Discontinuity Predictions of Porosity and Hydraulic Conductivity Based on Electrical Resistivity in Slopes through Deep Learning Algorithms

Electrical resistivity is used to obtain various types of information for soil strata. Hence, the prediction of electrical resistivity is helpful to predict the future behavior of soil. The objective of this study is to apply deep learning algorithms, including deep neural network (DNN), long-short term memory (LSTM), and gated recurrent unit (GRU), to determine the reliability of electrical resistivity predictions to find the discontinuity of porosity and hydraulic conductivity. New DNN-based algorithms, i.e., LSTM-DNN and GRU-DNN, are also applied in this study. The electrical resistivity values are obtained using 101 electrodes installed at 2 m intervals on a mountaintop, and a Wenner array is selected to simplify the electrode installation and measurement. A total of 1650 electrical resistivity values are obtained for one measurement considering the electrode spacing, and accumulated data measured for 15 months are used in the deep learning analysis. A constant ratio of 6:2:2 among the training, validation, and test data, respectively, is used for the measured electrical resistivity, and the hyperparameters in each algorithm are moderated to improve the reliability. Based on the deep learning model results, the distributions of porosity and hydraulic conductivity are deduced, and an average depth of 25 m is estimated for the discontinuity depth. This paper shows that the deep learning technique is well used to predict electrical resistivity, porosity, hydraulic conductivity, and discontinuity depth.

[1]  L. M. Costa Filho,et al.  Saturated-unsaturated analysis of water flow in slopes of Rio de Janeiro, Brazil. Technical note : Comput Geotech V10, N3, 1990, P247–261 , 1991 .

[2]  Masatoshi Ono,et al.  Relationship of tephra stratigraphy and hydraulic conductivity with slide depth in rainfall-induced shallow landslides in Aso Volcano, Japan , 2016, Landslides.

[3]  Anasuya Das,et al.  Estimation of spatial variability of aquifer parameters from geophysical methods: a case study of Sindhudurg district, Maharashtra, India , 2017, Stochastic Environmental Research and Risk Assessment.

[4]  Anita Simic,et al.  Landslide detection and susceptibility mapping using LiDAR and an artificial neural network approach: a case study in the Cuyahoga Valley National Park, Ohio , 2016, Landslides.

[5]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  J. Schön,et al.  Technical Note: A Relation between the Quadrature Component of Electrical Conductivity and the Specific Surface Area of Sedimentary Rocks , 1991 .

[7]  T. Kneib,et al.  Bayesian measurement error correction in structured additive distributional regression with an application to the analysis of sensor data on soil–plant variability , 2017, Stochastic Environmental Research and Risk Assessment.

[8]  B. Vieira,et al.  Landslides in Rio de Janeiro: The role played by variations in soil hydraulic conductivity , 2004 .

[9]  E. Tric,et al.  Identification of the gravitational boundary in weathered gneiss by geophysical survey: La Clapière landslide (France) , 2007 .

[10]  Chang-ming Wang,et al.  Application and comparison of different ensemble learning machines combining with a novel sampling strategy for shallow landslide susceptibility mapping , 2020, Stochastic Environmental Research and Risk Assessment.

[11]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[12]  Mohamed A. Khalil,et al.  Influence of Degree of Saturation in the Electric Resistivity–Hydraulic Conductivity Relationship , 2009 .

[13]  E. Tric,et al.  Geophysical survey to estimate the 3D sliding surface and the 4D evolution of the water pressure on part of a deep seated landslide , 2005 .

[14]  Hyung-Koo Yoon,et al.  Hydraulic Conductivity of Saturated Soil Medium through Time-Domain Reflectometry , 2020, Sensors.

[15]  Filippos Vallianatos,et al.  Estimation of aquifer hydraulic parameters from surficial geophysical methods: A case study of Keritis Basin in Chania (Crete - Greece) , 2007 .

[16]  Nelson Ferreira Fernandes,et al.  Subsurface hydrology of layered colluvium mantles in unchannelled valleys—south-Eastern Brazil , 1994 .

[17]  K. Yin,et al.  Time series analysis and long short-term memory neural network to predict landslide displacement , 2019, Landslides.

[18]  S. Friedman,et al.  Relationships between the Electrical and Hydrogeological Properties of Rocks and Soils , 2005 .

[19]  Linan Zhang,et al.  Short-term travel time prediction by deep learning: A comparison of different LSTM-DNN models , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[20]  Jun Zhou,et al.  Activation functions and their characteristics in deep neural networks , 2018, 2018 Chinese Control And Decision Conference (CCDC).

[21]  V. Lapenna,et al.  Pore water pressures and slope stability: a joint geophysical and geotechnical analysis. , 2008 .

[22]  Yong-Hoon Byun,et al.  Characterization of Cementation Factor of Unconsolidated Granular Materials Through Time Domain Reflectometry with Variable Saturated Conditions , 2019, Materials.

[23]  H. Yoon,et al.  Study of Activation Energy in Soil through Elastic Wave Velocity and Electrical Resistivity , 2017 .

[24]  S. Burns,et al.  Estimating Porosity and Particle Size for Hydraulic Conductivity of Binary Mixed Soils Containing Two Different-Sized Silica Particles , 2018 .

[25]  Quoc V. Le,et al.  Searching for Activation Functions , 2018, arXiv.

[26]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[27]  Young Su Kim,et al.  Four Electrode Resistivity Probe for Porosity Evaluation , 2011 .

[28]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[29]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[30]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[31]  Yuhao Wang,et al.  A deep learning algorithm using a fully connected sparse autoencoder neural network for landslide susceptibility prediction , 2019, Landslides.

[32]  Kyu Sun Kim,et al.  Soil Stiffness Gauge (SSG) and Dynamic Cone Penetrometer (DCP) tests for estimating engineering properties of weathered sandy soils in Korea , 2014 .

[33]  G. E. Archie.  The electrical resistivity log as an aid in determining some reservoir characteristics , 1942 .

[34]  Characterization of alluvium soil using geophysical and sounding methods , 2017 .

[35]  R. C. Velloso,et al.  Saturated-unsaturated analysis of water flow in slopes of Rio de Janeiro, Brazil. , 1990 .

[36]  H. Yoon,et al.  Theoretical relationship between elastic wave velocity and electrical resistivity , 2015 .

[37]  H. Yoon,et al.  Application of electrical conductivity method for adsorption of lead ions by rice husk ash , 2019, Measurement.

[38]  Vipin Kumar,et al.  Generalizing the notion of confidence , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[39]  Estimation of elastic wave velocity and DCPI distributions using outlier analysis , 2018, Engineering Geology.

[40]  Hyung-Koo Yoon,et al.  Analytical and experimental studies to obtain electrical resistivity in a small-scaled laboratory test , 2017 .