Seismic Acquisition Research Articles

Iterative Separation of Blended Seismic Data in Shot Domain Using Deep Learning

Accurate deblending techniques are essential for the successful application of blended seismic acquisition. Deep-learning-based deblending methods typically begin by performing a pseudo-deblending operation on blended data, followed by further processing in either the common-shot domain or a non-common-shot domain. In this study, we propose an iterative deblending framework based on deep learning, which directly addresses the blended data in the shot domain, eliminating the need for pseudo-deblending and domain transformation. This framework is built around a unique architecture, termed WNETR, which derives its name from its W-shaped network structure that combines U-Net and Transformer. During testing, the trained WNETR is incorporated into the iterative framework to extract useful signals iteratively. Tests on synthetic data validate the effectiveness of the proposed deblending iterative framework.

The Aerodynamic Assessment and Shot Point Position Accuracy of UAV Seismic Source

An unmanned aerial vehicle (UAV) seismic source, suitable for complex terrains due to its eco-friendly, cost-effective, and efficient nature, operates by hovering and releasing impact objects to generate seismic waves. The aerodynamic behavior of these impact objects is vital for shotpoint position accuracy and drag magnitude. Excessive drag will result in the loss of seismic source energy, whereas the deviations of the shotpoint position will disrupt the geometric structure of the observation system, significantly impacting the quality of seismic data acquisition. Through theoretical calculations, the influencing factors of air resistance and cross-wind deflection are analyzed. Air resistance increases with the increase in mass, cross-sectional area, speed, and drag coefficient. Increasing the mass and throwing height can increase the upper limit of the output, but after the air resistance and gravity are balanced, the output kinetic energy of the drone’s seismic source will no longer increase when the throwing height is increased. Using computational fluid dynamics simulations and field tests, this study examines the aerodynamics of four prevalent impact object designs. The results show that shuttle and spherical structures have the least drag during descent and are less influenced by crosswinds, thus being optimal for this application. Field measurement data are also presented for reference.

Unsupervised 3D seismic data reconstruction using a weighted-attentive deep-learning framework

The physical and cost limitations of seismic data acquisition often result in the spatial undersampling of data, which has a detrimental impact on subsequent data processing. Seismic data reconstruction plays a crucial role in recovering missing traces arising from the acquisition process. In recent years, deep learning (DL) has emerged as an intelligent solution for this purpose. We introduce an innovative approach called the weighted-attentive DL framework for unsupervised 3D seismic data reconstruction, which combines an attentive transformer network (ATNet) with a conventional projection onto convex sets (POCS) algorithm. Our framework follows the plug-and-play concept, requiring only the original subsampled data to achieve robust performance. It accomplishes this by iteratively updating ATNet parameters, wherein ATNet serves as the reconstruction operator during the DL process. This approach allows us to simultaneously recover missing traces and filter out random noise, with a key feature being its enhanced attention to the observed signal compared with convolutional neural networks. In addition, we incorporate the POCS algorithm into our framework to introduce a linear decay weight for the aliasing space containing noise and signal during the reconstruction process. We rigorously evaluate our method against four existing approaches: adaptive POCS, fast dictionary learning sequential generalized K-means, optimally damped rank-reduction, and DenseNet methods. Our comparative experiments, conducted on synthetic and field data examples, clearly demonstrate the substantial improvements achieved by our method in terms of reconstruction and denoising when compared with the four benchmarked methods.

