Adaptive Convolution Neural Networks for Electrical Resistivity Inversion
- 2 September 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (2) , 2055-2066
Abstract
Electrical Resistivity Inversion is an inverse problem that intends to infer the resistivity model from apparent resistivity data. The input and output have the format as the image but are with some unique characteristics that differ from the common natural images. The patterns in resistivity data are no longer spatial invariant. In this case, though the vanilla convolutional neural networks could build the mapping between images, their weight sharing kernels may cause ambiguous situations when coping with the resistivity data. To address this problem, in this work, we directly adapt convolutional kernels to fit for the electrical resistivity inversion task. By analyzing the resistivity data, we found the data patterns corresponding to the same abnormal body will vary with the vertical position change, correspondingly we learn extra offset and amplitude parameters for each vertical position the convolutional kernels applied, to make convolutional kernels transformed to capture the varying patterns. Unlike active convolution and deformable convolution, our learned offsets and amplitudes are sharing at each vertical position, which is neither too free nor too rigid. More importantly, it obeys the inherent characteristics of resistivity data. Finally, through adversarial training, the inversion results are more realistic as the resistivity model. From comprehensive comparisons and studies, our adaptive convolutional neural networks (ACN) outperform the baselines consistently, verifying our assumption and the effectiveness of our proposed method.Keywords
Funding Information
- Science and Technology Program of Department of Transport of Shandong Province (2019B47_2)
- National Natural Science Foundation of China (61702301)
This publication has 45 references indexed in Scilit:
- Synthetic model testing and distributed acquisition dc resistivity results over an unconformity uranium target from the Athabasca Basin, northern SaskatchewanThe Leading Edge, 2008
- The applicability of earth resistivity methods for saline interface definitionJournal of Hydrology, 2006
- One-dimensional inversion of geo-electrical resistivity sounding data using artificial neural networks—a case studyComputers & Geosciences, 2005
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Joint inversion of Wenner and dipole–dipole data to study a gasoline-contaminated soilJournal of Applied Geophysics, 2003
- The development of DC resistivity imaging techniquesComputers & Geosciences, 2001
- A New Survey Design for 3D IP Inversion Modelling at Copper HillExploration Geophysics, 2001
- Inversion of DC resistivity data using neural networksGeophysical Prospecting, 2001
- ERT monitoring of environmental remediation processesMeasurement Science and Technology, 1996
- Use of the Electrical Resistivity Method for Investigating Geologic and Hydrologic Conditions in Santa Clara County, CaliforniaGroundwater, 1968