Deterministic models have been widely applied in landslide risk assessment (LRA), but they have limitations in obtaining various geotechnical and hydraulic properties. The objective of this study is to suggest a new deterministic method based on machine learning (ML) algorithms. Eight crucial variables of LRA are selected with reference to expert opinions, and the output value is set to the safety factor derived by Mohr–Coulomb failure theory in infinite slope. Linear regression and a neural network based on ML are applied to find the best model between independent and dependent variables. To increase the reliability of linear regression and the neural network, the results of back propagation, including gradient descent, Levenberg–Marquardt (LM), and Bayesian regularization (BR) methods, are compared. An 1800-item dataset is constructed through measured data and artificial data by using a geostatistical technique, which can provide the information of an unknown area based on measured data. The results of linear regression and the neural network show that the special LM and BR back propagation methods demonstrate a high determination of coefficient. The important variables are also investigated though random forest (RF) to overcome the number of various input variables. Only four variables—shear strength, soil thickness, elastic modulus, and fine content—demonstrate a high reliability for LRA. The results show that it is possible to perform LRA with ML, and four variables are enough when it is difficult to obtain various variables.

The cementation factor is necessary to determine porosity via the Archie equation, and its range of values has been suggested in many previous studies. However, the cementation factors in the literature are limited to fully saturated conditions, and it may thus be inaccurate to use the same value in other saturation conditions. The objective of this study is to characterize how the cementation factor varies depending on the saturation percentage. In this study, glass beads and soil are selected as the specimens, and two relative density values, 40% and 80%, are selected. Time domain reflectometry (TDR) is used to obtain both the saturation and electrical resistivity of the specimens. TDR is installed in the cell, and fluid is continuously circulated from the bottom to the top of the porous material for 30 min. The estimated saturation increases with time and the electrical resistivity is reduced during the circulation. Finally, the cementation factor at every saturated stage is determined, and the error ratio based on the porosity is calculated to show the importance of the cementation factor. The results show that there is a high error ratio when an unsuitable cementation factor that does not consider the saturation condition is used. This study demonstrates that the method for determining the actual cementation factor using TDR and the Archie equation can be applied in various saturation conditions.

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.