High-Fidelity OC-Seislet Stacking Method for Low-SNR Seismic Data

Seismic stacking is a core technique in seismic data processing, aimed at enhancing the signal-to-noise ratio (SNR) of data by utilizing seismic data acquisition with multifold geometry. Traditional stacking methods always have certain limitations, such as the reliance on the accuracy of velocity analysis for dip moveout (DMO) in common midpoint (CMP) stacking. The seislet transform, a compression technique tailored to nonstationary seismic data, can compress and stack along the prediction direction of seismic data, which provides a new technical idea for high-fidelity seismic imaging based on the effectiveness of the compression. This paper introduces a high-order OC-seislet stacking method for low-SNR seismic data, capable of achieving the high-fidelity stacking of reflection and diffraction waves simultaneously. With the multi-scale analysis advantages of the seislet transform, this method addresses the dependency of DMO stacking on velocity analysis accuracy. In the frequency–wavenumber–scale domain, the correction compensation of the high-order CDF 9/7 basis function is used to obtain the compression coefficients of the high-order OC-seislet transform. This approach simultaneously stacks frequency–wavenumber information of reflection and diffraction waves with high fidelity while implementing DMO processing. After normalizing the weighting coefficients and applying soft thresholding for denoising, the final result is transformed back to the original time–space domain, yielding high-fidelity stacking sections. The results of applying this method to both synthetic and field data show that, compared with conventional DMO stacking methods, the high-order OC-seislet stacking technique reasonably represents dipping layers and fault amplitudes, and it can achieve a balance of a high SNR and high fidelity in stacked profiles.

Design and Application of Real‐Time and High‐Precision Seismic Acquisition Station in Antarctic Region

ABSTRACTIn this study, a polar seismic acquisition station based on the FPGA + ARM architecture was successfully developed. This system can achieve real‐time multifunctional acquisition and transmission of seismic signals and environmental information in the extreme low‐temperature environment of Antarctica at −40°C. The system adopts a modular design, with high‐precision data acquisition encoded by the main controller and uploaded to the host computer in real‐time. Integrated display controls enable real‐time data display and acquisition station location mapping for user interaction. We propose improving data transmission in traditional seismic acquisition stations by adopting a distributed computing model with data segment return. Integrating the first arrival picking algorithm as an IP core will reduce computational demands on the data processing center. This acquisition system features high precision (24‐bit), a wide dynamic range (> 130dB), low noise (0.5 V rms@40dB), and high‐precision timing control (200 ns). It supports real‐time wireless data transmission over 120 channels up to 1 km. The system also implements a self‐storage plus wired and wireless networking solution, allowing flexible networking based on actual needs. Test results indicate that the ice sheet thickness at the acquisition site is approximately 526.49 m, validating the experimental design's effectiveness and providing technical support for subsequent drilling and seismic exploration.

High dynamic range land wavefield reconstruction from randomized acquisition

Compressive sensing (CS) is an alternative to regular Shannon sampling that captures similar information from reduced measurements. It relies on randomized sampling patterns and a sparse data representation to reconstruct the regularly sampled object. CS is an important ingredient in affordable seismic acquisition, which can lead to improvements in the near-surface mapping and noise suppression for land data. However, the near surface traps most of the source-generated energy, resulting in data that are rich in high-wavenumber content and have amplitudes spanning several orders of magnitude. When dealing with such high dynamic range nonstationary data, the Fourier domain is not optimal for providing a sparse representation — a necessary condition for successful application of CS. In contrast, a discrete complex wavelet transform can localize high-energy features, has good directional selectivity, and is near-shift invariant. Combined, these properties allow complex wavelets to represent detail-rich wavefields in a compact form. To leverage these features and achieve good CS reconstructions, we develop a scale- and orientation-dependent iterative soft thresholding (IST) scheme for reconstructing high dynamic range wavefields. Our approach requires little parameterization, is easy to implement, and is robust to reconstructed wavefield sampling grid and dynamic range. We test IST on different wavefields with randomly missing traces and compare the data reconstructions with the spectral projected gradient solver and projection onto convex sets. We quantify the reconstructions by a direct comparison of Fourier coefficients between fully sampled and reconstructed wavefields. Taking log10 of Fourier coefficients prior to computing the quality metric deemphasizes the importance of magnitude match while highlighting Fourier coefficient support accuracy, which usually translates into good structural fidelity of reconstructed data. We find that IST performs consistently among all examples, yielding good phase match while performing gentle denoising.

