Article (Scientific journals)
Bayesian Neural Network Prediction and Uncertainty Analysis of Bio-Cemented Soil Strength
Zhang, Aoxi; Wang, Liang; Zhang, Wengang et al.
2026In International Journal for Numerical and Analytical Methods in Geomechanics, 50 (3), p. 1349 - 1366
Peer Reviewed verified by ORBi
 

Files


Full Text
Num Anal Meth Geomechanics - 2025 - Zhang - Bayesian Neural Network Prediction and Uncertainty Analysis of Bio‐Cemented.pdf
Publisher postprint (8.12 MB) Creative Commons License - Attribution
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Bayesian neural network; bio-cemented soils; microbially induced calcite precipitation; probabilistic modelling; strength prediction; uncertainty quantification; Bayesian neural networks; Bio-cemented soil; Calcite precipitation; Carbonate precipitation; Cemented soil; Microbially induced calcite precipitation; Probabilistic models; Strength prediction; Uncertainty; Uncertainty quantifications; Computational Mechanics; Materials Science (all); Geotechnical Engineering and Engineering Geology; Mechanics of Materials
Abstract :
[en] Microbially induced carbonate precipitation (MICP) has emerged as a promising ground improvement technique, with MICP-treated soils exhibiting substantial enhancements in strength. However, experimental results revealed significant variability in strength outcomes of MICP-treated soils, even under identical treatment conditions and soil properties. This uncertainty in strength is challenging to capture using traditional predictive approaches such as conventional constitutive models. The present study leverages artificial intelligence to address the challenge by developing a Bayesian neural network (BNN) model for predicting the strength of bio-cemented soils while considering uncertainty. A dataset comprising 480 experimental samples was used to develop the model. The results indicate that carbonate content and confining pressure emerge as the most influential factors governing the strength of bio-cemented soils. The BNN model exhibits lower uncertainty when predicting bio-cemented soils with relatively low strength, while demonstrating higher uncertainty for soils with strength exceeding 2 MPa. Moreover, micromechanical investigations using the discrete element method (DEM) reveal that multiscale factors, including crystal distribution patterns, fabric and spatial heterogeneity of precipitates, contribute significantly to the strength uncertainty of bio-cemented soils. The developed BNN model provides an alternative tool for predicting bio-cemented soil strength with quantified reliability, facilitating the design of MICP treatment and its application in geotechnical engineering.
Disciplines :
Civil engineering
Author, co-author :
Zhang, Aoxi ;  Université de Liège - ULiège > Département ArGEnCo > Géotechnique ; Department of Civil Engineering, Computing Center for Geotechnical Engineering, Zhejiang University, Hangzhou, China
Wang, Liang;  Department of Geoscience & Engineering, Delft University of Technology, Delft, Netherlands
Zhang, Wengang ;  School of Civil Engineering, Chongqing University, Chongqing, China
Zhao, Chaofa;  Department of Civil Engineering, Computing Center for Geotechnical Engineering, Zhejiang University, Hangzhou, China
Zhang, Pan;  Department of Civil Engineering, University of Ottawa, Ottawa, Canada
Language :
English
Title :
Bayesian Neural Network Prediction and Uncertainty Analysis of Bio-Cemented Soil Strength
Publication date :
2026
Journal title :
International Journal for Numerical and Analytical Methods in Geomechanics
ISSN :
0363-9061
eISSN :
1096-9853
Publisher :
John Wiley and Sons Ltd
Volume :
50
Issue :
3
Pages :
1349 - 1366
Peer reviewed :
Peer Reviewed verified by ORBi
Funders :
NSCF - National Natural Science Foundation of China
Funding text :
The following funds are greatly acknowledged for the support: National Natural Science Foundation of China (Grant No. 52311530699), National Key Research and Development Program of China (No. 2023YFB2604200), Key R&D Program of Zhejiang Province (No. 2023C03182), and Zhejiang Provincial Natural Science Foundation of China (No. LQ23E080013).
Available on ORBi :
since 09 April 2026

Statistics


Number of views
41 (0 by ULiège)
Number of downloads
63 (0 by ULiège)

Scopus citations®
 
0
Scopus citations®
without self-citations
0
OpenAlex citations
 
0

Bibliography


Similar publications



Contact ORBi