摘要
磁异常化极是磁测数据处理的重要基础工作,低纬度磁异常化极运算不稳定.深度学习是一种有效解决不稳定问题的数据驱动方法.然而,现有基于深度学习的位场数据处理仅以位场响应作为输入,缺乏场景外样本数据的通用性,往往导致深度学习网络预测结果的泛化性能不足.因此,为了克服这一问题以及进一步提高低纬度磁异常化极的精度.受“知识&数据”联合驱动深度学习网络结构的启发,本文提出一种基于初始模型约束的低纬度磁异常化极全卷积神经网络结构.该网络结构的输入包含两部分,一部分为低纬度磁异常,另外一部分为初始模型,网络输出为垂直磁化方向磁异常.训练与测试的磁异常数据采用基于网格点格架函数的空间域快速正演生成,以及对低纬度磁异常采用稳定的频率转换来获取初始模型,另外本文对数据集中10%的随机样本加入了5%的高斯噪声,以此增强全卷积神经网络结构的鲁棒性.理论模型试验验证了本文所提方法的有效性、精确性以及鲁棒性.最后,将本文方法应用于实际磁测数据,取得了良好的效果.
Reduction-to-the-pole(RTP)is a vital basic work of magnetic survey data processing.The operation of RTP at low latitude is unstable.Deep learning is an effective data-driven method to solve unstable problems.However,the existing potential field data processing based on deep learning only takes the field response as input.It lacks the universality of off-scene sample data,which often leads to the insufficient generalization performance of prediction results of the deep learning network.Therefore,in order to overcome this problem and further improve the accuracy of RTP at the low latitude,inspired by the“knowledge&data”co-driven deep learning network structure,we propose a fully convolutional RTP network structure for low latitude magnetic anomalies based on initial model constraints.The input of the network structure consists of two parts,one is the low latitude magnetic anomaly,the other is the initial model,and the output is the magnetic anomaly in the direction of vertical magnetization.The magnetic anomaly data of training and testing were generated by fast forward modeling in the spatial domain based on grid point lattice function,and the initial model was obtained by stable frequency conversion for low latitude magnetic anomaly.In addition,5%Gaussian noise is added to 10%random samples of the data set to strengthen the robustness of fully convolutional network structure.Theoretical model tests verify the effectiveness,accuracy and robustness of the proposed method.Finally,the proposed method is applied to magnetic data of original data,and good results are obtained.
作者
张志厚
刘慰心
石泽玉
张健
路润琪
谢小国
徐正宣
张天一
ZHANG ZhiHou;LIU WeiXin;SHI ZeYu;ZHANG Jian;LU RunQi;XIE XiaoGuo;XU ZhengXuan;ZHANG TianYi(Faculty of Geosciences and Environmental Engineering,Southwest Jiaotong University,Chengdu 611756,China;MOE Key Laboratory of High-speed Railway Engineering,Southwest Jiaotong University,Chengdu 610031,China;Sichuan Hua Di Building Engineering Co.,Ltd.,Chengdu 610081,China;Chengdu Center of Hydrogeology and Engineering Geology of Sichuan Provincial Geology and Mineral Resources Bureau,Chengdu 610081,China;Chengdu Geological Survey Geotechnical Engineering Co.,Ltd.,Chengdu 610000,China)
出处
《地球物理学报》
SCIE
EI
CAS
CSCD
北大核心
2023年第1期412-429,共18页
Chinese Journal of Geophysics
基金
四川省科技厅科技计划项目(2021YJ0031)
国家重点研发计划项目(2018YFC1505401)
成都市重点研发支撑计划项目(2022-YF05-00004-SN)
中国中铁股份有限公司科技研究开发计划项目(CZ01-重点-05)联合资助.
关键词
低纬度磁异常
初始模型
深度学习
化极
联合驱动
Low-latitude magnetic anomaly
Initial model
Deep learning
Reduction-to-the-pole
Joint drive
