Premium
Machine learning–based uncertainty modelling of mechanical properties of soft clays relating to time‐dependent behavior and its application
Author(s) -
Zhang Pin,
Jin YinFu,
Yin ZhenYu
Publication year - 2021
Publication title -
international journal for numerical and analytical methods in geomechanics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.419
H-Index - 91
eISSN - 1096-9853
pISSN - 0363-9061
DOI - 10.1002/nag.3215
Subject(s) - hydraulic conductivity , monte carlo method , geotechnical engineering , monotonic function , artificial neural network , interval (graph theory) , computer science , engineering , mathematics , geology , machine learning , soil science , soil water , statistics , mathematical analysis , combinatorics
Abstract Uncertainty is a commonplace and significant issue in geotechnical engineering. Unlike conventional statistical and machine learning methods, this study presents a novel approach to correlating soil properties that takes uncertainty into account using an artificial neural network with Monte Carlo dropout (ANN_MCD). An uncertainty model for two important soil properties, creep index C α, and hydraulic conductivity k , that control the long‐term performance of geotechnical structures is proposed in a function of three soil physical properties using ANN_MCD. Evaluation of the accuracy, uncertainty, and monotonicity of the predicted results for both C α and k reveals the excellent performance of the proposed model, which is used to simulate the long‐term settling and excess pore pressure of an embankment on soft clays. The predicted results show good agreement with observations, within a 95% confidence interval. All results indicate that the proposed ANN_MCD‐based modelling approach can be used to rapidly correlate soil properties with an uncertainty evaluation and can be further combined with numerical modelling to analyze an engineering‐scale problem and conduct risk assessment.