismic image denoising.