Seismic deconvolution is essential for extracting layer information from noisy seismic data, but it is an ill-posed problem with nonunique solutions. Inspired by classical optimization approaches, model-based deep learning architectures, such as loop unrolling (LU) methods, unfold the optimization process into iterative steps and learn gradient updates from data. These architectures rely on well-defined forward models, but in real seismic deconvolution scenarios, these models are often inaccurate or unknown. Previous approaches have addressed model uncertainty by training robust networks, either passively or actively. However, these methods require a large number of adversarial examples and diverse data structures, often necessitating retraining for unseen forward model structures, which is resource-intensive. In contrast, we propose a more efficient test-time adaptation (TTA) method for the LU architecture, which refines the forward model during inference. This approach incorporates physical principles into the reconstruction process, enabling higher quality results without the need for costly retraining. The code is available at:https://github.com/InvProbs/A-adaptive-seis-deconv

Future oil and gas exploration technology ought to be more modular, versatile, adaptable, scalable, and automated. However, a seismic survey generates massive amounts of data on a daily basis. Nevertheless, seismic data transmission via resource-constraint wireless medium remains a major challenge. Hence, a low-profile acquisition method is essential for both the geophone and the fusion center. This approach is required to minimize data congestion at the fusion center and alleviate storage demands. Seismic datasets are typically acquired in 32-bit floating point precision; however, after processing, the sparse reflectivity series is recovered with the objective to enhance the resolution. Hence, fine-scale quantization may be unnecessary, and a coarser scale with fewer bits might suffice. For this purpose, the study employs a segment-based deep neural network (DNN) coupled with low-bit uniform quantization to recover reflectivity, thereby effectively reducing the amount of seismic data collected in the field. The proposed technique has the potential of off-line DNN training, allowing it to be implemented in real-time. Since it does not rely on presuming the inherent statistical properties of noise or the seismic signal, the approach presented proves advantageous for a broad spectrum of seismic data. This approach, unlike other transform-domain methods, operates in time-domain, making it ideal for quickly diagnosing traces in fusion centers for quality. Finally, significant reconstruction gains is demonstrated when comparing the proposed method to the existing state-of-the-art method. Particularly, the proposed setup has the capability to reduce the 32-bits (4.3 billion levels) to 8-bits (256 levels) quantization while maintaining a normalized correlation metric of ~0.96.

This research presents a comprehensive investigation into subjective video shakiness assessment. A collection of 30 shaky videos was gathered, covering relevant categories such as climbing, driving, large parallax, rotation, running, and walking, with different scenes and levels of shakiness. A pairwise comparison (PWC) was conducted, involving human observers who evaluated the perceived quality of shaky videos, and the results have been converted into quality scores using the Just-Objectionable-Differences (JOD) scaling method. The shakiness assessment framework was proved effective by correlations between objective metrics and subjective judgments, and it can serve as a benchmark for future advancements in the field, fostering improvements in video stabilization technologies and applications. The complete dataset is made publicly available through the following link:Shakiness-QuAD

For large-scale seismic exploration in areas that lack even basic infrastructure, wired geophones are impractical because of the huge effort involved and their high deployment and operating costs. A network of wireless geophones capable of recording and transmitting data could be an inexpensive solution. However, a typical seismic survey can generate hundreds of terabytes of raw seismic data per day. It takes a huge amount of energy to transmit this massive amount of data from geophones to the on-site data collection center, thus making the transformation from pre-wired to wireless geophones a significant challenge. To reduce data traffic to the data center without putting additional strain on the geophone, a standalone and lightweight compressive sensing (CS) method is proposed in this work. The method takes advantage of the inherent sparsity in the seismic data to enable the geophone to sense data in a compressed manner. This significantly reduces the amount of data that needs to be recorded/transmitted by the geophone, making it energy efficient. However, instead of employing conventional optimization-based CS reconstruction methods, we propose an efficient implementation of a deep convolutional neural network (DCNN). This network processes the compressed data received at the collection center without any a priori assumptions about the underlying seismic signal statistics, making it appropriate for a wide range of seismic data. The use of CS for energy-efficient sensing and transmission combined with powerful DCNN for reconstruction yields a system that could achieve signal-to-noise ratio (SNR) of around 30 dB with a compression gain of 16 on a field data set. Finally, when compared with other methods, the proposed approach demonstrates significant superiority in maximizing compression gain and reconstruction quality for both synthetic and real field data sets.

