Application of the local maximum synchrosqueezing transform for seismic data

In recent years, Distributed Acoustic Sensing (DAS) deployed in deviated wells has been increasingly used for microseismic monitoring. DAS can provide observations of microseismic wavefields with high spatial resolution and wide aperture, at the cost of unusually large data volumes compared with conventional downhole microseismic monitoring. To tackle this big-data challenge, we have developed key elements of a processing workflow that is assisted by machine learning techniques. We trained a convolutional neural network (CNN) for event detection and a U-Net model for both P- and S-wave arrival time picking. The workflow was applied to two multiwell DAS datasets acquired during hydraulic fracturing completions in western Canada. These datasets also include co-located 3C borehole geophone arrays that enable further comparison between catalogs from both sensor types. Compared with a traditional short-term average/long-term average (STA/LTA) method for event detection, our results indicate that the CNN method has a lower false-trigger rate and increases the event catalog size by a factor of 2.6–5.6. U-Net yields arrival-time picks with relatively small errors, high efficiency, and minimal user intervention, providing hypocenter location and focal depth that is arguably more accurate than the geophone catalog. While the proposed automated workflow requires substantial effort to build high-quality and large training datasets, it enables the use of DAS for real-time seismicity monitoring and risk management after the training stage. Although the DAS system detected fewer events than the geophone catalog and missed smaller magnitude events, our results indicate that fiber-optic sensors provide enough sensitivity to detect and locate sufficient events to characterize the treatment stages. DAS also captured induced events located at a hypocentral distance of >1 km, which are possibly indicative of reactivation of structural features.

Section: Discussionmentioning

confidence: 99%

Machine learning-assisted processing workflow for multi-fiber DAS microseismic data

Eaton

Igonin

et al. 2023

“…The primary task in seismic data processing in hydrocarbon exploration is to remove noise and improve the signal of the data set to better understand the subsurface picture (Mahdavi et al, 2021;Mafakheri et al, 2022). The resolution of the seismic image is playing a key role to get the accuracy of the target for exploratory drilling by seismic data (Mahdavi et al, 2021). The seismic data was composed of 2D seismic sections.…”

Section: Methodsmentioning

confidence: 99%

Analyzing the seismic attributes, structural and petrophysical analyses of the Lower Goru Formation: A case study from Middle Indus Basin Pakistan

Tounkara

Ehsan²,

Iqbal³

et al. 2023

The purpose of this research is to delineate the structures of the Lower Goru Formation, investigate fluid properties, and clarify the hydrocarbon-prone areas through seismic attributes analysis. First, the acquired data was matched by the interpretation datum. Structural analysis was done by performing horizon interpretation, fault interpretation, and contour mapping on the C-Interval of the Lower Goru Formation. Hydrocarbon zones were marked with the help of attribute analysis on seismic sections and were justified by petrophysical analysis. An integrated approach such as seismic structural interpretation, seismic attribute, spectral decomposition, and petrophysical analyses was used in current research to better understand geological structure and features. This research showed that normal faults are present in the area showing negative flower structure, horst and graben, and faults oriented north-west to south-east. The contour map shows structural inclination and faults bound closure near well locations. Variance attribute and spectral decomposition attribute were used to verify horizon lineation and fault behavior. Instantaneous amplitude and instantaneous phase attributes justify hydrocarbon bearing zones, and bright spots are present on seismic sections at C–Interval of Lower Goru Formation. Petrophysical analysis of the available wells showed a number of significant hydrocarbon zones having more than 55% of hydrocarbon saturation at the C-Interval of the Lower Goru Formation. The four possible reservoir zones in Sawan-02 well, two zones in Sawan-07 well, and three zones in Sawan-09 well are identified based on well data interpretation. Based on these analyses, the area of interest has a very good reservoir potential, structural closure, and visible bright spots. The current finding of this research will be helpful for future exploration and development of the Sawan area.

“…Seismic data reconstruction is important in seismic imaging. Many traditional intelligent methods have been proposed to solve various problems in seismic imaging, such as seismic resolution enhancement (Alaei et al, 2018;Soleimani, 2016;Soleimani, 2017;Soleimani et al, 2018;Mahdavi et al, 2021), complex geological structure identification (Soleimani, 2015;Farrokhnia et al, 2018;Kahoo et al, 2021;Khasraji et al, 2021;Hosseini-Fard et al, 2022;Khayer et al, 2022a;Khayer et al, 2022b), and noise attenuation (Gholtashi et al, 2015;Siahsar et al, 2017;Anvari et al, 2018;Anvari et al, 2020). In recent years, deep learning has achieved outstanding successes in a variety of domains, including computer vision (Ferdian et al, 2020;Manor and Geva, 2015) and medical image processing (Li et al, 2021;Tavoosi et al, 2021), with its powerful representing ability.…”

Section: Introductionmentioning

confidence: 99%

Depthwise separable convolution Unet for 3D seismic data interpolation

Jin

Yang

et al. 2023

In seismic exploration, dense and evenly spatial sampled seismic traces are crucial for successful implementation of most seismic data processing and interpretation algorithms. Recently, numerous seismic data reconstruction approaches based on deep learning have been presented. High dimension-based methods have the benefit of making full use of seismic signal at different perspectives. However, with the transformation of data dimension from low to high, the parameter capacity and computation cost of training deep neural network increase significantly. In this paper, we introduce depthwise separable convolution instead of standard convolution to reduce the operation cost of Unet for 3D seismic data missing trace interpolation. The structural similarity (SSIM), L1 hybrid loss function, and switchable normalization further improve the reconstruction performance of the network. The comparative experiments on the synthetic and field seismic data show that depthwise separable convolution can effectively reduce the number of network parameters and computation intensity with the interpolation results comparable to the standard convolution results.