Application of Supervised Descent Method for 3-D Gravity Data Focusing Inversion

反演(地质) 计算机科学 正规化(语言学) 梯度下降 计算 算法 反问题 数学优化 数学 人工智能 人工神经网络 地质学 古生物学 数学分析 构造盆地
作者
Rongzhe Zhang,Haoyuan He,Xintong Dong,Tonglin Li,Cai Liu,Xinze Kang
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:61: 1-10 被引量:7
标识
DOI:10.1109/tgrs.2023.3312541
摘要

Three-dimensional gravity inversion is an effective method for extracting underground density distribution from gravity data. However, traditional deterministic gravity inversion methods suffer from problems such as skin effect, low computational accuracy, and poor efficiency. Therefore, we propose a three-dimensional gravity data focusing inversion algorithm based on the supervised descent method. Supervised descent method (SDM) is a non-linear optimization method based on the combination of machine learning and gradient descent method. In the offline phase, we construct a training set based on a priori information and iteratively learn a set of average descent directions between the initial model and the training model. In the online phase, we introduce a focused regularization into the prediction objective function. This addition aims to obtain a sharp boundary density model that conforms to the physical distribution. Additionally, we incorporate property boundary constraints in both the offline and online phases to control the upper and lower bounds of the density values to ensure consistency with reality. Model tests show that the proposed method can effectively overcome skin effect, improve the resolution of gravity inversion. Moreover, the construction of the training set of the proposed method is less affected by prior information, and it has strong generalization ability. Furthermore, the method does not require solving large-scale linear equations, accelerating the inversion computation speed and having strong noise resistance. Field examples demonstrate that this method has good potential for improving the accuracy and efficiency of actual gravity data inversion.
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
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
刚刚
1秒前
cm5257完成签到,获得积分10
1秒前
sunpacino完成签到,获得积分10
1秒前
2秒前
追寻若男发布了新的文献求助10
2秒前
安格完成签到 ,获得积分10
3秒前
健壮不斜发布了新的文献求助10
3秒前
rby发布了新的文献求助10
4秒前
猫猫完成签到,获得积分20
5秒前
嘻嘻哈哈发布了新的文献求助210
5秒前
ding的应助被文静冰海采纳,获得10
5秒前
syvshc的应助被RuYi采纳,获得10
5秒前
5秒前
一百发布了新的文献求助10
6秒前
小二郎的应助被繁花似锦采纳,获得10
6秒前
毗昙的应助被贪玩的慕晴采纳,获得50
6秒前
科研通AI6.4的应助被liutao采纳,获得10
7秒前
7秒前
繁星若水完成签到,获得积分10
7秒前
7秒前
猫猫发布了新的文献求助10
9秒前
9秒前
daomaihu发布了新的文献求助100
9秒前
9秒前
10秒前
10秒前
11秒前
11秒前
Dr_chi发布了新的文献求助10
12秒前
13秒前
华仔的应助被上邪采纳,获得10
13秒前
13秒前
加油完成签到,获得积分10
13秒前
14秒前
14秒前
YiYang完成签到 ,获得积分10
14秒前
文静冰海完成签到,获得积分10
14秒前
15秒前
Code_king发布了新的文献求助10
15秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8177614
求助须知:如何正确求助?哪些是违规求助? 9568432
关于积分的说明 21799252
捐赠科研通 7772168
什么是DOI,文献DOI怎么找? 3432399
关于科研通互助平台的介绍 2556593
邀请新用户注册赠送积分活动 2477966