Convolutional neural networks with SegNet architecture applied to three-dimensional tomography of subsurface electrical resistivity. CNN-3D-ERT

2021 ◽  
Author(s):  
M T Vu ◽  
A Jardani
Keyword(s):  
Neural Networks ◽  
Electrical Resistivity ◽  
Convolutional Neural Networks ◽  
Apparent Resistivity ◽  
Electrical Resistivity Tomography ◽  
Learning Algorithm ◽  
Inverse Operator ◽  
Feature Maps ◽  
Resistivity Tomography ◽  
Subsurface Resistivity

Summary In general, the inverse problem of electrical resistivity tomography is treated using a deterministic algorithm to find a model of subsurface resistivity that can numerically match the apparent resistivity data acquired at the ground surface and has a smooth distribution that has been introduced as prior information. In this paper, we propose a new deep-learning algorithm for processing the 3D reconstruction of electrical resistivity tomography (ERT). This approach relies on the approximation of the inverse operator considered as a non-linear function linking the section of apparent resistivity as input and the underground distribution of electrical resistivity as output. This approximation is performed with a large amount of known data to obtain an accurate generalization of the inverse operator by identifying during the learning process a set of parameters assigned to the neural networks. To train the network, the subsurface resistivity models are theoretically generated by a geostatistical anisotropic Gaussian generator, and their corresponding apparent resistivity by solving numerically 3D Poisson's equation. These data are formed in a way to have the same size and trained on the convolutional neural networks with Segnet architecture containing a 3-level encoder and decoder network ending with a regression layer. The encoders including the convolutional, max-pooling and nonlinear activation operations, are sequentially performed to extract the main features of input data in lower resolution maps. On the other side, the decoders are dedicated to upsampling operations in concatenating with feature maps transferred from encoders to compensate the loss of resolution. The tool has been successfully validated on different synthetic cases and with particular attention to how data quality in terms of resolution and noise affect the effectiveness of the approach.

scholarly journals Experimental Studies on the Changes in Resistivity and Its Anisotropy Using Electrical Resistivity Tomography

2012 ◽  
Vol 2012 ◽  
pp. 1-10
Author(s):  
Tao Zhu ◽  
Jian-Guo Zhou ◽  
Jin-Qi Hao
Keyword(s):  
Electrical Resistivity ◽  
Apparent Resistivity ◽  
Large Scale ◽  
Electrical Resistivity Tomography ◽  
Experimental Studies ◽  
Major Axis ◽  
Residual Resistivity ◽  
Resistivity Tomography ◽  
D Region ◽  
Resistivity Anisotropy

Three measuring lines were arranged on one of free planes of magnetite cuboid samples. Apparent resistivity data were acquired by MIR-2007 resistivity meter when samples were under uniaxial compression of servocontrol YAW-5000F loadingmachine in laboratory. Then we constructed the residual resistivity images using electrical resistivity tomography (ERT) and plotted the diagrams of apparent resistivity anisotropy coefficient (ARAC)λ∗and the included angleαbetween the major axis of apparent resistivity anisotropy ellipse and the axis of load with pressure and effective depth. Our results show that with increasing pressure, resistivity and the decreased (D region) and increased (I region) resistivity regions have complex behaviors, but when pressure is higher than a certain value, the average resistivity decrease and the area of D region expand gradually in all time with the increase of pressure, which may be significant to the monitoring and prediction of earthquake, volcanic activities, and large-scale geologic motions. The effects of pressure onλ∗andαare not very outstanding for dry magnetite samples.

scholarly journals Two-dimensional Electrical Resistivity Tomography of Bitumen Occurrence in Agbabu, Southwest Nigeria

2019 ◽  
pp. 1-9
Author(s):  
O. F. Ogunlana ◽  
O. M. Alile ◽  
O. J. Airen
Keyword(s):  
Electrical Resistivity ◽  
Apparent Resistivity ◽  
Electrical Resistivity Tomography ◽  
Electrode Spacing ◽  
Southwestern Nigeria ◽  
Resistivity Tomography ◽  
2D Inversion ◽  
Earth Resistivity ◽  
Southwest Nigeria ◽  
Resistivity Meter

