A Deep Learning Method for the Prediction of the Index Mechanical Properties and Strength Parameters of Marlstone

Abstract

The index mechanical properties, strength, and stiffness parameters of rock materials (i.e., uniaxial compressive strength, c, ϕ, E, and G) are critical factors in the proper geotechnical design of rock structures. Direct procedures such as field surveys, sampling, and testing are used to estimate these properties, and are time-consuming and costly. Indirect methods have gained popularity in recent years due to their time-saving and highly accurate results, which are comparable to those obtained through direct approaches. This study presents a procedure for establishing a deep learning-based predictive model (DNN) for obtaining the geomechanical characteristics of marlstone samples that have been recovered from the South Pars region of southwest Iran. The model was implemented on a dataset resulting from the execution of numerous geotechnical tests and the evaluation of the geotechnical parameters of a total of 120 samples. The applied model was verified by using benchmark learning classifiers (e.g., Support Vector Machine, Logistic Regression, Gaussian Naïve Bayes, Multilayer Perceptron, Bernoulli Naïve Bayes, and Decision Tree), Loss Function, MAE, MSE, RMSE, and R-square. According to the results, the proposed DNN-based model led to the highest accuracy (0.95), precision (0.97), and the lowest error rate (MAE = 0.13, MSE = 0.11, and RMSE = 0.17). Moreover, in terms of R2, the model was able to accurately predict the geotechnical indices (0.933 for UCS, 0.925 for E, 0.941 for G, 0.954 for c, and 0.921 for φ).

Influence of chemical composition and discontinuities on energy transformation and rock mass behaviour: Insights into geological dynamic

“…The problems are related to underground mines ground stability, foundation design, earthworks, embankments and wellbore stability and tunnelling [15][16][17]. In tunnelling and underground mining, understanding the mechanical properties of rock is paramount for addressing associated challenges [18]. A quantitative evaluation model for assessing the effect of surrounding rocks experiencing rock bursts has been recently developed.…”

A Generalized Limit Equilibrium-Based Platform Incorporating Simplified Bishop, Janbu and Morgenstern–Price Methods for Soil Slope Stability Problems

“…A few of literatures [22,23,24,25] discussed the stability of unsupported rock slopes mostly based on Hoek-Brown model. In some cases, [26,27,28] machine learning techniques are involved in slope stability analysis. Though all these methods can be reliably applied for slope stability analysis, the LE method is still used worldwide because of its simplicity and robustness.…”

A multi-target prediction model for dam seepage field

“…Hou et al (2022) combined time series decomposition and deep learning to predict the deformation of high embankment dams. Azarafza et al (2021), Azarafza et al (2022), andNikoobakht et al (2022) have also done much research work based on deep learning to verify its advantages in landslide susceptibility assessment, landslide susceptibility mapping, and prediction of geotechnical features of rock materials. To give a brief summary, Table 1 is presented to describe about deep learning models, along with the application in dam behavior prediction, as well as their advantages and disadvantages.…”