Deep learning on image denoising: An overview.

Seismic velocity is one of the most important parameters used in seismic exploration. Accurate velocity models are the key prerequisites for reverse time migration and other high-resolution...

Deep-learning inversion: A next-generation seismic velocity model building method

Terahertz (THz) science and technology have greatly progressed over the past two decades to a point where the THz region of the electromagnetic spectrum is now a mature research area with many fundamental and practical applications. Furthermore, THz imaging is positioned to play a key role in many industrial applications, as THz technology is steadily shifting from university-grade instrumentation to commercial systems. In this context, the objective of this review is to discuss recent advances in THz imaging with an emphasis on the modalities that could enable real-time high-resolution imaging. To this end, we first discuss several key imaging modalities developed over the years: THz transmission, reflection, and conductivity imaging; THz pulsed imaging; THz computed tomography; and THz near-field imaging. Then, we discuss several enabling technologies for real-time THz imaging within the time-domain spectroscopy paradigm: fast optical delay lines, photoconductive antenna arrays, and electro-optic sampling with cameras. Next, we discuss the advances in THz cameras, particularly THz thermal cameras and THz field-effect transistor cameras. Finally, we overview the most recent techniques that enable fast THz imaging with single-pixel detectors: mechanical beam-steering, compressive sensing, spectral encoding, and fast Fourier optics. We believe that this critical and comprehensive review of enabling hardware, instrumentation, algorithms, and potential applications in real-time high-resolution THz imaging can serve a diverse community of fundamental and applied scientists.

Toward real-time terahertz imaging

Compared with traditional seismic noise attenuation algorithms that depend on signal models and their corresponding prior assumptions, removing noise with a deep neural network is trained b...

Deep learning for denoising

https://www.it.uu.se/katalog/praba420/LIKES.pdf

SPICE and LIKES: Two hyperparameter-free methods for sparse-parameter estimation

Recently deep learning (DL), as a new data-driven technique compared to conventional approaches, has attracted increasing attention in geophysical community, resulting in many opportunities and challenges. DL was proven to have the potential to predict complex system states accurately and relieve the “curse of dimensionality” in large temporal and spatial geophysical applications. We address the basic concepts, state-of-the-art literature, and future trends by reviewing DL approaches in various geosciences scenarios. Exploration geophysics, earthquakes, and remote sensing are the main focuses. More applications, including Earth structure, water resources, atmospheric science, and space science, are also reviewed. Additionally, the difficulties of applying DL in the geophysical community are discussed. The trends of DL in geophysics in recent years are analyzed. Several promising directions are provided for future research involving DL in geophysics, such as unsupervised learning, transfer learning, multimodal DL, federated learning, uncertainty estimation, and active learning. A coding tutorial and a summary of tips for rapidly exploring DL are presented for beginners and interested readers of geophysics.

https://agupubs.onlinelibrary.wiley.com/doi/pdf/10.1029/2021RG000742

Deep learning for geophysics: Current and future trends

Sparse transforms play an important role in seismic signal processing steps, such as prestack noise attenuation and data reconstruction. Analytic sparse transforms (so-called implicit dictionaries), such as the Fourier, Radon, and curvelet transforms, are often used to represent seismic data. There are situations, however, in which the complexity of the data requires adaptive sparse transform methods, whose basis functions are determined via learning methods. We studied an application of the data-driven tight frame (DDTF) method to noise suppression and interpolation of high-dimensional seismic data. Rather than choosing a model beforehand (for example, a family of lines, parabolas, or curvelets) to fit the data, the DDTF derives the model from the data itself in an optimum manner. The process of estimating the basis function from the data can be summarized as follows: First, the input data are divided into small blocks to form training sets. Then, the DDTF algorithm is applied on the training set...

Interpolation and denoising of high-dimensional seismic data by learning a tight frame

Seismic data denoising and interpolation are essential preprocessing steps in any seismic data processing chain. Sparse transforms with a fixed basis are often used in these two steps. Recently, we have developed an adaptive learning method, the data-driven tight frame (DDTF) method, for seismic data denoising and interpolation. With its adaptability to seismic data, the DDTF method achieves high-quality recovery. For 2D seismic data, the DDTF method is much more efficient than traditional dictionary learning methods. But for 3D or 5D seismic data, the DDTF method results in a high computational expense. The motivation behind this work is to accelerate the filter bank training process in DDTF, while doing less damage to the recovery quality. The most frequently used method involves only a randomly selective subset of the training set. However, this random selection method uses no prior information of the data. We have designed a new patch selection method for DDTF seismic data recovery. We suppose...

Monte Carlo data-driven tight frame for seismic data recovery

We have introduced a new decomposition method for seismic data, termed complex variational mode decomposition (VMD), and we have also designed a new filtering technique for random noise attenuation in seismic data by applying the VMD on constant-frequency slices in the frequency–offset ( $f$ – $x$ ) domain. The motivation behind this paper is to overcome the potential low performance of empirical mode decomposition (EMD) for energy preservation of the steeply dipping events when used for noise attenuation, and low resolution when used for signal decomposition. The VMD is proposed to decompose a signal into an ensemble of band-limited modes. For seismic data consisting of linear events, the constant-frequency slices of its $f$ – $x$ spectrum are exactly band-limited. The noise attenuation algorithm is summarized as follows. First, the Fourier transform is applied on the time axis of the 2-D seismic data. Next, the VMD is applied on each frequency slice of the $f$ – $x$ spectrum and the decomposed modes are combined to obtain the filtered frequency slice. Finally, an inverse Fourier transform is applied on the frequency axis of the $f$ – $x$ spectrum to obtain the denoised result. The resulting VMD-based noise attenuation method is equivalent to applying a Wiener filter on each decomposed mode, which is achieved during the decomposition progress. We also applied 2-D VMD on 3-D seismic data for denoising. Numerical results show that the proposed VMD-based method achieves a higher denoising quality than both the $f$ – $x$ deconvolution method and the EMD-based denoising method, especially for preserving the steep slopes.

Siwei Yu

Papers

Deep learning for denoising

Deep learning for geophysics: Current and future trends

Interpolation and denoising of high-dimensional seismic data by learning a tight frame

Monte Carlo data-driven tight frame for seismic data recovery

Complex Variational Mode Decomposition for Slop-Preserving Denoising