The Electrical Resistivity Tomography (ERT) data was acquired within the area suspected to have high potential for bitumen occurrence using the Wenner-Schlumberger configuration in Agbabu, southwestern Nigeria. PASI 16GL-N Earth resistivity meter instrument was used to acquire data along five (5) traverses with 5m electrode spacing and traverses length of 150m. The apparent resistivity values obtained was processed using RES2DINV software which helped to automatically obtain the 2D inversion model of the subsurface. This study has shown the occurrence of bitumen between the depth of 13.4m and 9.93m for Traverses 1, 2, 3 and Traverses 4, 5 respectively in a 2-Dimensional electrical resistivity images for boreholes with a depth of about 18m. The results indicate that the bitumen is characterized by good lateral continuity and is sufficiently thick for commercial exploitation.

scholarly journals Electrical resistivity tomography for aquifer imaging

2000 ◽  
Vol 22 ◽  
Author(s):  
Dipak Raj Pant
Keyword(s):  
Electrical Resistivity ◽  
Cross Section ◽  
Electrical Resistance ◽  
Apparent Resistivity ◽  
Electrical Resistivity Tomography ◽  
Field Experiments ◽  
Region Of Interest ◽  
Electrical Energy ◽  
Resistivity Tomography ◽  
Computerised Analysis

Aspects related to the development of a technique called electrical resistance tomography for producing two- or three­ dimensional subsurface images of an aquifer have been discussed. The technique is based on the automated measurement and computerised analysis of electrical resistivity changes caused by natural or man-made processes. A subsurface region of the aquifer to be studied is sampled by transmitting electrical energy through it along many paths of known orientations, and the apparent resistivity data derived are used to construct a cross-section al image of the region of interest. The physical model experiments and field experiments show that the presented method is effective and flexible for crosshole resistivity imaging of aquifer with bipole-bipole electrode configurations.

scholarly journals Exploring the regolith with electrical resistivity tomography in largescale surveys: electrode spacing related issues and possibility

2020 ◽  
Author(s):  
Laurent Gourdol ◽  
Rémi Clément ◽  
Jérôme Juilleret ◽  
Laurent Pfister ◽  
Christophe Hissler
Keyword(s):  
Electrical Resistivity ◽  
Apparent Resistivity ◽  
Large Scale ◽  
Electrical Resistivity Tomography ◽  
Subsurface Layer ◽  
Electrode Spacing ◽  
High Resistivity ◽  
Constant Thickness ◽  
Resistivity Tomography

Abstract. Within the Critical Zone, regolith plays a key role in the fundamental hydrological functions of water collection, storage, mixing and release. Electrical Resistivity Tomography (ERT) is recognized as a remarkable tool for characterizing the geometry and properties of the regolith, overcoming limitations inherent to conventional borehole-based investigations. For exploring shallow layers, a small electrode spacing (ES) will provide a denser set of apparent resistivity measurements of the subsurface. As this option is cumbersome and time-consuming, smaller ES – albeit offering poorer shallow apparent resistivity data – are often preferred for large horizontal ERT surveys. To investigate the negative trade-off between larger ES and reduced accuracy of the inverted ERT images for shallow layers, we use a set of synthetic conductive/resistive/conductive three-layered soil–saprock/saprolite–bedrock models in combination with a reference field dataset. Our results suggest that an increase in ES causes a deterioration of the accuracy of the inverted ERT images in terms of both resistivity distribution and interface delineation and, most importantly, that this degradation increases sharply when the ES exceeds the thickness of the top subsurface layer. This finding, which is obvious for the characterization of shallow layers, is also relevant even when solely aiming for the characterization of deeper layers. We show that an oversized ES leads to overestimations of depth to bedrock and that this overestimation is even more important for subsurface structures with high resistivity contrast. To overcome this limitation, we propose adding interpolated levels of surficial apparent resistivity relying on a limited number of ERT profiles with a smaller ES. We demonstrate that our protocol significantly improves the accuracy of ERT profiles when using large ES, provided that the top layer has a rather constant thickness and resistivity. For the specific case of large-scale ERT surveys the proposed upgrading procedure is cost-effective in comparison to protocols based on small ES.

