Active learning inspired multi-fidelity probabilistic modelling of geomaterial property

GF He, P Zhang, ZY Yin - Computer Methods in Applied Mechanics and …, 2024 - Elsevier
The identification of geomaterial properties is costly but pivotal for engineering design. A
wide range of approaches perform well with sufficiently measured data but their …

Special issue on “Machine learning and AI in geotechnics”

KK Phoon, LM Zhang, ZJ Cao - … of Risk for Engineered Systems and …, 2023 - Taylor & Francis
The potential for machine learning and artificial intelligence to shape geotechnical
engineering practice (and possibly theory) is immense. However, the agenda for machine …

A multifidelity neural network (MFNN) for constitutive modeling of complex soil behaviors

M Su, N Guo, Z Yang - … for Numerical and Analytical Methods in …, 2023 - Wiley Online Library
The development and calibration of soil models under the framework of plasticity is
notoriously challenging given the prismatic features in soil's shear behaviors. Data‐driven …

[HTML][HTML] An efficient physics-guided Bayesian framework for predicting ground settlement profile during excavations in clay

C Tang, S He, W Zhou - Journal of Rock Mechanics and Geotechnical …, 2024 - Elsevier
Recently, the application of Bayesian updating to predict excavation-induced deformation
has proven successful and improved prediction accuracy significantly. However, updating …

Multi-fidelity deep neural network with Monte Carlo dropout technique for uncertainty-aware risk recognition of backward erosion piping in dikes

H Liu, H Su, J Yang, H Li - Applied Soft Computing, 2024 - Elsevier
Backward erosion piping (BEP) is an increasingly critical failure mechanism in dike systems,
often triggered by floods resulting from extreme rainfall events, which are exacerbated by the …

The potential of a multi-fidelity residual neural network based optimizer to calibrate DEM parameters of rock-like bonded granular materials

Z Zhou, YIN Zhen-Yu, GF He, P Zhang… - Computers and …, 2024 - Elsevier
The commonly used trial-and-error approach on selecting appropriate inter-particle
parameters in DEM simulations incurs criticism such as user dependence and high …

Multifidelity-based Gaussian process for quasi-site-specific probabilistic prediction of soil properties

GF He, P Zhang, ZY Yin, SH Goh - Canadian Geotechnical …, 2024 - cdnsciencepub.com
Conventional empirical equations for soil properties prediction tend to be site-specific,
exhibiting poor reliability and accuracy. Meanwhile, alternative data-driven methods require …

A multi‐fidelity residual neural network based surrogate model for mechanical behaviour of structured sand

Z Zhou, ZY Yin, GF He, M Jiang - International Journal for …, 2024 - Wiley Online Library
The structured sand presents significant interparticle bonding and anisotropy, resulting in
significant differences in the physical and mechanical properties from the pure sand. This …

A Case Study of Performance Comparison Between Vacuum Preloading and Fill Surcharge for Soft Ground Improvement

K Liu, HT He, DY Tan, WQ Feng, HH Zhu… - International Journal of …, 2024 - Springer
Vacuum preloading and fill surcharge are two common ground improvement methods,
which have been successfully utilized in many soil improvement and land reclamation …

[PDF][PDF] A multi-fidelity neural network (MFNN) for constitutive modeling

MM Su, N Guo, ZX Yang - researchgate.net
The development and calibration of soil models under the framework of plasticity is
notoriously challenging given the prismatic features in soil's shear behaviors. Datadriven …