NeRSI: Neural Implicit Representations for 5D Seismic Data Interpolation

Due to challenging field operations and resource constraints, seismic data acquisition often requires coping with missing traces. Interpolation algorithms are crucial for reconstructing these missing traces to enable improved subsurface analysis and interpretation. While deep learning has made exciting advances in seismic reconstruction, its focus has predominantly been on 2D and 3D datasets with relatively low rates of missing data. Five-dimensional (5D) seismic data reconstruction entails considering simultaneous sources and receivers deployed in areal arrays to solve the reconstruction problem. The latter offers greater data redundancy, which can be leveraged to enhance interpolation quality. Traditional 5D deep learning interpolation methods rely heavily on synthetic training pairs, posing challenges when applied to real-world data. This necessitates transfer learning techniques, which can be cumbersome. Addressing this, we introduce a self-supervised, coordinate-based deep interpolation algorithm that obviates the need for labeled data. Employing a multi-layer perceptron (MLP) network can effectively encode the continuous seismic wavefield inherent in 5D data. Once trained, the MLP can infer missing trace amplitudes from their coordinates. We contribute to boosting the MLP, enabling it to generate seismic profiles rather than single-point predictions. This enhancement significantly strengthens the model’s performance and efficiency. Moreover, we apply nuclear norm regularization to the output profiles, improving the reconstruction quality. The effectiveness of our algorithm is supported by both synthetic and field data experiments, demonstrating its superior reconstruction capabilities.

Application of Seismic Attribute Clustering Method Based on PCA-SOM in Identification of Paleochannels

Abstract Paleochannels are crucial reservoir types in continental oil and gas fields. The P oil layer in the Sanzhao Depression of the Songliao Basin is a typical example of river-controlled delta-phase deposition. The underwater diversion channel is highly developed and serves as the primary unit of the oil and gas reservoir. The stacking of the river channel creates a complex relationship. Identifying river channels has always been a challenging aspect of predicting sweet spot reservoirs due to the thinness of the sand, fault cutting, seismic acquisition and processing noise, low-resolution constraints, and other factors. This paper proposes a method for identifying river channels by combining principal component analysis (PCA) and self-organised mapping network (SOM) with seismic attribute clustering. The aim is to address the issue of difficult identification of paleochannels. The seismic attribute set, which contains multiple types of attributes, is first dimensionality reduced using principal component analysis. Then, a few principal components that can characterise the attribute set are extracted and used as inputs to the self-organising map (SOM). This reduces the dimensionality of the training sample set and simplifies the network structure. The self-organising neural network structure is designed based on the input sample features. Training is then carried out, and the network weights are updated. Attribute clustering is performed to obtain the river identification results. The effectiveness of this method for paleochannel recognition is verified by the clear morphology of the recognised paleochannels in the Songliao Basin, their conformity to geological understanding, and their matching with drilling information.

Prestack reservoir prediction method in ray parameter domain based on wide azimuth ocean bottom node seismic data

AbstractWide azimuth seismic data play an important role in deep reservoir prediction. According to the Paleogene clastic rock reservoir prediction, the high‐density and wide azimuth 3D seismic data acquisition of ocean bottom nodes was first carried out in a Chinese offshore oilfield in 2019. After high precision amplitude‐preserving processing, we obtained the high‐quality wide azimuth gathers. However, the research on anisotropy and reservoir prediction using wide azimuth seismic data mainly focuses on carbonate and bedrock intervals, which is not suitable for clastic rock reservoir prediction. Therefore, this paper innovatively proposes a clastic rock reservoir prediction method, which studies prestack reservoir prediction in the ray parameter domain based on wide azimuth ocean bottom node seismic data. Based on the azimuth gathers, we can obtain elastic parameters through prestack amplitude versus offset inversion, which is used to characterize the reservoir, so it is significant to obtain high precision elastic parameters in order to get highly reliable reservoir prediction results. In this paper, we develop an amplitude versus offset inversion method based on the Bayesian theory in ray parameter domain, the output of which is density, P‐wave impedance and Vp/Vs. These elastic parameters have high precision, and density data are valuable input for reservoir characterization because they are sensitive to the lithology of clastic rock reservoir at different orientations. In ray parameter domain inversion, the ray path of seismic wave propagation is considered polyline, which is more consistent with the actual situation; thus, extracted amplitudes of P gathers used in inversion are more accurate. In addition, the reflection coefficient formula in ray parameter domain has higher precision when the incident angle is large. The inversion based on the Bayesian theory can improve the stability of the inversion. Test on the actual data shows that the result of ray parameter domain inversion with a Bayesian scheme is more accurate, stable and reliable. Based on the above high precision density inversion results, an innovative wide azimuth data reservoir prediction technology based on elliptical short‐axis fitting was proposed. The actual prediction of the deep reservoir in the Bohai oilfield shows that sand thickness fitting prediction results in the short axis can best match the actual drilling sandstone thickness. The coincidence rate is 86% and the short‐axis fitting results are more in agreement with geological laws. Theoretical research and practical applications have shown that this method is feasible and effective, with high prediction accuracy, computational efficiency and strong application value.