Noise attenuation is a crucial phase in seismic signal processing. Enhancing the signal-to-noise ratio (SNR) of registered seismic signals improves subsequent processing and, eventually, data analysis and interpretation. In this work, a novel noise reduction framework based on an intelligent deep convolutional neural network is proposed that works on segments of the time-frequency domain and, hence named as DeepSeg. The proposed network is efficient in learning sparse representation of the data simultaneously in the time-frequency domain and adaptively capturing seismic signals corrupted with noise. DeepSeg is able to achieve impressive denoising performance even when seismic signal shares common frequency band with noise. The proposed approach properly tackles a variety of correlated (color) and uncorrelated noise, and other nonseismic signals. DeepSeg can boost the SNR considerably even in extremely noisy environments with minimal changes to the signal of interest. The effectiveness of the proposed methodology is demonstrated in enhancing passive seismic event detection/denoising. However, there are other obvious applications of the DeepSeg in active and passive seismic fields, e.g., seismic imaging, preprocessing of ambient noise data, and microseismic event monitoring. It is worth pointing out here that the deep neural network is trained exclusively using synthetic seismic data, negating the need for real data during the training phase. Furthermore, the proposed setup is general and its potential applications are not confined to passive event denoising or even seismic. The method proposed is also adaptable to other diverse signals in different settings, like medical images/signals [magnetic resonance imaging (MRI), electroencephalogram (EEG) signals, electrocardiograms (ECG) signals, and retinal images, to name a few], radar signals, speech signals, fault detection in electrical/mechanical systems, daily life images, etc. Experiments on synthetic and real seismic data reveal the efficacy and supremacy of the proposed method in terms of SNR improvement and required training data when compared to the state-of-the-art deep neural network-based denoising technique.

There has been a recent rise in the uses and applications of passive seismic data, such as tomographic imaging, volcanic monitoring, and hydrocarbon exploration. Consequently, the sharp increase in passive seismic applications requires real-time event detection capabilities with high accuracy. Proper analysis of such events depends largely on the signal-to-noise ratio improvement through noise suppression techniques. Recent advances in the fields of signal processing and deep learning coupled with the available computational resources provide a great opportunity to address this challenge. In this work, a workflow is proposed where a residual deep neural network is customized and employed to detect passive seismic events. The automated detection is followed by a denoising step to extract the signal of interest from background noise using an IIR Wiener filter. The proposed method does not require any prior knowledge of the signal/noise, and therefore, it can work with various types of signals/noises. Another benefit of the proposed detection method is that the deep neural network is trained only on synthetic seismic data without the need to use real data in the training process. Nevertheless, it exhibits high accuracy in detecting and denoising events from real passive seismic data sets. In particular, field seismic data is recorded in northern Saudi Arabia and used to test the complete detection and denoising method. The detection method proved its capability of detecting events automatically in large data sets and in real time (due to off-line training).

In this paper, we introduce a novel approach for 2D blind multichannel identification using the helix transform in conjunction with the Cross Relation (CR) method. The helix transform is used to convert the 2D convolution of image and channels into 1D convolution. The CR method, known for its simplicity, efficiency and low computational cost, is then adapted and used to estimate the unknown channel coefficients. A main advantage of the proposed approach resides in its ability to help extending the plethora of methods from 1D to 2D blind system identification and ease their implementations.

In this paper, a robust iterative block decision feedback equalization (DFE) algorithm is developed for uplink single-carrier frequency division multiple access (SC-FDMA) systems. Three important problems that can adversely affect the performance of the DFE in SC-FDMA systems are to be addressed here, i.e., the feedback symbols reliability, the feedback correlation metric, and the phase noise due to inaccuracies in the fabrication process of the crystal oscillator. Instead of using all the detected symbols in the feedback loop of the DFE, only the highly reliable symbols are selected to be fed back. This results in the improvement of the error propagation, one of the common problems in a DFE. Also, the feedback correlation is an important metric in the design of the DFE, and hence an elegant method is proposed in this design and found to perform better than the available existing designs in the literature. Finally, the transmitter and receiver phase noise is iteratively compensated using its corresponding time- and frequency-domain properties. Simulation results demonstrate the robustness of our designed iterative block DFE.

In this work, a variable step-size (VSS) blind equalization algorithm is presented for a multimodulus blind equalization scheme. The parameters of the proposed algorithm are selected using a particle swarm optimization strategy. Eventually, the best parameters for the proposed VSS blind equalization algorithm are obtained and better performance is obtained when compared to the trial-and-error method for choosing these parameters. Ultimately, a considerable reduction in computational complexity when compared to the fixed-step algorithm with extra constraints. Simulation results support this new proposed technique.

Traditional seismic data acquisition systems used for surveying during the exploration of oil and gas rely on cables between geophones and data collection center. Despite the fact that cable-based systems provide reliable seismic data transfer, their deployment and maintenance costs increase substantially as the survey area increases in scale. This paper investigates the aggregate data throughput and transmission time from wireless geophones to gateway node in a wireless geophone network architecture based on IEEE802.11af standard. The analytical expressions of throughput and transmission time are derived using Markov chain models. Two Markov models are considered for this purpose: one for modeling carrier sense multiple access method with collision avoidance (CSMA/CA) behavior and the other for representing a buffer in a wireless geophone. Furthermore, the physical layer path-loss models are taken into account.