BP neural network and improved differential evolution for transient electromagnetic inversion

Abstract In the transient electromagnetic (TEM) inversion, the BP neural network method has high efficiency owing to avoid the complicated forward model calculation in every iteration. The global optimization ability of the differential evolution Algorithm (DE) is adopted for amending BP's sensitive to initial parameters. A chaotic mutation and crossover with constraint factor DE (CCDE) is proposed in improving the global optimization ability. The CCDE-BP algorithm performance is validated by two typical testing functions and then by two geoelectric models inversion. The results show that the CCDE-BP method has better inversion speed, accuracy and stability yet with higher fitting degree. It is feasible in geophysical inverse applications.

[1]  Eric Mandolesi,et al.  A reversible-jump Markov chain Monte Carlo algorithm for 1D inversion of magnetotelluric data , 2018, Comput. Geosci..

[2]  Zexuan Zhu,et al.  Adaptive multiple-elites-guided composite differential evolution algorithm with a shift mechanism , 2018, Inf. Sci..

[3]  Li Dong,et al.  An ICPSO-RBFNN nonlinear inversion for electrical resistivity imaging , 2016 .

[4]  Kamel Baddari,et al.  Application of a radial basis function artificial neural network to seismic data inversion , 2009, Comput. Geosci..

[5]  Zhang,et al.  Inversion of 3D density interface with PSO-BP method , 2016 .

[6]  R. K. Tiwari,et al.  ANN based inversion of DC resistivity data for groundwater exploration in hard rock terrain of western Maharashtra (India) , 2012 .

[7]  L. Coelho.  Reliability–redundancy optimization by means of a chaotic differential evolution approach , 2009 .

[8]  Xiaohui Yuan,et al.  Hydrothermal scheduling using chaotic hybrid differential evolution , 2008 .

[9]  Fuli Wang,et al.  Optimization of dynamic economic dispatch with valve-point effect using chaotic sequence based differential evolution algorithms , 2011 .

[10]  Ying Wang,et al.  Chaotic differential evolution methods for dynamic economic dispatch with valve-point effects , 2011, Eng. Appl. Artif. Intell..

[11]  S. B. Singh,et al.  Neural network modeling and prediction of resistivity structures using VES Schlumberger data over a geothermal area , 2013, Comput. Geosci..

[12]  Ling‐Yun Zhang,et al.  The Application of ABP Method in High‐Density Resistivity Method Inversion , 2011 .

[13]  Li Dong,et al.  Electrical resistivity imaging inversion: An ISFLA trained kernel principal component wavelet neural network approach , 2018, Neural Networks.

[14]  J. A. Vrugt,et al.  Two-dimensional probabilistic inversion of plane-wave electromagnetic data: Methodology, model constraints and joint inversion with electrical resistivity data , 2014, 1701.02540.

[15]  O. L. Johnson,et al.  Application of Artificial Neural Network for the Inversion of Electrical Resistivity Data , 2017 .

[16]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[17]  Li Dong,et al.  Nonlinear inversion of electrical resistivity imaging using pruning Bayesian neural networks , 2016, Applied Geophysics.

[18]  Muhammad Khurram Khan,et al.  An effective memetic differential evolution algorithm based on chaotic local search , 2011, Inf. Sci..

[19]  Y. Srinivas,et al.  A robust behavior of Feed Forward Back propagation algorithm of Artificial Neural Networks in the application of vertical electrical sounding data inversion , 2012 .

[20]  Wan Ahmad Tajuddin Wan Abdullah,et al.  Using artificial neural networks to invert 2D DC resistivity imaging data for high resistivity contrast regions: A MATLAB application , 2009, Comput. Geosci..

[21]  A Stanley Raj,et al.  A novel and generalized approach in the inversion of geoelectrical resistivity data using Artificial Neural Networks (ANN) , 2014, Journal of Earth System Science.