scholarly journals STRUCTURE OF FREEZING TALIK UNDER LAKE AT THE PARISENTO FIELD STATION (GYDAN PENINSULA) ACCORDING TO ELECTRICAL RESISTIVITY TOMOGRAPHY

2019 ◽  
Vol 2 (2) ◽  
pp. 103-110
Author(s):  
Alexandr Shein ◽  
Vladimir Olenchenko ◽  
Yaroslav Kamnev ◽  
Anton Sinitskiy
Keyword(s):  
Electrical Resistivity ◽  
Apparent Resistivity ◽  
Electrical Resistivity Tomography ◽  
Two Dimensional ◽  
Resistivity Tomography ◽  
Field Station ◽  
Approximate Rate

The article presents the results of studies of freezing talik under lake with using of electrical resistivity tomography. The research was conducted on one of paleolake – khasyrey. The measurements performed in two perpendicular profiles by pole-dipole array with a maximum spacing of 435 m. According to results of two-dimensional inversion, an area of low electrical resistivity of rocks at a depth of 25-30 m associated with a freezing talik under lake was identified. It was determined that the depth of freezing within drained lake for the period from 1996 to 2018 is 17-22 m. The approximate rate of freezing is 1 m/year. Formation of talik have a resistance of 5-15 Ω·m. Frozen formations in the contours of young paleolake have apparent resistivity hundreds Ω·m. Within the boundaries of the more ancient khasyrey apparent resistivity of the frozen rocks up to several thousand Ω·m.

scholarly journals An Extension of the Data-Adaptive Probability-Based Electrical Resistivity Tomography Inversion Method (E-PERTI)

Geosciences ◽  
2020 ◽  
Vol 10 (10) ◽  
pp. 380
Author(s):  
Marilena Cozzolino ◽  
Paolo Mauriello ◽  
Domenico Patella
Keyword(s):  
Electrical Resistivity ◽  
Apparent Resistivity ◽  
Electrical Resistivity Tomography ◽  
Inversion Method ◽  
Resistivity Tomography ◽  
Synthetic Test ◽  
Statistical Determination ◽  
Data Adaptive ◽  
Tomography Inversion

About a decade ago, the PERTI algorithm was launched as a tool for a data-adaptive probability-based analysis of electrical resistivity tomography datasets. It proved to be an easy and versatile inversion method providing estimates of the resistivity values within a surveyed volume as weighted averages of the whole apparent resistivity dataset. In this paper, with the aim of improving the interpretative process, the PERTI method is extended by exploiting some peculiar aspects of the general theory of probability. Bernoulli’s conceptual scheme is assumed to comply with any resistivity dataset, which allows a multiplicity of mutually independent subsets to be extracted and analysed singularly. A standard least squares procedure is at last adopted for the statistical determination of the model resistivity at each point of the surveyed volume as the slope of a linear equation that relates the multiplicity of the resistivity estimates from the extracted data subsets. A 2D synthetic test and a field apparent resistivity dataset collected for archaeological purposes are discussed using the new extended PERTI (E-PERTI) approach. The comparison with the results from the original PERTI shows that by the E-PERTI approach a significantly greater robustness against noise can be achieved, besides a general optimisation of the estimates of the most probable resistivity values.

