重力异常AlexNet深度神经网络反演  

Inversion of Gravity Anomaly Based on AlexNet Deep Neural Network

作　　者：刘彩云[1] 李梦迪 熊杰[2] 王蓉 LIU Caiyun;LI Mengdi;XIONG Jie;WANG Rong(School of Information and Math,Yangtze University,Jingzhou,Hubei 434023,China;School of Electronic Information,Yangtze University,Jingzhou,Hubei 434023,China)

机构地区：[1]长江大学信息与数学学院,湖北荆州434023 [2]长江大学电子信息学院,湖北荆州434023

出　　处：《现代地质》2023年第1期164-172,共9页Geoscience

基　　金：国家自然科学基金项目(62273060,61673006)。

摘　　要：针对传统反演方法存在的初始模型依赖、计算时间较长等问题,提出了一种新的基于AlexNet深度神经网络的重力异常反演方法。该方法首先借鉴经典的深度神经网络AlexNet设计了一种用于重力异常反演的Alex反演网络(AlexInvNet),接着设计大量密度异常体模型并通过正演计算得到带标签的数据集,然后用该数据集训练AlexInvNet网络,最后将重力异常数据输入训练好的AlexInvNet网络直接得到反演结果。理论模型反演结果表明,该方法相较于全连接网络深度学习反演方法,能够更好地反演出异常体的位置和密度,具有较好的泛化能力和抗噪声能力。实测数据反演结果表明,该方法能有效解决重力异常反演问题。In order to solve the problems of traditional inversion methods,such as dependence of initial model and long time for calculation,this paper proposes a noval gravity anomaly inversion method based on AlexNet deep neural network.This method designs an Alex inversion network(AlexInvNet)for gravity anomaly inversion inspired by classical deep neural network AlexNet firstly;constructs labeled datasets by forward modeling using a large number of synthetic density models secondly;uses the dataset train the AlexInvNet thirdly;and finally inputs the gravity anomaly data to the trained AlexInvNet to obtain the inversion result directly.The inversion experimental results of synthetic models show that this method can invert the position and density of anomaly body accurately,with good generalization and anti-noise ability,better than the full connected network deep learning inversion method.The field data inversion result demonstrates that this method can solve gravity anomaly inversion problem effectively.

关 键 词：重力异常 反演 深度神经网络 Alex反演网络 

分 类 号：P631[天文地球—地质矿产勘探]