New insights into the structural model of the Makran subduction zone by fusion of 3D inverted geophysical models

Nasri, Sara; Kalate, Ali Nejati; Kahoo, Amin Roshandel; Monfared, Mehrdad Soleimani

doi:10.1016/j.jseaes.2019.104075

Cited by 20 publications

(5 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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). Recently, great attention has been caught to applying deep learning for the waste classification related to computer version (CV) with the development of computer hardware (Nasri et al, 2020). Compared with traditional CV algorithms like scale-invariant feature transform (SIFT), supporting vector machine (SVM), and principal component (PCA) (Soleimani, 2016a,b;Lu and Chen, 2022), deep learning has the ability to automatically extract the representation and equips with more applicability, robustness, generalization, and scability (Lin et al, 2022;Mafakheri et al, 2022;Saad and Chen, 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

“…Conversional integration and inversion methods of magnetic and gravity data would result in uncertainty and inconsistency in complex geological media, because magnetic model could reveal near-surface structure, and deep anomalies could be modeled by gravity data. A novel strategy by simultaneous gravity and magnetic inversion followed by fusion procedure was developed to construct a geological model for the Makran subduction zone in southeast of Iran [36]. While preserving information both from near surface and subsurface structures, the fused model could be able to provide a better view of Makran subduction for geological interpretation.…”

Section: Discussionmentioning

confidence: 99%

Seismic Survey in Lesser Himalayan Thrust Belt, Western Nepal

Zhang

et al. 2022

International Journal of Geophysics

View full text Add to dashboard Cite

Two hundred km of 2D seismic survey was carried out at the Lesser Himalayan Thrust Belts in Dailekh district, western Nepal. The main motivation is to elucidate the geologic relationship between the known oil and gas seeps, subsurface structure, and stratigraphy in the area. This is a challenging task which is from its extreme structural and geological complexity such as thrust faulting, tight folding, steep dip layers, and strong lateral variations in seismic velocity. Seismic data were acquired with SERCEL 428XL system and processed by GEOEAST computer software. In order to increase signal-to-noise ratio (SNR), suppress interference, and search for optimum acquisition parameters, a series of comparative tests on the different charge depth and size, group interval, CDP fold, geophone array, and single high-sensitivity geophone were conducted. We also tested 2S3L (two lines shooting and three lines receiving) wide line profiling. The results indicate that single hole with charge depth of 12 m, 4-16 kg charge size (less charge size for the densely populated areas), single high-sensitivity geophone, and 1S2L wide line profiling with 132 folds are the optimum acquisition parameters. On the basis of comparative process experiment, data processing workflow consisting of data preparation, prestack denoising, amplitude compensation, deconvolution, tomography static correction, velocity analysis, residual static correction, CRS stack, poststack migration, prestack time migration (PSTM), and prestack depth migration (PSDM) was selected. Maybe affected by problem of conflicting dip in complex media, CRS stack section does not show satisfactory geological characteristics. PSTM profile has moderate signal-to-noise (S/N) ratio; the shallow, medium, and deep continuous reflections can be observed in section. More details of the geological structures can be observed in PSDM section, especially in medium and shallow layers (less than 3000 ms or 4000 m), but PSDM method is more expensive and highly time consuming than that of CRS stack and PSTM. So, the PSTM section can be reasonably used for geological interpretation. By reference to field mapping, thrust characteristics, and MT data, the final interpretation to the PSTM section identified the interfaces of 6 geological units (Paleoproterozoic Nabhisthan Fm., Paleoproterozoic Dubidanda Fm., Neogene to Late Cretaceous Surkhet group, Late Carboneferous to Early Cretaeous Gondwana group, Mesoproterozoic Upper Lakharpata group, and Lower Lakharpata group) and delineated Main Boundary Thrust (MBT), Ramgarh Thrust (RMT), Padukasthan Thrust (PT), and Dailekh Thrust (DT). The bottom of Surkhet group which is our top target zone is about 4250 meters deep.

show abstract

“…Finally, as new research, a 3D inverse modeling procedure was applied to the Charmaleh Iron deposit magnetic data in Iran to obtain a valid anomaly edge perimeter. It focused on investigating the simultaneous application of 3D inversion and edge-detecting methods [ 16 , 17 , 25 , 26 , 64 , 67 , [81] , [82] , [83] ].…”

Section: Introductionmentioning

confidence: 99%

Geobody estimation by Bhattacharyya method utilizing nonlinear inverse modeling of magnetic data in Baba-Ali iron deposit, NW Iran

Kianoush,

Keshavarz Faraj Khah,

Hosseini

et al. 2023

Heliyon

View full text Add to dashboard Cite

New insights into the structural model of the Makran subduction zone by fusion of 3D inverted geophysical models

Cited by 20 publications

References 53 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

Seismic Survey in Lesser Himalayan Thrust Belt, Western Nepal

Geobody estimation by Bhattacharyya method utilizing nonlinear inverse modeling of magnetic data in Baba-Ali iron deposit, NW Iran

Contact Info

Product

Resources

About