Modeling multisource multifrequency acoustic wavefields by a multiscale Fourier feature physics-informed neural network with adaptive activation functions

傅里叶变换 计算机科学 声波方程 奇点 人工神经网络 频域 特征(语言学) 激活函数 偏微分方程 波动方程 功能(生物学) 算法 物理 数学分析 数学 声学 声波 人工智能 语言学 哲学 进化生物学 计算机视觉 生物
作者
Xintao Chai,Zhiyuan Gu,Hang Long,Shaoyong Liu,Taihui Yang,Lei Wang,Fenglin Zhan,Xiaodong Sun,Wenjun Cao
出处
期刊:Geophysics [Society of Exploration Geophysicists]
卷期号:: 1-97 被引量:2
标识
DOI:10.1190/geo2023-0394.1
摘要

Recently, the physics-informed neural network (PINN) was adopted to solve partial differential equation (PDE)-based forward and inverse problems. Compared to numerical differentiation, a PINN calculates derivatives by mesh-free automatic differentiation without dispersion artifacts. The Fourier feature PINN was applied to solve the frequency-domain acoustic wave equation to model multifrequency scattered wavefields. Although solving for scattered wavefields avoids the source singularity problem, it has drawbacks (e.g., requiring an analytic formula for computing the background wavefield, which only exists for the wave equation for simple models). We evaluated an approach for modeling multisource multifrequency acoustic wavefields using a multiscale Fourier feature mapping (MFFM) PINN with adaptive activations, directly solving for full wavefields instead of scattered wavefields and naturally avoiding the drawbacks of solving the scattered wave equation. For the MFFM, we explored the determination of the maximum and number of Fourier scales. Our inputs to the MFFM were only the spatial coordinates of the subsurface model; this result is lower than that of previous work (improving the efficiency of the PINN while maintaining its accuracy). Because the activation function is extremely important for a PINN, we use an existing technique and adapt it to a new architecture and develop an adaptive amplitude-scaled and phase-shifted sine activation function, which performs the best among the studied activation functions. Experiments show that the MFFM, adaptive activation, an appropriate learning rate, a linearly shrinking NN, and transfer learning greatly improve the convergence rate, accuracy, and efficiency of the PINN for simulating multisource multifrequency wavefields, laying the foundation for applying a PINN to wave equation-based inversion and imaging. We shared our codes, data, and results via a public repository.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
mjtsurgery发布了新的文献求助10
刚刚
1秒前
荣艺完成签到,获得积分10
2秒前
李健的小迷弟应助小鱼儿采纳,获得10
4秒前
zzz发布了新的文献求助10
5秒前
请叫我风吹麦浪应助欧皇采纳,获得10
5秒前
mjtsurgery完成签到,获得积分20
6秒前
7秒前
8秒前
内向寒云完成签到,获得积分20
8秒前
FashionBoy应助科研鸟采纳,获得10
8秒前
忧郁凡灵完成签到,获得积分20
9秒前
科目三应助wsz采纳,获得10
10秒前
沐沐发布了新的文献求助10
12秒前
12秒前
12秒前
12秒前
等待的谷波完成签到 ,获得积分10
13秒前
起起完成签到 ,获得积分10
15秒前
15秒前
Joker发布了新的文献求助30
16秒前
17秒前
FancyShi发布了新的文献求助10
18秒前
满眼星辰发布了新的文献求助10
19秒前
内向寒云关注了科研通微信公众号
21秒前
21秒前
汉堡包应助FancyShi采纳,获得10
23秒前
24秒前
瞿霞完成签到 ,获得积分10
25秒前
25秒前
桐桐应助小猪跳水采纳,获得10
25秒前
好了没了完成签到,获得积分10
27秒前
28秒前
研友_LX66qZ完成签到,获得积分10
28秒前
28秒前
stars发布了新的文献求助10
30秒前
好了没了发布了新的文献求助10
30秒前
小智发布了新的文献求助10
30秒前
hubanj完成签到,获得积分10
31秒前
31秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3966399
求助须知:如何正确求助?哪些是违规求助? 3511837
关于积分的说明 11160190
捐赠科研通 3246481
什么是DOI,文献DOI怎么找? 1793425
邀请新用户注册赠送积分活动 874438
科研通“疑难数据库(出版商)”最低求助积分说明 804388