Research on the Application of CEEMD and CEEMDAN in Seismic Random Noise Suppression

Empirical Mode Decomposition (EMD) is an adaptive method for processing nonlinear and non-stationary data. Complementary Ensemble Empirical Mode Decomposition (CEEMD) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) are noise-assisted signal processing methods developed from EMD. During seismic data acquisition, various types of noise, including random noise, are inevitably captured, and current methods for dealing with such noise are limited. In this study, these two signal processing methods were applied in simulated experiments and real seismic data to suppress random noise. By analyzing the processing effects and runtime, it was found that CEEMDAN offers better processing performance and speed, making it a valuable tool for practical applications.

Benefits of Integrating Seismic and Gravity Data in a Subsalt Environment. A Case Study at Block BM-C-33, Deepwater Campos Basin, offshore Brazil

Imaging subsalt layers is challenging in the BM-C-33 block in the Campos Basin's ultradeep waters. This block is important as it has three significant gas and condensate discoveries in the pre-salt carbonate and volcanic reservoirs -- Seat, G൥a, and P⭠de A洣ar. Understanding basement morphology is essential to better define the petroleum system in the area. To that end, we performed a 2D gravity modeling exercise along a northwest-southeast section, using seismic interpretation as input to reduce the ambiguity of the modeling exercise. To achieve this, we fixed the main sedimentary horizons and their densities (calculated via well-log information) to better estimate the top of the basement morphology. This interpretation strategy better delineated the pre-salt sedimentary section and the complex structural framework with two asymmetric grabens bounded by a prominent horst, interpreted as a migration focusing high in the BM-C-33 area. In addition, our findings show that obtaining clear images remains challenging even after extensive processing of the seismic data set. We suggest that seismic node acquisition with ultra-long offsets and multi-azimuthal illumination and then carefully processing the data is required to accurately reveal the area's pre-rift section and basement morphology under study.

Compensating Acquisition Footprint for Amplitude-Preserving Angle Domain Common Image Gathers Based on 3D Reverse Time Migration

Angle domain common image gathers (ADCIGs) play a crucial role in seismic exploration, offering prestack underground illumination information that aids in validating migration velocity and conducting prestack amplitude versus angle (AVA) analysis for reservoir characterization. This paper introduces an innovative approach for compensating amplitude errors caused by irregular seismic acquisition geometries in ADCIGs. By incorporating an angle domain illumination compensation factor, the proposed method effectively modifies these errors, preserving the amplitude of seismic reflectivity in the prestack angle domain. The effectiveness of the proposed approach is validated through comprehensive tests conducted on synthetic and field data examples. The results demonstrate the capability of the method to enhance the quality of ADCIGs derived from 3D reverse time migration (RTM), yielding accurate and reliable amplitude preservation. While the illumination compensation factor assumes a vertically linear velocity model, the method holds promise for extension to more complex media and diverse migration techniques. This suggests its applicability and adaptability beyond the specific assumptions considered in this study. In conclusion, this paper presents an innovative angle domain illumination compensation factor that significantly improves the quality of ADCIGs by addressing amplitude errors arising from irregular seismic acquisition geometries. The experimental validation using synthetic and field data confirms the effectiveness of the proposed method within the context of 3D RTM. Furthermore, the technique holds potential for broader application in more complex subsurface scenarios and various migration methodologies.

