利用卷积自编码器重建含噪重力数据  

Noisy Gravity Data Reconstruction Using the Convolutional Autoencoder

作　　者：王逸宸 柳林涛 许厚泽 WANG Yichen;LIU Lintao;XU Houze(State Key Laboratory of Geodesy and Earth􀆳s Dynamics,Institute of Geodesy and Geophysics,Chinese Academy of Sciences,Wuhan 430077,China)

机构地区：[1]中国科学院精密测量科学与技术创新研究院大地测量与地球动力学国家重点实验室,湖北武汉430077

出　　处：《武汉大学学报（信息科学版）》2022年第4期543-550,共8页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金(Y211641064);(科技部)国家重大科学仪器设备开发专项基金海洋/航空重力仪研制(2011YQ120045)。

摘　　要：卷积自编码器融合了适于处理相同维度数据映射的自编码器神经网络,以及近年来在图像处理领域取得广泛应用的卷积神经网络。基于深度学习处理重力观测数据图像,利用卷积自编码器从含噪声的重力图像中重建重力观测图像。首先,随机建模生成大量不同参数的重力异常体,正演其重力异常,将加入噪声的重力异常和原始重力异常分别作为卷积自编码器的输入和输出进行训练;然后,模拟数据测试表明训练得到的神经网络重建效果良好;最后,用Kauring实验场实测重力数据测试该神经网络的泛化性能,并与快速傅里叶变换(fast Fourier transform,FFT)滤波、db小波(Daubechies wavelet)滤波方法进行了比较。结果表明,训练好的卷积自编码器重建实测重力数据的平均误差小于FFT滤波方法及db小波滤波,且能避免重力异常特征过度滤波而消失,受噪声干扰小于db小波滤波,综合效果理想。Objectives:CAE(convolutional autoencoder)combines the autoencoder neural network structure and the convolutional network structure.This paper processes the gravity data based on the deep learning,and reconstructs the gravity contour image from the noisy gravity data with the CAE.The autoencoder structure contains the equal dimensional input and output data,which goes for the gravity data processing.The convolutional network structure is widely used in image recognition recent years,which can learn and recognize the specific objects in an image.Methods:To create the training set,we generate 1000 hexahedrons with the random triaxial length parameters and the random density to simulate the natural gravity source bodies.The 2D gravity data set for these bodies is fast computed with the gravity forward formula and the noisy gravity data set is generated by adding Gaussian noise to the computed data.Meanwhile the accuracy of the length parameters and density is limited in order to improve the representativeness of the training data set.Hence the 2D gravity data and the noisy data will be output and input data of the CAE.We design 5 layers CAE.The input and output layers both are 26×26.32 and 64 feature maps are generated with 3×3 convolution kernels in the inner layers.The training is executed using RMSProp(root mean square propagation)optimizer.Results:To test the generalization of the trained CAE,the testing set with500 samples is generated in the same way with the training set.The relative error histogram on the testing set shows that the reconstructing error is less than 5%and most of the error is around 0.To test the recognition of the gravity features in the 2D gravity,we test the CAE with simulated gravity data which contain 2and more gravity anomalies.The results show that the CAE can recognize all gravity anomalies in an noisy gravity image and reconstruct them and the output image shows fairly fine reconstruction from the gravity with 10%noise.The measured gravity data of Kauring testing ground are used to

关 键 词：深度学习 卷积自编码器 重力滤波 快速傅里叶变换滤波 小波滤波 

分 类 号：P223[天文地球—大地测量学与测量工程]