Dealiased seismic data interpolation using a deep-learning-based prediction-error filter

计算机科学 插值(计算机图形学) 人工神经网络 深度学习 一般化 人工智能 卷积神经网络 滤波器(信号处理) 可解释性 数据集 机器学习 数据挖掘 算法 模式识别(心理学) 数学 运动(物理) 数学分析 计算机视觉
作者
Wenqian Fang,Lihua Fu,Shaoyong Liu,Hongwei Li
出处
期刊:Geophysics [Society of Exploration Geophysicists]
卷期号:86 (4): V317-V328 被引量:25
标识
DOI:10.1190/geo2020-0487.1
摘要

Deep-learning (DL) technology has emerged as a new approach for seismic data interpolation. DL-based methods can automatically learn the mapping between regularly subsampled and complete data from a large training data set. Subsequently, the trained network can be used to directly interpolate new data. Therefore, compared with traditional methods, DL-based methods reduce the manual workload and render the interpolation process efficient and automatic by avoiding the selection of hyperparameters. However, two limitations of DL-based approaches exist. First, the generalization performance of the neural network is inadequate when processing new data with a different structure compared to the training data. Second, the interpretation of the trained networks is very difficult. To overcome these limitations, we have combined the deep neural network and classic prediction-error filter (PEF) methods, proposing a novel seismic data dealiased interpolation framework called prediction-error filters network (PEFNet). The PEFNet designs convolutional neural networks to learn the relationship between the subsampled data and the PEFs. Thus, the filters estimated by the trained network are used for the recovery of missing traces. The learning of filters enables the network to better extract the local dip of seismic data and has a good generalization ability. In addition, PEFNet has the same interpretability as traditional PEF-based methods. The applicability and the effectiveness of our method are demonstrated here by synthetic and field data examples.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
besatified应助受伤芝麻采纳,获得20
1秒前
金刚经应助丽Li采纳,获得10
2秒前
乐乐应助风来枫去采纳,获得10
2秒前
终究完成签到,获得积分10
2秒前
华仔应助牛牛采纳,获得10
2秒前
3秒前
清爽的绫完成签到,获得积分10
4秒前
4秒前
JK_phd完成签到,获得积分10
5秒前
5秒前
5秒前
6秒前
科研通AI2S应助xwl9955采纳,获得50
7秒前
CipherSage应助ss采纳,获得10
7秒前
8秒前
科研通AI2S应助Acc采纳,获得10
9秒前
111发布了新的文献求助10
9秒前
谦让若冰发布了新的文献求助10
9秒前
10秒前
wandong完成签到,获得积分10
11秒前
12秒前
大模型应助蜜CC采纳,获得10
12秒前
12秒前
慕青应助qianqian采纳,获得10
14秒前
Jasper应助顺利可兰采纳,获得10
14秒前
123发布了新的文献求助10
15秒前
王崇霖完成签到,获得积分10
15秒前
华仔应助鹏程采纳,获得10
16秒前
万能图书馆应助koritto采纳,获得10
17秒前
等待的时光完成签到,获得积分10
17秒前
Acc完成签到,获得积分10
17秒前
无魇完成签到,获得积分10
17秒前
18秒前
Orange应助小跳蚤采纳,获得10
18秒前
时光倒流的鱼完成签到,获得积分10
18秒前
18秒前
18秒前
小蘑菇应助耍酷的白梦采纳,获得10
19秒前
王崇霖发布了新的文献求助20
19秒前
19秒前
高分求助中
The late Devonian Standard Conodont Zonation 2000
Nickel superalloy market size, share, growth, trends, and forecast 2023-2030 2000
The Lali Section: An Excellent Reference Section for Upper - Devonian in South China 1500
Smart but Scattered: The Revolutionary Executive Skills Approach to Helping Kids Reach Their Potential (第二版) 1000
Very-high-order BVD Schemes Using β-variable THINC Method 830
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 800
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3248346
求助须知:如何正确求助?哪些是违规求助? 2891768
关于积分的说明 8268557
捐赠科研通 2559696
什么是DOI,文献DOI怎么找? 1388596
科研通“疑难数据库(出版商)”最低求助积分说明 650772
邀请新用户注册赠送积分活动 627744