Electrical Resistivity Tomography Concept for CO2 Injection Monitoring at the Svelvik CO2 Field Lab

2020 ◽  
Author(s):  
Tobias Raab ◽  
Wolfgang Weinzierl ◽  
Dennis Rippe ◽  
Bernd Wiese ◽  
Cornelia Schmidt-Hattenberger
Keyword(s):  
Electrical Resistivity ◽  
Apparent Resistivity ◽  
Electrical Resistivity Tomography ◽  
Co2 Storage ◽  
Carbon Capture And Storage ◽  
Integrated Approach ◽  
Reservoir Modeling ◽  
Co2 Injection ◽  
Target Area ◽  
Resistivity Tomography

<p>Carbon Capture and Storage technology is considered to be able to contribute to a carbon neutral society and is again receiving increased attention in the efforts to reduce CO<sub>2 </sub>emissions. To ensure safe operation of such CO<sub>2</sub> storage projects, reliable monitoring technologies are required. Due to the generally high electrical resistivity contrast between CO<sub>2</sub> and formation water, Electrical Resistivity Tomography (ERT) can be considered one of the most effective geophysical techniques in the monitoring of CO<sub>2</sub> migration in the subsurface.</p><p>Within the ERA-NET co-funded ACT project Pre-ACT (Pressure control and conformance management for safe and efficient CO2 storage - Accelerating CCS Technologies) a CO<sub>2</sub> injection and monitoring experiment was planned at the Svelvik CO<sub>2</sub> Field Lab, located on the Svelvik ridge at the outlet of the Drammensfjord in Norway. The Svelvik field lab consists of four 100 m deep monitoring wells, drilled in July 2019, surrounding an existing well used for brine and CO<sub>2</sub> injection. Each monitoring well is equipped with modern sensing systems including five types of fiber-optic cables, conventional and capillary pressure monitoring systems, as well as 16 ERT electrodes with a spacing of five meters.</p><p>With 64 installed electrodes, a large number of measurement configurations is possible. We combine the free and open-source geophysical modeling library pyGIMLI with ECLIPSE reservoir modeling to simulate the expected behavior of all cross-well electrode configurations during a CO<sub>2</sub> injection experiment. Simulated CO<sub>2 </sub>saturations are converted to changes in apparent resistivity using Archie's law. Different considerations have to be made to select a suitable set of electrode configurations, i.e. not too large geometric factors, maximum response to the predicted change, as well as sensitivity in the target area. We select sets of configurations based on different criteria, i.e. the ratio between the measured change in resistivity in relation to the geometric factor, the maximum change in apparent resistivity, and maximum sensitivity in the target area. The individually selected measurement schedules are tested by inverting them with different assumed data errors. The numerical results show adequate resolution of the CO<sub>2</sub> plume.</p><p>The CO<sub>2</sub> injection took place between 27th October 2019 and 5th November 2019. Approximately two metric tonnes of CO<sub>2</sub> were injected in 65 m depth. Preliminary field results indicate a considerably lower response than predicted by our model. These discrepancies can potentially be explained by oversimplified simulations as well as operational uncertainties. Results from baseline and repeat surveys can therefore support an integrated approach towards a revised static and dynamic model for the test site.</p><p><strong>Acknowledgements:</strong></p><p>This work was produced within the SINTEF-coordinated Pre-ACT project (Project No. 271497) funded by RCN (Norway), Gassnova (Norway), BEIS (UK), RVO (Netherlands), and BMWi (Germany) and co-funded by the European Commission under the Horizon 2020 programme, ACT Grant Agreement No 691712. We also acknowledge industry partners Total, Equinor, Shell, TAQA.</p><p>Finally, we thank the SINTEF-owned Svelvik CO<sub>2</sub> Field Lab (funded by ECCSEL through RCN, with additional support from Pre-ACT and SINTEF) for assistance during installations and for financial support.</p>

scholarly journals Exploring the regolith with electrical resistivity tomography in large-scale surveys: electrode spacing-related issues and possibility

