利用卷积神经网络与变压器相结合的融合网络进行高精度微震源定位

IF 4.9 2区 地球科学 Q1 GEOCHEMISTRY & GEOPHYSICS
Qiang Feng, Liguo Han, Liyun Ma, Qiang Li
{"title":"利用卷积神经网络与变压器相结合的融合网络进行高精度微震源定位","authors":"Qiang Feng,&nbsp;Liguo Han,&nbsp;Liyun Ma,&nbsp;Qiang Li","doi":"10.1007/s10712-024-09846-8","DOIUrl":null,"url":null,"abstract":"<div><p>Microseismic source localization methods with deep learning can directly predict the source location from recorded microseismic data, showing remarkably high accuracy and efficiency. Two main categories of deep learning-based localization methods are coordinate prediction methods and heatmap prediction methods. Coordinate prediction methods provide only a source coordinate and generally do not provide a measure of confidence in the source location. Heatmap prediction methods require the assumption that the microseismic source is located on a grid point. Thus, they tend to provide lower resolution information and localization results may lose precision. This study reviews and compares previous methods for locating the source based on deep learning. To address the limitations of existing methods, we devise a network fusing a convolutional neural network and a Transformer to locate microseismic sources. We first introduce the multi-modal heatmap combining the Gaussian heatmap and the offset coefficient map to represent the source location. The offset coefficients are utilized to correct the source locations predicted by the Gaussian heatmap so that the source is no longer confined to the grid point. We then propose a fusion network to accurately estimate the source location. A gated multi-scale feature fusion module is developed to efficiently fuse features from different branches. Experiments on synthetic and field data demonstrate that the proposed method yields highly accurate localization results. A comprehensive comparison of coordinate prediction method and heatmap prediction methods with our proposed method demonstrates that the proposed method outperforms the other methods.</p></div>","PeriodicalId":49458,"journal":{"name":"Surveys in Geophysics","volume":null,"pages":null},"PeriodicalIF":4.9000,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"High-Precision Microseismic Source Localization Using a Fusion Network Combining Convolutional Neural Network and Transformer\",\"authors\":\"Qiang Feng,&nbsp;Liguo Han,&nbsp;Liyun Ma,&nbsp;Qiang Li\",\"doi\":\"10.1007/s10712-024-09846-8\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Microseismic source localization methods with deep learning can directly predict the source location from recorded microseismic data, showing remarkably high accuracy and efficiency. Two main categories of deep learning-based localization methods are coordinate prediction methods and heatmap prediction methods. Coordinate prediction methods provide only a source coordinate and generally do not provide a measure of confidence in the source location. Heatmap prediction methods require the assumption that the microseismic source is located on a grid point. Thus, they tend to provide lower resolution information and localization results may lose precision. This study reviews and compares previous methods for locating the source based on deep learning. To address the limitations of existing methods, we devise a network fusing a convolutional neural network and a Transformer to locate microseismic sources. We first introduce the multi-modal heatmap combining the Gaussian heatmap and the offset coefficient map to represent the source location. The offset coefficients are utilized to correct the source locations predicted by the Gaussian heatmap so that the source is no longer confined to the grid point. We then propose a fusion network to accurately estimate the source location. A gated multi-scale feature fusion module is developed to efficiently fuse features from different branches. Experiments on synthetic and field data demonstrate that the proposed method yields highly accurate localization results. A comprehensive comparison of coordinate prediction method and heatmap prediction methods with our proposed method demonstrates that the proposed method outperforms the other methods.</p></div>\",\"PeriodicalId\":49458,\"journal\":{\"name\":\"Surveys in Geophysics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.9000,\"publicationDate\":\"2024-06-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Surveys in Geophysics\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s10712-024-09846-8\",\"RegionNum\":2,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"GEOCHEMISTRY & GEOPHYSICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Surveys in Geophysics","FirstCategoryId":"89","ListUrlMain":"https://link.springer.com/article/10.1007/s10712-024-09846-8","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GEOCHEMISTRY & GEOPHYSICS","Score":null,"Total":0}
引用次数: 0

摘要

利用深度学习的微震源定位方法可以直接从记录的微震数据中预测震源位置,显示出极高的准确性和效率。基于深度学习的定位方法主要有两类,即坐标预测方法和热图预测方法。坐标预测方法只提供震源坐标,一般不提供震源位置的置信度。热图预测方法需要假设微震源位于网格点上。因此,它们往往提供较低分辨率的信息,定位结果可能会失去精确性。本研究回顾并比较了之前基于深度学习的震源定位方法。针对现有方法的局限性,我们设计了一种融合卷积神经网络和变形器的网络来定位微震源。我们首先引入多模态热图,结合高斯热图和偏移系数图来表示震源位置。偏移系数用于修正高斯热图预测的震源位置,使震源不再局限于网格点。然后,我们提出了一个融合网络,以准确估计源位置。我们开发了一个门控多尺度特征融合模块,以有效融合来自不同分支的特征。在合成数据和实地数据上的实验证明,所提出的方法能产生高度精确的定位结果。将坐标预测方法和热图预测方法与我们提出的方法进行综合比较后发现,我们提出的方法优于其他方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

High-Precision Microseismic Source Localization Using a Fusion Network Combining Convolutional Neural Network and Transformer

High-Precision Microseismic Source Localization Using a Fusion Network Combining Convolutional Neural Network and Transformer

High-Precision Microseismic Source Localization Using a Fusion Network Combining Convolutional Neural Network and Transformer

Microseismic source localization methods with deep learning can directly predict the source location from recorded microseismic data, showing remarkably high accuracy and efficiency. Two main categories of deep learning-based localization methods are coordinate prediction methods and heatmap prediction methods. Coordinate prediction methods provide only a source coordinate and generally do not provide a measure of confidence in the source location. Heatmap prediction methods require the assumption that the microseismic source is located on a grid point. Thus, they tend to provide lower resolution information and localization results may lose precision. This study reviews and compares previous methods for locating the source based on deep learning. To address the limitations of existing methods, we devise a network fusing a convolutional neural network and a Transformer to locate microseismic sources. We first introduce the multi-modal heatmap combining the Gaussian heatmap and the offset coefficient map to represent the source location. The offset coefficients are utilized to correct the source locations predicted by the Gaussian heatmap so that the source is no longer confined to the grid point. We then propose a fusion network to accurately estimate the source location. A gated multi-scale feature fusion module is developed to efficiently fuse features from different branches. Experiments on synthetic and field data demonstrate that the proposed method yields highly accurate localization results. A comprehensive comparison of coordinate prediction method and heatmap prediction methods with our proposed method demonstrates that the proposed method outperforms the other methods.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Surveys in Geophysics
Surveys in Geophysics 地学-地球化学与地球物理
CiteScore
10.00
自引率
10.90%
发文量
64
审稿时长
4.5 months
期刊介绍: Surveys in Geophysics publishes refereed review articles on the physical, chemical and biological processes occurring within the Earth, on its surface, in its atmosphere and in the near-Earth space environment, including relations with other bodies in the solar system. Observations, their interpretation, theory and modelling are covered in papers dealing with any of the Earth and space sciences.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信