Articles | Volume 26, issue 4
https://doi.org/10.5194/npg-26-445-2019
https://doi.org/10.5194/npg-26-445-2019
Research article
 | 
26 Nov 2019
Research article |  | 26 Nov 2019

A fast approximation for 1-D inversion of transient electromagnetic data by using a back propagation neural network and improved particle swarm optimization

Ruiyou Li, Huaiqing Zhang, Nian Yu, Ruiheng Li, and Qiong Zhuang

Download

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision
AR by Huaiqing Zhang on behalf of the Authors (28 Sep 2019)  Author's response   Manuscript 
ED: Referee Nomination & Report Request started (30 Sep 2019) by Norbert Marwan
RR by Anonymous Referee #2 (08 Oct 2019)
RR by Anonymous Referee #1 (15 Oct 2019)
ED: Publish subject to minor revisions (review by editor) (17 Oct 2019) by Norbert Marwan
AR by Huaiqing Zhang on behalf of the Authors (19 Oct 2019)  Author's response   Manuscript 
ED: Publish subject to minor revisions (review by editor) (22 Oct 2019) by Norbert Marwan
AR by Huaiqing Zhang on behalf of the Authors (22 Oct 2019)
ED: Publish as is (24 Oct 2019) by Norbert Marwan
AR by Huaiqing Zhang on behalf of the Authors (25 Oct 2019)  Manuscript 
Download
Short summary
The chaotic-oscillation inertia weight back propagation (COPSO-BP) algorithm is proposed for transient electromagnetic inversion. The BP's initial weight and threshold parameters were trained by COPSO, overcoming the BP falling into a local optimum. Inversion of the layered geoelectric model showed that the COPSO-BP method is accurate and stable and needs less training time. It can be used in 1-D direct current sounding, 1-D magnetotelluric sounding, seismic-wave impedance and source detection.