Search

The traditional artificial neural network (ANN) inversion of electrical resistivity imaging (ERI) based on gradient descent algorithm is known to be inept for its low computation efficiency and does not ensure global convergence. In order to solve above problems, a kernel principal component wavelet neural network (KPCWNN) trained by an improved shuffled frog leaping algorithm (ISFLA) method is proposed in this study. An additional kernel principal component (KPC) layer is applied to reduce the dimensionality of apparent resistivity data and increase the computational efficiency of wavelet neural network (WNN). Meanwhile, a novel ISFLA algorithm is adopted for improving the learning ability and inversion quality of WNN. In the proposed ISFLA, a hybrid LC mutation attractor is used to enhance the exploitation ability and a differential updating rule is used to enhance the exploration ability. Four groups of experiments are considered to demonstrate the feasibility of the proposed inversion method. The inversion results of the synthetic and field examples show that the introduced method is superior to other algorithms in terms of prediction accuracy and computational efficiency, which contribute to better inversion results. [ABSTRACT FROM AUTHOR]

Electrical resistivity imaging (ERI) inversion is a complicated non-linear inversion problem, which is high dimensional and non-convex. Using traditional neural networks to solve the ERI inversion problem has an over-fitting phenomenon and easily falls into local minima. Moreover, the artificial neural network (ANN) model is a black box; its relationships between the inputs and outputs are not easy to interpret. In order to solve these problems, a wavelet packet denoising (WPD) procedure and an improved adaptive neuro-fuzzy inference system (ANFIS) based on Cauchy oscillation shuffled frog leaping algorithm (COSFLA) are proposed in this paper. The wavelet packet denoising methodology is based on soft thresholding and Shannon entropy using a Db10 wavelet which is applied to remove the noise component from the measured apparent resistivity data. Meanwhile, COSFLA is introduced for updating the premise parameters of the ANFIS to improve the learning ability and prediction accuracy of the algorithm. The development of the proposed method and the total inversion process are also presented. The inversion of the synthetic and field examples are provided to demonstrate the feasibility and validity of the proposed method. Additionally, the introduced method is transparent and its if–then rules are easy to understand and interpret. [ABSTRACT FROM AUTHOR]