Feasibility Study and Results from a Baseline Multi-Tool Active Seismic Acquisition for CO2 Monitoring at the Hellisheiði Geothermal Field

CO2 capture and underground storage, combined with geothermal resource exploitation, are vital for future sustainable and renewable energy. The SUCCEED project explores the feasibility of re-injecting CO2 into geothermal fields to enhance production and store CO2 for climate change mitigation. This integration requires novel time-lapse monitoring approaches. At the Hellisheiði geothermal power plant in Iceland, seismic surveys utilizing conventional geophones and a permanent fiber-optic helically wound cable (HWC) for Distributed Acoustic Sensing (DAS) were designed to provide subsurface information and CO2 monitoring. This work details the feasibility study and active seismic acquisition of the baseline survey, focusing on optical fiber sensitivity, seismic modeling, acquisition parameters, source configurations, and quality control. Post-acquisition signal analysis using a novel electromagnetic vibrating source is discussed. The integrated analysis of datasets from co-located sensors improved quality-control performance and geophysical interpretation. The study demonstrates the advantages of using densely sampled DAS data in space by multichannel processing. This experimental work highlights the feasibility of using HWC DAS cables in active surface seismic surveys with an environmentally friendly electromagnetic source, providing also a unique case of joint signal analysis from different types of sensors in high-temperature geothermal areas for energy and CO2 storage monitoring in a time-lapse perspective.

Rejuvenating exploration opportunities in Egypt's Mediterranean region using basin-scale 3D seismic reprocessing and subsurface evaluations

The Eastern Mediterranean region has proven to be a key province for natural gas resources over the last two decades. Gas discoveries in the Nile Delta Basin, Levantine Basin, and over the Eratosthenes platform have proven that an efficient working petroleum system extends to the deepwater areas and into the distal parts of the Nile Delta and Levantine basins. While the suprasalt biogenic post-Messinian play is adequately imaged in various areas in the Eastern Mediterranean region, seismic imaging of the deeper subsalt pre-Messinian plays is challenged by legacy seismic acquisition and processing techniques. Moreover, the complexity of the Messinian salt structures and the heterogeneity of the lithology of the Messinian layer across the Mediterranean basins represent a key subsurface challenge. In phase 1 of the study presented in this paper, we reprocessed 12 legacy 3D seismic data sets over 12,000 km2 and constructed a consistent basin-scale earth model from the shelf areas offshore Sinai to the deepwater areas around the Zohr carbonate platform. The data processing and imaging sequences incorporate full-waveform inversion and tomography in the earth model building process followed by a basin-to-lead evaluation to delineate exploration opportunities in phase 1. The evaluations resulted in delineating Cretaceous and Oligo-Miocene untested structures. Furthermore, potential deepwater Lower Miocene sand fairways were outlined, supported by improved regional seismic imaging and consistent seismic attributes over multiple legacy surveys. The authors of this paper expect to update the results of their work after completing the earth model building and the prestack depth migration workflows of an additional 13 legacy surveys over 35,000 km2 in phase 2 of the study.

