Xinkai Han

Dr. Xinkai Han

Civil engineering, Universiti Teknologi Malaysia, Johor Bahru, Johor, Malaysia
orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2025 in Journal of Engineering
Verified
Journal Article
Open access
CYCHEN YINTAO
CHEN YINTAO
SXShao Xin
Shao Xin
CXChang Xiangyu
Chang Xiangyu
SJSiti Norafida Jusoh
Siti Norafida Jusoh
LZLu Zhongxiang
Lu Zhongxiang
XJXu Jun
Xu Jun
Accurate tunnel deformation prediction is critical for mitigating construction risks and ensuring tunnel stability. This study introduces a novel hybrid model integrating long short‐term memory (LSTM) networks and random forest (RF) to enhance the precision of tunnel deformation predictions during construction. Bayesian optimization was utilized to fine‐tune model parameters, ensuring optimal performance. Validated with multidepth data from the Yangjiashan highway tunnel in China, the hybrid model demonstrates remarkable adaptability to complex geological conditions. The results show that the LSTM‐RF model achieves a mean square error (MSE) of 0.0025, a root‐mean‐square error (RMSE) of 0.0052, and a coefficient of determination ( R 2 ) of 0.9810, outperforming individual models and other hybrid frameworks in predicting deformation trends. By effectively capturing temporal dependencies and modeling nonlinear residuals, the hybrid model provides a robust and reliable solution for improving safety and efficiency in tunneling projects. These findings emphasize the potential of hybrid approaches for geotechnical engineering, particularly in predictive maintenance and infrastructure monitoring.

1 February 2025 in Physics of Fluids
Verified
Journal Article
Closed access
XHXinkai Han
Xinkai Han
AIAmber Islam
Amber Islam
RARini Asnida Abdullah
Rini Asnida Abdullah
Rainfall-induced slope instability poses a significant geotechnical challenge, particularly during heavy rainfall events. Traditional seepage models often neglect the combined effects of surface runoff and preferential flow, leading to limited predictive capabilities. This study presents a novel coupled dual permeability with runoff model (DPWRM) to analyze runoff and seepage during rainfall-induced preferential flow on unsaturated slopes. Combining the kinematic wave equation and dual permeability model, this approach addresses the limitations in existing methods for slope seepage predictions under intense rainfall. First, the critical role of preferential flow pathways enhanced infiltration and drainage efficiency, influencing seepage in single permeability model. Second, the DPWRM integrates infiltration dynamics, pore water pressure and runoff velocity to simulate hydrological responses. A physical model test validated the numerical model, demonstrating accurate predictions of cumulative runoff, pore water pressure variations. The results revealed significant impacts of runoff and soil heterogeneity on hydraulic conductivity and water distribution. This research provides insights into slope hydrology and geotechnical applications, offering practical strategies for managing rainfall-induced slope failures.

1 June 2025 in Physics of Fluids
Verified
Journal Article
Closed access
XHXinkai Han
Xinkai Han
RARini Asnida Abdullah
Rini Asnida Abdullah
ZIZuhaila Ismail
Zuhaila Ismail
MZMengqiu Zhang
Mengqiu Zhang
AIAmber Islam
Amber Islam
CYCHEN YINTAO
CHEN YINTAO
Surficial slope failures in residual soils are prevalent in tropical and subtropical regions due to rainfall infiltration and seepage. While numerous studies have explored rainfall-induced slope stability through the interaction between pore water pressure (PWP) and effective stress, the influence of water gravity on effective stress under infiltration and seepage boundary conditions has often been overlooked. This study introduces a novel coupled PWP and water gravity increase method (PWP–WGIM) model to comprehensively analyze slope stability and failure processes. The proposed model integrates PWP dynamics with the water gravity increase method (WGIM), taking variations in infiltration capacity and seepage boundaries into consideration. Using COMSOL Multiphysics, the governing partial differential equations are numerically solved based on the finite element method with appropriate hydrologic boundary conditions (rainfall infiltration and seepage face boundary conditions). Results indicate that unsaturated soil slopes experience more pronounced changes in effective saturation, PWP, effective stress, and deformation at both shallow and deeper regions when evaluated with the PWP–WGIM model compared to PWP-only models. Furthermore, the safety factor for the PWP–WGIM model is lower, revealing that gravitational effects coupled with PWP significantly reduce slope stability under varying rainfall intensities. These findings highlight the importance of incorporating water gravity in slope stability assessments, providing a more accurate predictive tool for managing risks in regions prone to landslides and erosion.

6 August 2024 in Acta Geodynamica et Geomaterialia
Verified
Journal Article
Open access
XHXinkai Han
Xinkai Han
RARini Asnida Abdullah
Rini Asnida Abdullah
ZIZuhaila Ismail
Zuhaila Ismail
AIAmber Islam
Amber Islam
ZLZhongxiang Lu
Zhongxiang Lu
This study examines the influence of preferential flow (PF) on seepage under different rainfall infiltration scenarios, addressing a critical gap in current modeling practices, which often overlook the interactive dynamics between matrix flow (MF) and PF domains within soil environments. In this study, an integrated saturated and unsaturated subsurface flow of dual-permeability (DP) model is developed to calculate seepage and slope stability using pore water pressure. This study aims to conduct numerical experiments of shallow landslides induced by rainfall to quantify the temporal and spatial impact of preferential flow on hydrological mechanisms and slope stability. For low-rainfall intensity, the variation in pore water pressure is greater in the MF domain than in the PF domain. 90 % of rainwater infiltrates downward through the MF domain. Water exchange predominantly occurs in the PF domain, as opposed to the MF domain. The factor of safety decreases from 1.61 to 1.55 when comparing before and after rainfall, which reduces by 3.73 %. For high-rainfall intensity, the pore water pressure variation in the PF domain is more pronounced than in the MF domain. The entirety of precipitation infiltration downwards through the PF domain. Water exchange mainly flows from the PF domain to the MF domain. The factor of safety decreases from 1.61 to 1.45 when comparing before and after rainfall, resulting in a reduction of 9.94 %.