Distilling Knowledge From an Ensemble of Convolutional Neural Networks for Seismic Fault Detection

Wang, Zirui; Li, Bo; Liu, Naihao; Wu, Bangyu; Zhu, Xu

doi:10.1109/lgrs.2020.3034960

Cited by 23 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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. In the field of geophysics, deep learning methods have also been applied to many research directions recently, such as seismic inversion (Shahbazi et al, 2020;Wu et al, 2020;, fault analysis (Wu et al, 2019;Lin et al, 2022;Wang et al, 2022;Zhu et al, 2022), denoising (Qiu et al, 2022;Jiang et al, 2022;Yang et al, 2021;Yang et al, 2022), and interpolation (Liu et al, 2021;Yu and Wu, 2022).…”

Section: Introductionmentioning

confidence: 99%

Depthwise separable convolution Unet for 3D seismic data interpolation

Jin

Yang

et al. 2023

Front. Earth Sci.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

Depthwise separable convolution Unet for 3D seismic data interpolation

Jin

Yang

et al. 2023

Front. Earth Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…More recently, with the successes of deep learning in the computer vision community, time series forecasting [2], and natural language processing, researchers have developed various data-driven seismic inversion techniques. The amount of available seismic data is growing exponentially and the deep learning methods are becoming integral components of geophysical exploration workflows [3], such as P-wave detection [4], seismic fault detection [5][6][7][8], seismic data noise attenuation [9,10], seismic data interpolation [11][12][13][14][15], and seismic slope estimation [16].…”

Section: Introductionmentioning

confidence: 99%

Multi-Task Deep Learning Seismic Impedance Inversion Optimization Based on Homoscedastic Uncertainty

Zheng

Zhu

et al. 2022

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Seismic inversion is a process to obtain the spatial structure and physical properties of underground rock formations using surface acquired seismic data, constrained by known geological laws and drilling and logging data. The principle of seismic inversion based on deep learning is to learn the mapping between seismic data and rock properties by training a neural network using logging data as labels. However, due to high cost, the number of logging curves is often limited, leading to a trained model with poor generalization. Multi-task learning (MTL) provides an effective way to mitigate this problem. Learning multiple related tasks at the same time can improve the generalization ability of the model, thereby improving the performance of the main task on the same amount of labeled data. However, the performance of multi-task learning is highly dependent on the relative weights for the loss of each task, and manual tuning of the weights is often time-consuming and laborious. In this paper, a Fully Convolutional Residual Network (FCRN) is proposed to achieve seismic impedance inversion and seismic data reconstruction simultaneously, and a method based on the homoscedastic uncertainty of the Bayesian model is used to balance the weights of the loss function for the two tasks. The test results on the synthetic datasets of Marmousi2, Overthrust, and Volve field data show that the proposed method can automatically determine the optimal weight of the two tasks, and predicts impedance with higher accuracy than single-task FCRN model.

show abstract

“…The combination of predictions of the distinct neural networks is expected to improve the overall generalization ability of the neural network system [10]. It has already been effectively applied to areas as diverse as face recognition [11], medical diagnosis [12] [13], and seismic signals classification [14] and fault detection [15].…”

Section: Introductionmentioning

confidence: 99%

Enhanced Perspective Generation by Consensus of NeX neural models

Lima¹,

Rodríguez²,

Ortiz-de-Lazcano-Lobato³

et al. 2022

2022 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Neural rendering is a relatively new field of research that aims to produce high quality perspectives of a 3D scene from a reduced set of sample images. This is done with the help of deep artificial neural networks that model the geometry and color characteristics of the scene. The NeX model relies on neural basis expansion to yield accurate results with a lower computational load than the previous NeRF model. In this work, a procedure is proposed to further enhance the quality of the perspectives generated by NeX. Our proposal is based on the combination of the outputs of several NeX models by a consensus mechanism. The approach is compared to the original NeX for a wide range of scenes. It is found that our method significantly outperforms the original procedure, both in quantitative and qualitative terms.

show abstract

Distilling Knowledge From an Ensemble of Convolutional Neural Networks for Seismic Fault Detection

Cited by 23 publications

References 27 publications

Depthwise separable convolution Unet for 3D seismic data interpolation

Depthwise separable convolution Unet for 3D seismic data interpolation

Multi-Task Deep Learning Seismic Impedance Inversion Optimization Based on Homoscedastic Uncertainty

Enhanced Perspective Generation by Consensus of NeX neural models

Contact Info

Product

Resources

About