Abstract. As one of the most active nonlinear inversion methods in transient electromagnetic (TEM) inversion, the back propagation (BP) neural network has high efficiency because the complicated forward model calculation is unnecessary in iteration. The global optimization ability of the particle swarm optimization (PSO) is adopted for amending BP's sensitivity on initial parameters, which avoids it falling into local optimum. A chaotic oscillation inertia weight PSO (COPSO) is proposed in accelerating convergence. The COPSO-BP algorithm performance is validated by two typical testing functions and then by two geoelectric models inversion. The results show that the COPSO-BP method has better accuracy, stability and relative less training times. The proposed algorithm has a higher fitting degree for the data inversion, and it is feasible in geophysical inverse applications.
BP Neural Network and improved Particle Swarm Optimization for Transient Electromagnetic Inversion
