Abstract
Induced polarization (IP) is a near-surface geophysical exploration method. Inverting the electrical properties of the underground medium from surface apparent IP parameters is a highly nonlinear problem. To further improve the accuracy, the artificial neural network (ANN) algorithm is applied to the two-dimensional (2D) IP data inversion for the first time. We firstly produced smooth geo-electric models based on the stochastic medium theory, and obtained the corresponding theoretical responses through forward modelling. Then, we compressed the responses and models through image compression technology. Finally, the above compressed responses and models were used as input and output samples to train an optimal network system for inversion. We tested the algorithm with synthetic examples. The results show that ANN can improve the longitudinal resolution of the inversion results and make the inversion results more focused.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
