Research on the Integration and Application of CNN and MRF in Geotechnics
DOI:
https://doi.org/10.54097/rk7xw167Keywords:
Stratigraphic uncertainty; convolutional neural networks; Markov random field; stochastic geological modeling.Abstract
Stratigraphic uncertainty can result in serious construction accidents or extra construction costs when the geotechnical information is limited. The Markov random field (MRF), based on the stochastic theory, provides engineers with a useful but time-consuming solution to predict the unknown stratum and relevant parameters under some priori knowledge. A new integrated model of convolutional neural network (CNN) and MRF has been proved to greatly improve the computation efficiency compared with the mentioned conventional method while keeping a relatively good accuracy, but it has not been widely used yet. In the background of rapid development of artificial intelligence (AI) and big data technology, this paper aims to introduce the above-mentioned stochastic geological modeling method to stimulate engineers to explore possible data-driven solutions to geotechnical problems. This paper firstly introduces the progress of stratigraphic uncertainty analysis, and then analyses the principles and applications in geotechnic fields of MRF and CNN. Consequently, the integrated model and a case study are introduced to prove its feasibility. Finally, the evaluation and foresight of the model is given.
Downloads
References
Nadim F. Tools and Strategies for Dealing with Uncertainty in Geotechnics. In: Probabilistic Methods in Geotechnical Engineering. Springer Vienna; 2007:71-95.
Phoon K-K, Shuku T, Ching J. Uncertainty, Modeling, and Decision Making in Geotechnics. Vol 1. 1st ed. CRC Press; 2024;2023;
Christian JT. Geotechnical Engineering Reliability: How Well Do We Know What We Are Doing? Journal of geotechnical and geoenvironmental engineering. 2004;130(10):985-1003.
Elkateb T, Chalaturnyk R, Robertson PK. An overview of soil heterogeneity: quantification and implications on geotechnical field problems. Canadian geotechnical journal. 2003;40(1):1-15.
Fenton GA. Estimation for Stochastic Soil Models. Journal of geotechnical and geoenvironmental engineering. 1999;125(6):470-485.
Griffiths DV, Fenton GA. Probabilistic Slope Stability Analysis by Finite Elements. Journal of geotechnical and geoenvironmental engineering. 2004;130(5):507-518.
Martinez JG, Yeung T, Sacks R, Shahaf Y, Sharoni L-O. Situational Awareness in Construction Using a Serious Game. Journal of construction engineering and management. 2023;149(3).
Morrison FA. Uncertainty Analysis for Engineers and Scientists: A Practical Guide. 1st ed. Cambridge University Press; 2021;2020;
Ababou R, Chastanet J, Côme J-M, Marcoux M, Quintard M, service) SL (O. Uncertainty Analyses in Environmental Sciences and Hydrogeology: Methods and Applications to Subsurface Contamination. 1st 2023. Springer Nature Singapore; 2023.
Shuku T, Phoon K-K. Data-driven subsurface modelling using a Markov random field model. Georisk. 2023;17(1):41-63.
Zhou, Z.-H. (2021). Machine Learning (1st 2021.). Springer Singapore.
Bakhshi A, Alamdari P, Heidari A, Mohammadi MH. Estimating soil–water characteristic curve (SWCC) using machine learning and soil micro-porosity analysis. Earth science informatics. 2023;16(4):3839-3860.
Ma Y, Minasny B, Demattê JAM, McBratney AB. Incorporating soil knowledge into machine‐learning prediction of soil properties from soil spectra. European journal of soil science. 2023;74(6): n/a.
Bondi G, Creamer R, Ferrari A, Fenton O, Wall D. Using machine learning to predict soil bulk density on the basis of visual parameters: Tools for in-field and post-field evaluation. Geoderma. 2018; 318:137-147.
Calabrese A, Lai CG. Fragility functions of blockwork wharves using artificial neural networks. Soil dynamics and earthquake engineering (1984). 2013; 52:88-102.
Zhang J-Z, Zhang D-M, Huang H-W, Phoon KK, Tang C, Li G. Hybrid machine learning model with random field and limited CPT data to quantify horizontal scale of fluctuation of soil spatial variability. Acta geotechnica. 2022;17(4):1129-1145.