Innovative solutions to frontier exploration in Eastern Mediterranean salt basins

The Eastern Mediterranean region is expected to hold large undiscovered natural gas resources that could address critical energy supply needs of the surrounding countries. However, exploration is challenged due to regional geologic complexities. The combination of Messinian salt structures and diapiric shales in offshore Cyprus and Egypt often causes strong attenuation of seismic energy and severe seismic imaging illumination shadows, which lead to large uncertainty regarding subsalt reservoir presence and the underlying petroleum system assessment. As part of the efforts to solve these imaging challenges, we present innovative seismic acquisition solutions to address key exploration risks such as reservoir presence. A one-sided wide-azimuth configuration consisting of one streamer vessel and one dedicated source vessel operating under the simultaneous-source mode was used to acquire data in a cost-effective way. An 8000 in3 low-frequency source was used on both vessels to provide higher energy output in the low-frequency bands of less than approximately 4 Hz. Our preliminary results show evidence of seismic image uplift due to enhanced acquisition and processing, leading to greater confidence in interpretation, which is critical for positioning wells in future drilling campaigns. This paper highlights seismic testing results undertaken to design a large exploration-scale seismic survey in the Eastern Mediterranean and early results from the execution of that program. This will help better refine optimal design criteria for future acquisition, signal processing, and imaging in order to unlock additional resources beneath complex salt provinces and identify where additional imaging needs still exist.

GPU accelerated sparse curvelet-constrained wavefield reconstruction inversion with source estimation: Application to Chevron Benchmark 2014 blind test data set

Full-waveform inversion (FWI) is a pivotal tool in seismic exploration and seismology but encounters a persistent challenge known as “cycle-skipping,” causing it to frequently converge to local minima. Wavefield reconstruction inversion (WRI) has emerged as a potential solution to mitigate the risk of cycle skipping. Researchers have provided numerical examples indicating that WRI is less prone to being ensnared in local minima caused by the absence of low-frequency component data and the absence of a well-defined initial model compared with conventional FWI. Despite its potential, the computational demands of WRI have hindered its widespread application, especially in scenarios involving ocean towed streamer seismic acquisition and unknown sources, where the augmented systems differ from source to source. In our study, we introduce a novel approach — sparse curvelet-constrained WRI with source estimation (WRI-SE-CC) — accelerated by graphics processing unit (GPU). Real-time source function estimation is achieved through the variable projection method, and noise-related artifacts are suppressed using sparse curvelet constraints. By optimizing the utilization of hundreds of computation processors within a GPU for parallel computing of matrix-vector multiplications, we present a GPU-based grouped conjugate gradient method to accelerate the computation of WRI-SE-CC. Numerical experiments demonstrate a significant 240-fold acceleration compared with the preconditioned conjugate gradient using one CPU core for computations involving multiple sources. Inversion experiments with the overthrust model demonstrate the capability of our method in mitigating local minima and suppressing noise-related artifacts. Furthermore, we validate the framework on the Chevron 2014 blind test data set, showcasing its effectiveness in addressing practical challenges in the field.

On-demand high-resolution areal scouting via unmanned aerial vehicles enables sustainable near-surface geoscience data acquisition

An accurate data acquisition plan is critical for near-surface geoscience investigations. Detailed understanding of the terrain and land cover of the survey area is essential to designing a data acquisition layout that efficiently meets the objective while mapping potential obstacles. Using satellite-based data is the most affordable and straightforward method to obtain this information. However, near-surface geoscience investigations demand a higher-resolution map than commonly available satellite imagery to design a detailed acquisition plan. This paper presents a concept that utilizes unmanned aerial vehicles (UAVs) to successfully and sustainably perform on-demand high-resolution areal scouting to aid near-surface geoscience data acquisition campaigns and seismic drone deployment. We share the results of two field trial cases where the presented concept was evaluated. Case A is a 16 km2 extensive outcrop investigation in an arid desert environment. The initial satellite-based acquisition plan was changed considerably when UAV data sets became available. This led to an approximately 60% improvement in data productivity and efficiency, effectively reducing the carbon footprint of conventional scouting operations. Case B utilizes high-resolution areal scouting to determine the safe landing zone for autonomous seismic drone swarms to further support sustainable geophysical data acquisition. The UAV data enable seismic drone swarms to land optimally on preprogrammed landing points while navigating subsatellite-resolution obstacles. These two successful cases suggest that analogous productivity and efficiency improvements may be achieved in industrial-scale land seismic data acquisition planning that utilizes the UAV data set.

