Pixel- and Model-Based Microwave Inversion With Supervised Descent Method for Dielectric Targets

We present a general framework of applying supervised descent method (SDM) to the pixel- and model-based full-wave inversion of microwave data for dielectric targets. SDM is a machine learning approach that utilizes the learned descent directions to reconstruct models. In this article, we study the pixel-based inversion with an online regularization scheme, and the model-based inversion with the parametric level set approach. Furthermore, an online restart scheme is studied to further reduce the data residual. In addition, we investigate the generalization ability of this machine-learning algorithm. In the numerical test, the pixel-based SDM inversion are used to process both single- or multi-frequency data, and the model-based inversion are performed on data with limited observations. Both synthetic and experimental results show good accuracy, speed, and generalization ability of this algorithm. SDM may provide us a potential way to improve reconstruction quality in nonlinear inversion through information fusion of measured data, microwave physics, and various prior information.

[1]  P. Rocca,et al.  Evolutionary optimization as applied to inverse scattering problems , 2009 .

[2]  Xudong Chen,et al.  Computational Methods for Electromagnetic Inverse Scattering , 2018 .

[3]  Vladimir Puzyrev,et al.  Deep learning electromagnetic inversion with convolutional neural networks , 2018, Geophysical Journal International.

[4]  Eric L. Miller,et al.  Parametric Level Set Methods for Inverse Problems , 2010, SIAM J. Imaging Sci..

[5]  A. Abubakar,et al.  A Three-Dimensional Model-Based Inversion Algorithm Using Radial Basis Functions for Microwave Data , 2012, IEEE Transactions on Antennas and Propagation.

[6]  P. M. Berg,et al.  Extended contrast source inversion , 1999 .

[7]  Fernando De la Torre,et al.  Supervised Descent Method and Its Applications to Face Alignment , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  A. Abubakar,et al.  Multiplicative regularization for contrast profile inversion , 2003 .

[9]  Margaret Cheney,et al.  The Linear Sampling Method and the MUSIC Algorithm , 2001 .

[10]  Jianwei Ma,et al.  Velocity model building with a modified fully convolutional network , 2018, SEG Technical Program Expanded Abstracts 2018.

[11]  Xudong Chen,et al.  Subspace-Based Optimization Method for Solving Inverse-Scattering Problems , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[13]  Albert Tarantola,et al.  Inverse problem theory - and methods for model parameter estimation , 2004 .

[14]  Rui Guo,et al.  Supervised Descent Learning Technique for 2-D Microwave Imaging , 2019, IEEE Transactions on Antennas and Propagation.

[15]  Li Jun Jiang,et al.  Two-Step Enhanced Deep Learning Approach for Electromagnetic Inverse Scattering Problems , 2019, IEEE Antennas and Wireless Propagation Letters.

[16]  Xudong Chen,et al.  Physics-Inspired Convolutional Neural Network for Solving Full-Wave Inverse Scattering Problems , 2019, IEEE Transactions on Antennas and Propagation.

[17]  Christophe Reboud,et al.  Real-Time NDT-NDE Through an Innovative Adaptive Partial Least Squares SVR Inversion Approach , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Guangyou Fang,et al.  Application of supervised descent method to transient electromagnetic data inversion , 2019, GEOPHYSICS.

[19]  Christin Wirth.  The Essential Physics of Medical Imaging , 2003, European Journal of Nuclear Medicine and Molecular Imaging.

[20]  Andreas Kirsch,et al.  Characterization of the shape of a scattering obstacle using the spectral data of the far field operator , 1998 .

[21]  Jonas Adler,et al.  Solving ill-posed inverse problems using iterative deep neural networks , 2017, ArXiv.

[22]  Paolo Rocca,et al.  Learning-by-examples techniques as applied to electromagnetics , 2018 .

[23]  Matteo Pastorino,et al.  Microwave imaging based on a Markov random field model , 1994 .

[24]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[25]  Amir Adler,et al.  Deep-learning tomography , 2018 .

[26]  C. Eyraud,et al.  Free space experimental scattering database continuation: experimental set-up and measurement precision , 2005 .

[27]  O. Dorn,et al.  Level set methods for inverse scattering , 2006 .

[28]  W. Chew.  Waves and Fields in Inhomogeneous Media , 1990 .

[29]  A. Abubakar,et al.  A General Framework for Constraint Minimization for the Inversion of Electromagnetic Measurements , 2004 .

[30]  Aria Abubakar,et al.  Application of a two-and-a-half dimensional model-based algorithm to crosswell electromagnetic data inversion , 2010 .

[31]  Li Jun Jiang,et al.  Enhanced Deep Learning Approach Based on the Deep Convolutional Encoder–Decoder Architecture for Electromagnetic Inverse Scattering Problems , 2020, IEEE Antennas and Wireless Propagation Letters.

[32]  Dino Giuli,et al.  Microwave tomographic inversion technique based on stochastic approach for rainfall fields monitoring , 1999, IEEE Trans. Geosci. Remote. Sens..

[33]  A. Massa,et al.  Parallel GA-based approach for microwave imaging applications , 2005, IEEE Transactions on Antennas and Propagation.

[34]  W. Chew,et al.  Reconstruction of two-dimensional permittivity distribution using the distorted Born iterative method. , 1990, IEEE transactions on medical imaging.

[35]  Asimina Kiourti,et al.  A Novel Method to Mitigate Real–Imaginary Image Imbalance in Microwave Tomography , 2020, IEEE Transactions on Biomedical Engineering.

[36]  Xudong Chen,et al.  Subspace-Based Distorted-Born Iterative Method for Solving Inverse Scattering Problems , 2017, IEEE Transactions on Antennas and Propagation.

[37]  Wlodek Kofman,et al.  Microwave imaging from experimental data within a Bayesian framework with realistic random noise , 2009 .

[38]  Fan Yang,et al.  Microwave Inversion for Sparse Data using Descent Learning Technique , 2019, 2019 13th European Conference on Antennas and Propagation (EuCAP).

[39]  Ali Mohammad-Djafari,et al.  Bayesian approach with the maximum entropy principle in image reconstruction from microwave scattered field data , 1994, IEEE Trans. Medical Imaging.

[40]  P. M. van den Berg,et al.  TWO- AND THREE-DIMENSIONAL ALGORITHMS FOR MICROWAVE IMAGING AND INVERSE SCATTERING , 2003 .

[41]  Fan Yang,et al.  First arrival traveltime tomography using supervised descent learning technique , 2019, Inverse Problems.

[42]  Andrea Boni,et al.  An innovative real-time technique for buried object detection , 2003, IEEE Trans. Geosci. Remote. Sens..

[43]  Ioannis T. Rekanos,et al.  Neural-network-based inverse-scattering technique for online microwave medical imaging , 2002 .

[44]  Lianlin Li,et al.  DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scattering , 2018, IEEE Transactions on Antennas and Propagation.

[45]  Miguel Moscoso,et al.  Structural level set inversion for microwave breast screening , 2010 .

[46]  Jianming Jin.  Theory and Computation of Electromagnetic Fields , 2010 .

[47]  M. Salucci,et al.  DNNs as Applied to Electromagnetics, Antennas, and Propagation—A Review , 2019, IEEE Antennas and Wireless Propagation Letters.

[48]  P. M. Berg,et al.  A contrast source inversion method , 1997 .

[49]  Xudong Chen,et al.  Deep-Learning Schemes for Full-Wave Nonlinear Inverse Scattering Problems , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[50]  Avrim Blum,et al.  Foundations of Data Science , 2020 .