Fault Enhancement in Seismic Images by Introducing a Novel Strategy Integrating Attributes and Image Analysis Techniques

Mousavi, Jabar; Radad, Mohammad; Monfared, Mehrdad Soleimani; Kahoo, Amin Roshandel

doi:10.1007/s00024-022-03014-y

Cited by 10 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is urgent to find a more efficient and intelligent method for MSW classification. Data about semismic images can be used to identify hydrocarbon structure to help classify wet waste and residual waste (Radad et al, 2016;Hadiloo et al, 2017;Mousavi et al, 2022). The application methods in indentifying hydrocarbon resevoirs and structure related to hydrocarbon also have been discussed (Soleimani and Balarostaghi, 2016;Farrokhnia et al, 2018;Khayer et al, 2022a;Khayer et al, 2022b;Hosseini-Fard et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Effect of transfer learning on the performance of VGGNet-16 and ResNet-50 for the classification of organic and residual waste

Lin²

2022

Front. Environ. Sci.

View full text Add to dashboard Cite

It is crucial to realize the municipal solid waste (MSW) classification in terms of its treatments and disposals. Deep learning used for the classification of residual waste and wet waste from MSW was considered as a promising method. While few studies reported using the method of deep learning with transfer learning to classify organic waste and residual waste. Thus, this study aims to discuss the effect of the transfer learning on the performance of different deep learning structures, VGGNet-16 and ResNet-50, for the classification of organic waste and residual waste, which were compared in terms of the training time, confusion matric, accuracy, precision, and recall. In addition, the algorithms of PCA and t-SNE were also adopted to compare the representation extracted from the last layer of various deep learning models. Results indicated that transfer learning could shorten the training time and the training time of various deep learning follows this order: VGGNet-16 (402 s) > VGGNet-16 with TL (272 s) > ResNet-50 (238 s) > ResNet-50 with TL (223 s). Compared with the method of PAC, waste representations were better separated from high dimension to low dimension by t-SNE. The values of organic waste in terms of F1 score follows this order: ResNet-50 with transfer learning (97.8%) > VGGNet-16 with transfer learning (97.1%) > VGGNet-16 (95.0%) > ResNet-50 (92.5%).Therefore, the best performance for the classification of organic and residual waste was ResNet-50 with transfer learning, followed by VGGNet-16 with transfer learning and VGGNet-16, and ResNet-50 in terms of accuracy, precision, recall, and F1 score.

show abstract

Section: Introductionmentioning

confidence: 99%

Effect of transfer learning on the performance of VGGNet-16 and ResNet-50 for the classification of organic and residual waste

Lin²

2022

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…For the identification of relatively larger scale faults, the commonly used seismic attributes include amplitude, coherence, variance, curvature, azimuth, instantaneous phase, Hilbert transform attribute and other attributes (Qi et al, 2017;Wen, 2020;Ojha et al, 2023). Additionally, there is increasing research using image recognition methods to enhance fault edge and identify faults, achieving good results (Hosseini-Fard et al, 2022;Mousavi et al, 2022). However, these attributes cannot quantitatively identify the development density and orientation of faults/fractures.…”

Section: Introductionmentioning

confidence: 99%

Application of seismic attribute analysis techniques to multi-scale natural fractures description: a case study of the Longmaxi-Wufeng formation in H shale gas block, Yangtze plate, China

Xie,

Chen,

Zhao

et al. 2024

Front. Earth Sci.