Offset VSP acquired with a single-use fiber-optic probe: Gorgon CCS case study

There are many challenges associated with monitoring industrial subsurface CO2 storage. Utilizing a reliable strategy for monitoring and assurance is paramount. Numerous aspects and trade-offs need to be considered when designing a cost-effective monitoring solution that must satisfy regulatory and social licensing requirements and minimize operational complexity. Among various geophysical techniques that are included in the suite of carbon capture and storage (CCS) monitoring programs, seismic surveys provide reliable observations of the deep subsurface. However, active surface seismic techniques are expensive, resulting in significant time separation between surveys (several months or years). Downhole seismic approaches combined with fiber-optic sensing provide flexible options in designing on-demand monitoring strategies. Distributed acoustic sensing offers the opportunity to utilize injection wells for downhole time-lapse seismic imaging and microseismic detection, minimizing the impact on production operations. This paper presents the results of a multioffset vertical seismic profiling survey acquired in CO2 injection wells using bare fibers. The fibers were deployed inside the production tubing through FiberLine Intervention technology developed by Well-SENSE. The test utilized two injection wells for active seismic acquisition. The study took place on Barrow Island (Western Australia) as part of the Gorgon CCS project. The study demonstrates the technological advantages of fast deployment of the sensing fiber and the high quality of acquired seismic data. The paper highlights characteristic noise patterns in the recorded data and suggests approaches to attenuate their effects on seismic image quality. Finally, the impact of survey geometry and directional sensitivity of fiber on the recorded wavefield and the quality of seismic imaging is discussed.

Ultra-dense nodal seismic acquisition for automated geohazard analysis

In this paper, we address the problem of shallow geohazard mapping by developing an integrated workflow consisting of nodal seismic acquisition and automated data analysis. Densely spaced point-receiver land nodes and point sources are adopted as an alternative to receiver arrays or groups conventionally used in seismic exploration. The recently developed methodology of surface-consistent decomposition of the transmitted wavefield is applied to the nodal data. Ultra-resolution mapping of surface-consistent attributes in amplitude and phase is obtained, together with the generation of high-energy signal beams at the common midpoint positions, forming virtual (shot) supergathers (VSGs). The VSG preserves frequency and true-amplitude content thanks to the surface-consistent corrections applied before beam forming. Traveltimes, waveforms, and surface waves are then analyzed in the high signal-to-noise ratio VSG, leading to inversion of the subsurface parameters. Human-intensive interpretation of surface-wave dispersion curves in the f-k spectra is facilitated by the introduction of efficient machine learning algorithms for the unsupervised and supervised paradigms. The ultra-dense nodal acquisition and automated data analysis are effectively applied to the analysis of several cases of near-surface geohazards.

Multi-Source Feature-Fusion Method for the Seismic Data of Cultural Relics Based on Deep Learning.

The museum system is exposed to a high risk of seismic hazards. However, it is difficult to carry out seismic hazard prevention to protect cultural relics in collections due to the lack of real data and diverse types of seismic hazards. To address this problem, we developed a deep-learning-based multi-source feature-fusion method to assess the data on seismic damage caused by collected cultural relics. Firstly, a multi-source data-processing strategy was developed according to the needs of seismic impact analysis of the cultural relics in the collection, and a seismic event-ontology model of cultural relics was constructed. Additionally, a seismic damage data-classification acquisition method and empirical calculation model were designed. Secondly, we proposed a deep learning-based multi-source feature-fusion matching method for cultural relics. By constructing a damage state assessment model of cultural relics using superpixel map convolutional fusion and an automatic data-matching model, the quality and processing efficiency of seismic damage data of the cultural relics in the collection were improved. Finally, we formed a dataset oriented to the seismic damage risk analysis of the cultural relics in the collection. The experimental results show that the accuracy of this method reaches 93.6%, and the accuracy of cultural relics label matching is as high as 82.6% compared with many kinds of earthquake damage state assessment models. This method can provide more accurate and efficient data support, along with a scientific basis for subsequent research on the impact analysis of seismic damage to cultural relics in collections.