Wang ZZ, Xiao C, Goh SH, Deng M-X. Metamodel-Based Reliability Analysis in Spatially Variable Soils Using Convolutional Neural Networks. Journal of geotechnical and geoenvironmental engineering. 2021;147(3).
Rue H, Held L. Gaussian Markov Random Fields: Theory and Applications. Vol 104;104.; 1st ed. Chapman & Hall/CRC; 2005.
Geman S, Geman D. Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images. IEEE transactions on pattern analysis and machine intelligence. 1984; PAMI-6(6):721-741.
Jiang Q-H, Zhang J-Z, Zhang D-M, Analysis of Tunnel Deformational Performance Considering Geological Uncertainty and Spatial Variability. Geo-Risk. 2023; 49-58.
Li Z, Wang X, Wang H, Liang R-Y. Quantifying stratigraphic uncertainties by stochastic simulation techniques based on Markov random field. Engineering geology. 2016; 201:106-122.
Zhang D-M, Jiang Q-H, Zhang J-Z, Huang H-W. Bearing capacity of shallow foundations considering geological uncertainty and soil spatial variability. Acta geotechnica. Published online 2023.
Karimpouli S, Tahmasebi P. Image-based velocity estimation of rock using Convolutional Neural Networks. Neural networks. 2019; 111:89-97.
Geng L, Sun J, Xiao Z, Zhang F, Wu J. Combining CNN and MRF for road detection. Computers & electrical engineering. 2018; 70:895-903.
Qu, X-F, Wang J-J, Wang X-L, Hu Y-K, Zeng TC, and Tan T-W. Gravelly soil uniformity identification based on the optimized Mask R-CNN model. Expert systems with applications. 2023; 212:118837.
Li L, Liu Z, Zhou H, Zhang J, Shen W, Shao J. Prediction of TBM cutterhead speed and penetration rate for high-efficiency excavation of hard rock tunnel using CNN-LSTM model with construction big data. Arabian journal of geosciences. 2022;15(3).
Ng W, Minasny B, Montazerolghaem M, et al. Convolutional neural network for simultaneous prediction of several soil properties using visible/near-infrared, mid-infrared, and their combined spectra. Geoderma. 2019; 352:251-267.
Bao L, Wu B, Liu W, IEEE. CNN in MRF: Video Object Segmentation via Inference in a CNN-Based Higher-Order Spatio-Temporal MRF. In: IEEE; 2018:5977-5986.
Zhang C, Sargent I, Pan X, Gardiner A, Hare J, Atkinson PM. VPRS-Based Regional Decision Fusion of CNN and MRF Classifications for Very Fine Resolution Remotely Sensed Images. IEEE transactions on geoscience and remote sensing. 2018;56(8):4507-4521.
Zhao X, Gao L, Chen Z, Zhang B, Liao W, Yang X. An Entropy and MRF Model-Based CNN for Large-Scale Landsat Image Classification. IEEE geoscience and remote sensing letters. 2019;16(7):1145-1149.
Phoon K-K, Zhang W. Future of machine learning in geotechnics. Georisk. 2023;17(1):7-22.
Wu C, Hong L, Wang L, Zhang R, Pijush S, Zhang W. Prediction of wall deflection induced by braced excavation in spatially variable soils via convolutional neural network. Gondwana research. 2023; 123:184-197.
Wang Z-Z, Goh SH. Novel approach to efficient slope reliability analysis in spatially variable soils. Engineering geology. 2021; 281:105989.
Zhang J-Z, Zhang D-M, Huang H-W, Phoon KK, Tang C, Li G. Hybrid machine learning model with random field and limited CPT data to quantify horizontal scale of fluctuation of soil spatial variability. Acta geotechnica. 2022;17(4):1129-1145.
Jiang S-H, Zhu G-Y, Wang ZZ, Huang Z-T, Huang J. Data augmentation for CNN-based probabilistic slope stability analysis in spatially variable soils. Computers and geotechnics. 2023; 160:105501.
Goh ATC, Zhang WG, Wong KS. Deterministic and reliability analysis of basal heave stability for excavation in spatial variable soils. Computers and geotechnics. 2019; 108:152-160.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
