Recurrent Neural Network-Based Approach for Sparse Geomagnetic Data Interpolation and Reconstruction

IEEE Access

卷:7

Zheng Liu¹  Huan Liu²  Jian Ge²  Haobin Dong²  Xuming Zeng³  Zhiwen Yuan⁴  Haiyang Zhang⁴  Jun Zhu⁴ 

[1] Faculty of Applied Science, School of Engineering, The University of British Columbia, Okanagan Campus, Kelowna, Canada;

[2] School of Automation, China University of Geosciences, Wuhan, China;

[3] School of Navigation, Wuhan University of Technology, Wuhan, China;

[4] Science and Technology on Near Surface Detection Laboratory, Wuxi, China;

关键词: Interpolation;    geomagnetic data;    deep neural network;    long short-term memory;    modeling;   

DOI  :  10.1109/ACCESS.2019.2903599

来源: DOAJ

【 摘 要 】

Aimed to interpolate the geomagnetic data from under-sampled or missing traces, this paper presented an approach based on recurrent neural network (RNN) techniques to avoid the time & labor-intensive nature of the traditional manual and linear interpolation approaches. In this paper, a deep learning algorithm, long short-term memory (LSTM) was employed to build the precisely model for sparse geomagnetic data interpolation. First, a continuous regression hyperplane was specified to recognize the probably intrinsic relationships between sparse and integral traces by inputting the training data. Afterward, the trained model was tested with 20% of the trained geomagnetic data and other new untrained data for validation. Finally, extensive experiments were conducted for 2D and 3D field data. The results demonstrated that our RNN-based approach was more superior than a classic linear method and a state-of-the-art method, support vector machine (SVM), as the interpolation precision was approximately improved by 10%.

【 授权许可】

Unknown