2021 ◽  
Vol 25 (4) ◽  
pp. 1785-1812
Author(s):  
Laurent Gourdol ◽  
Rémi Clément ◽  
Jérôme Juilleret ◽  
Laurent Pfister ◽  
Christophe Hissler
Keyword(s):  
Electrical Resistivity ◽  
Apparent Resistivity ◽  
Large Scale ◽  
Electrical Resistivity Tomography ◽  
Subsurface Layer ◽  
Electrode Spacing ◽  
High Resistivity ◽  
Constant Thickness ◽  
Resistivity Tomography

Abstract. Within the critical zone, regolith plays a key role in the fundamental hydrological functions of water collection, storage, mixing and release. Electrical resistivity tomography (ERT) is recognized as a remarkable tool for characterizing the geometry and properties of the regolith, overcoming limitations inherent to conventional borehole-based investigations. For exploring shallow layers, a small electrode spacing (ES) will provide a denser set of apparent resistivity measurements of the subsurface. As this option is cumbersome and time-consuming, larger ES – albeit offering poorer shallow apparent resistivity data – is often preferred for large horizontal ERT surveys. To investigate the negative trade-off between larger ES and reduced accuracy of the inverted ERT images for shallow layers, we use a set of synthetic “conductive–resistive–conductive” three-layered soil–saprock/saprolite–bedrock models in combination with a reference field dataset. Our results suggest that an increase in ES causes a deterioration of the accuracy of the inverted ERT images in terms of both resistivity distribution and interface delineation and, most importantly, that this degradation increases sharply when the ES exceeds the thickness of the top subsurface layer. This finding, which is obvious for the characterization of shallow layers, is also relevant even when solely aiming for the characterization of deeper layers. We show that an oversized ES leads to overestimations of depth to bedrock and that this overestimation is even more important for subsurface structures with high resistivity contrast. To overcome this limitation, we propose adding interpolated levels of surficial apparent resistivity relying on a limited number of ERT profiles with a smaller ES. We demonstrate that our protocol significantly improves the accuracy of ERT profiles when using large ES, provided that the top layer has a rather constant thickness and resistivity. For the specific case of large-scale ERT surveys the proposed upgrading procedure is cost-effective in comparison to protocols based on small ES.

scholarly journals Development of an Underground Tunnels Detection Algorithm for Electrical Resistivity Tomography Based on Deep Learning

2022 ◽  
Vol 12 (2) ◽  
pp. 639
Author(s):  
Yin-Chun Hung ◽  
Yu-Xiang Zhao ◽  
Wei-Chen Hung
Keyword(s):  
Artificial Intelligence ◽  
Electrical Resistivity ◽  
Deep Learning ◽  
Electrical Resistivity Tomography ◽  
Learning Algorithm ◽  
Detection Algorithm ◽  
Image Resolution ◽  
Resistivity Tomography ◽  
Military Installations ◽  
Deep Learning Algorithm

Kinmen Island was in a state of combat readiness during the 1950s–1980s. It opened for tourism in 1992, when all troops withdrew from the island. Most military installations, such as bunkers, anti airborne piles, and underground tunnels, became deserted and disordered. The entries to numerous underground bunkers are closed or covered with weeds, creating dangerous spaces on the island. This study evaluates the feasibility of using Electrical Resistivity Tomography (ERT) to detect and discuss the location, size, and depth of underground tunnels. In order to discuss the reliability of the 2D-ERT result, this study built a numerical model to validate the correctness of in situ measured data. In addition, this study employed the artificial intelligence deep learning technique for reprocessing and predicting the ERT image and discussed using an artificial intelligence deep learning algorithm to enhance the image resolution and interpretation. A total of three 2D-ERT survey lines were implemented in this study. The results indicate that the three survey lines clearly show the tunnel location and shape. The numerical simulation results also indicate that using 2D-ERT to survey underground tunnels is highly feasible. Moreover, according to a series of studies in Multilayer Perceptron of deep learning, using deep learning can clearly show the tunnel location and path and effectively enhance the interpretation ability and resolution for 2D-ERT measurement results.

Sign in / Sign up

Export Citation Format

Share Document