鉴别器
缺少数据
计算机科学
插值(计算机图形学)
数据集
试验装置
集合(抽象数据类型)
试验数据
发电机(电路理论)
噪音(视频)
训练集
合成数据
模式识别(心理学)
高斯分布
生成对抗网络
人工神经网络
深度学习
人工智能
数据挖掘
机器学习
图像(数学)
物理
功率(物理)
探测器
程序设计语言
电信
量子力学
作者
Qing Wei,Xiang‐Yang Li,Mingpeng Song
出处
期刊:Geophysics
[Society of Exploration Geophysicists]
日期:2021-09-27
卷期号:86 (6): V471-V488
被引量:13
标识
DOI:10.1190/geo2020-0644.1
摘要
During acquisition, due to economic and natural reasons, irregular missing seismic data are always observed. To improve accuracy in subsequent processing, the missing data should be interpolated. A conditional generative adversarial network (cGAN) consisting of two networks, a generator and a discriminator, is a deep-learning model that can be used to interpolate the missing data. However, because cGAN is typically data set oriented, the trained network is unable to interpolate a data set from an area different from that of the training data set. We design a cGAN based on Pix2Pix GAN to interpolate irregular missing seismic data. A synthetic data set synthesized from two models is used to train the network. Furthermore, we add a Gaussian-noise layer in the discriminator to fix a vanishing gradient, allowing us to train a more powerful generator. Two synthetic data sets synthesized by two new geologic models and two field data sets are used to test the trained cGAN. The test results and the calculated recovered signal-to-noise ratios indicate that although the cGAN is trained using synthetic data, the network can reconstruct irregular missing field seismic data with high accuracy using the Gaussian-noise layer. We test the performances of cGANs trained with different patch sizes in the discriminator to determine the best structure, and we train the networks using different training data sets for different missing rates, demonstrating the best training data set. Compared with conventional methods, the cGAN-based interpolation method does not need different parameter selections for different data sets to obtain the best interpolation data. Furthermore, it is also an efficient technique as the cost is because of the training, and after training, the processing time is negligible.
科研通智能强力驱动
Strongly Powered by AbleSci AI