Yue Chen

Dr. Yue Chen


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
25 April 2025 in Polymers
Verified
Journal Article
Open access
PDF file
TSTaiwo Sesay
Taiwo Sesay
YXYuekai Xie
Yuekai Xie
YCYue Chen
Yue Chen
JXJianfeng Xue
Jianfeng Xue
Rammed earth (RE), despite being an ancient method of construction, has smoothly integrated into contemporary civil engineering due to its compatibility with current sustainability requirements for housing structures. However, typical RE needs some improvements to fully realize its potential as both a structurally effective and environmentally friendly building technique. As a result, multiple bio-inspired enhancement methods have been suggested to substitute traditional cement or lime stabilizers. This review examines the various efforts made in the past decade to biologically stabilize natural soil for the construction of RE. It provides a brief overview of the different bio-based materials utilized in this area but primarily concentrates on their effects on the mechanical strength and water durability of RE structures. The review also addresses current obstacles that prevent the widespread industrial adoption of this valuable earth-building method and identifies potential directions for future research. Overall, the available literature on the mechanical performance and durability of bio-based rammed earth (BRE) shows encouraging outcomes. Nonetheless, various issues, such as the absence of thorough data on the discussed topics, issues related to the inherent properties of soil and biomaterials, and doubts regarding the reliability of durability evaluation methods, have been identified as factors that could lead to a lack of confidence among RE practitioners in adopting bio-based treatments. This study will provide a solid foundation for future researchers aiming to advance BRE technology, thus enhancing sustainability within the construction sector.

1 February 2022 in Canadian Geotechnical Journal
Verified
Journal Article
Closed access
YCYue Chen
Yue Chen
MJMark B. Jaksa
Mark B. Jaksa
YKYien-Lik Kuo
Yien-Lik Kuo
DADavid W. Airey
David W. Airey
Rolling dynamic compaction (RDC) is a soil compaction technique, which is capable of improving thick layers of soil at a relatively fast operating speed. The paper presents the results of laboratory experiments conducted on 1:13 scale models of the four-sided, 8 and 12 t, Broons BH-1300 and BH-1300 HD impact rollers, respectively, to study the performance of the scale model at four different operating speeds. A series of laboratory tests is undertaken using transparent soils and the particle image velocimetry (PIV) technique to investigate the effectiveness of the models. The transparent soil employed in this study consists of fused quartz and a pore fluid that matched the refractive index of the fused quartz. A one-particle thick layer of coloured fused quartz is embedded in the centre plane of the transparent soil to visualize soil internal displacements and a digital camera is used to capture the speckled pattern during the scale model testing process. The results show that the heavier module induces greater soil displacements at each operating speed. The optimal operating speed is approximately 299 mm/s for both module weights. The most significant soil displacements occur within the first 20 passes and no obvious ground improvement is observed after 35 passes. The results of this study demonstrate the unique capability of transparent soil to study soil displacements induced by the ground improvement scale models.

15 January 2026 in Sustainability
Verified
Journal Article
Open access
PDF file
YCYue Chen
Yue Chen
BQBoshi Qian
Boshi Qian
JXJianfeng Xue
Jianfeng Xue
The construction sector generates a substantial proportion of Australia’s total solid waste, underscoring the urgent need for sustainable and circular resource management approaches to mitigate environmental impacts. This study evaluates the environmental performance and circularity potential of construction and demolition waste (C&DW) management across five Australian states. Three representative building cases were modelled using both national-average and state-specific recycling rates and electricity generation mixes. A Life Cycle Assessment (LCA) was conducted to compare two end-of-life pathways: landfill and recycling. Key parameters, including transport distance and substitution ratio, were also examined to assess their influence on carbon outcomes. The results show that regional variations in electricity generation mix and recycling rate have a strong influence on the total Global Warming Potential of C&DW management. States with cleaner electricity grids and higher recycling rates, such as South Australia, exhibited notably lower recycling-related emissions than those relying on fossil-fuel-based power. The findings highlight the importance of incorporating regional characteristics into sustainability assessments of C&DW management and provide practical insights to support Australia’s transition toward a circular and low-carbon construction industry.

22 September 2021 in Granular Matter
Verified
Journal Article
Closed access
PDF file
YCYue Chen
Yue Chen
MJMark Jaksa
Mark Jaksa
YKYien-Lik Kuo
Yien-Lik Kuo
DADavid William Airey
David William Airey

22 August 2025 in Sensors
Verified
Journal Article
Open access
PDF file
GXGUO XINYU
GUO XINYU
YCYue Chen
Yue Chen
NSNan Sun
Nan Sun
The accurate prediction of the pavement structural modulus is crucial for maintenance planning and life-cycle assessment. While recent deep learning models have improved predictive accuracy using Falling Weight Deflectometer data, challenges remain in effectively structuring time-series inputs and ensuring robustness against noise measurement. This paper presents an integrated framework that combines systematic time-step modeling with perturbation-based robustness evaluation. Five distinct input sequencing strategies (Plan A through Plan E) were developed to investigate the impact of temporal structure on model performance. A hybrid Wide & Deep ResRNN architecture incorporating SimpleRNN, GRU, and LSTM components was designed to jointly predict four-layer moduli. To simulate real-world sensor uncertainty, Gaussian noise with ±3% variance was injected into inputs, allowing the Monte-Carlo-style estimation of confidence intervals. Experimental results revealed that time-step design plays a critical role in both prediction accuracy and robustness, with Plan D consistently achieving the best balance between accuracy and stability. These findings offer a practical and generalizable approach for deploying deep sequence models in pavement modulus prediction tasks, particularly under uncertain field conditions.