View full text Add to dashboard Cite

The H shale gas block in the Yangtze plate of China has undergone multistage tectonic evolution, which has resulted in the development of faults and natural fractures that are multistage, multi-scale, multi-type, and multi-strike in nature. To precisely characterize the natural fractures, this study used the seismic attribute analysis method to conduct a multi-scale prediction and natural fracture modelling. Initially, manual fault interpretation and the conventional seismic attributes including variance attribute, curvature and edge detection are used to interpret large-to medium-scale faults. Subsequently, the ant-tracking attribute based on the divided-frequency seismic cubes is used to predict and quantitatively interpret the mid- and small-scale fractures; The third step is to quantitatively divide the ant-tracking attribute value into multiple scales and convert them linearly into fracture intensity. The fourth step is to establish a multi-scale fracture model. This approach has established a comprehensive prediction workflow, progressing from large-scale to small-scale analysis, and shifting from qualitative to quantitative assessment. Compared with traditional fracture prediction and modeling methods, this method not only enhances the accuracy, but also satisfies the engineering requirements of multi-scale modeling. By applying the method in the H shale gas block, we gained a microscopic understanding of the fractures, which are predominantly NW, NE, and nearly NS trending, with a minimal occurrence of nearly EW trending faults/fractures. This method can be effectively applied to characterize multi-scale fractures in areas similar to the geological background of the H shale gas block.

show abstract

“…However, forward models, which rely on state-of-the-art approximations of the underlying physics, are computationally expensive, and inverse models often lead to non-unique solutions. Notwithstanding, noise reduction (e.g., Dong et al, 2006;Mafakheri et al, 2022) and data exploration (e.g., Khasraji-Nejad et al, 2021;Mahdavi et al, 2021;Mousavi et al, 2022) are key analyses that need to be carried out before any forward or inverse simulation. Particularly for studies of crustal deformation, an exhaustive inspection of observations can be a time-consuming task, considering the decades long records of hundreds or even thousands of GNSS stations located at some plate boundaries.…”

Section: Introductionmentioning

confidence: 99%

Mosaicking Andean morphostructure and seismic cycle crustal deformation patterns using GNSS velocities and machine learning

et al. 2023

View full text Add to dashboard Cite

We use unsupervised machine learning techniques to analyze continental-scale crustal motions in areas affected by the seismic cycle of large subduction earthquakes along the Chilean Trench. Specifically, we use the agglomerative clustering algorithm as an exploratory tool to investigate spatial patterns in GNSS regional velocities without the complexity of modeling a physical source. We present a continental-scale velocity field including all available GNSS data for two-time windows (pre-2014, 2018–2021) that represents two periods with different deformation patterns of the seismic cycle. We test two different pre-processing methodologies for the design of machine learning features from the GNSS-derived velocities. The first method uses the direction and magnitude of the secular rates as input features to the clustering algorithm. These results show a clustering spatially related to seismic cycle deformation, separating latitudinal segments with different velocities in the fore-arc and back-arc, as well as regions affected by postseismic relaxation. Thus, highlighting the effectiveness of this method for mapping first-order patterns of active deformation in a subduction zone, that are particularly related to variations on interplate coupling and postseismic transient deformation. In a more sophisticated approach, we use surface strain and rotational rates from GNSS velocities as features in the second methodology. Here, we develop a novel methodology to estimate strain and rotation rates accounting for the spatial heterogeneity of the GNSS-network. We determine the spatial scale at which these features are estimated by least squares inversions, by using a Bayesian model class selection method. The distribution of stations allows to identify heterogeneities in strain and rotation rates at spatial scales larger than 50 km, being particularly notorious the main features of regional deformation at scales > 100 km. Interestingly, the results show a spatial correlation between seismic segmentation in the fore-arc and geologic and structural domains in the arc and back-arc. Our results demonstrate the ability of the combination of inverse and machine learning methods to efficiently identify active deformation patterns and their relationship to the subduction seismic cycle and regional-scale geological structures. Furthermore, our analysis suggests that Andean geological structures influence the observed deformation field.

show abstract

Fault Enhancement in Seismic Images by Introducing a Novel Strategy Integrating Attributes and Image Analysis Techniques

Cited by 10 publications

References 38 publications

Effect of transfer learning on the performance of VGGNet-16 and ResNet-50 for the classification of organic and residual waste

Effect of transfer learning on the performance of VGGNet-16 and ResNet-50 for the classification of organic and residual waste

Application of seismic attribute analysis techniques to multi-scale natural fractures description: a case study of the Longmaxi-Wufeng formation in H shale gas block, Yangtze plate, China

Mosaicking Andean morphostructure and seismic cycle crustal deformation patterns using GNSS velocities and machine learning

Contact Info

Product

Resources

About