Techno Press
Tp_Editing System.E (TES.E)
Login Search
You logged in as

gae
 
CONTENTS
Volume 25, Number 1, April10 2021
 


Abstract
Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

Key Words
landslide; susceptibility assessment; machine learning; feature selection; Geographic Information System (GIS)

Address
Lei-Lei Liu, Can Yang: Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring, Ministry of Education, School of Geosciences and Info-Physics, Central South University, Changsha 410083, P.R. China

Xiao-Mi Wang: School of Resources and Environmental Science, Hunan Normal University, Changsha 410083, P.R. China


Abstract
This paper develops a convenient approach for deterministic and probabilistic evaluations of tunnel face stability using support vector machine classifiers. The proposed method is comprised of two major steps, i.e., construction of the training dataset and determination of instance-based classifiers. In step one, the orthogonal design is utilized to produce representative samples after the ranges and levels of the factors that influence tunnel face stability are specified. The training dataset is then labeled by two-dimensional strength reduction analyses embedded within OptumG2. For any unknown instance, the second step applies the training dataset for classification, which is achieved by an ad hoc Python program. The classification of unknown samples starts with selection of instance-based training samples using the k-nearest neighbors algorithm, followed by the construction of an instance-based SVM-KNN classifier. It eventually provides labels of the unknown instances, avoiding calculate its corresponding performance function. Probabilistic evaluations are performed by Monte Carlo simulation based on the SVM-KNN classifier. The ratio of the number of unstable samples to the total number of simulated samples is computed and is taken as the failure probability, which is validated and compared with the response surface method.

Key Words
tunnel face stability; support vector machine; the k-nearest neighbors; strength reduction analysis; Monte Carlo simulation

Address
Bin Li: School of Transportation, Wuhan University of Technology, Hubei Highway Engineering Research Center,
1178 Heping Avenue, Wuhan, Hubei Province 430063, China

Yong Fu: Department of Ocean Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China

Yi Hong: College of Civil Engineering and Architecture, Zhejiang University, Hang Zhou, China

Zijun Cao: State Key Laboratory of Water Resources and Hydropower Engineering Science, Key Laboratory of Rock Mechanics in Hydraulic Structural Engineering, Ministry of Education,Wuhan University, 8 Donghu South Road, Wuhan, China


Abstract
Injection grouting is one of the most common ground improvement practice to increase the strength and reduce the hydraulic conductivity of soils. Owing to the environmental concerns of conventional grout materials, such as cement-based or silicate-based materials, bio-inspired biogeotechnical approaches are considered to be new sustainable and environmentally friendly ground improvement methods. Biopolymers, which are excretory products from living organisms, have been shown to significantly reduce the hydraulic conductivity via pore-clogging and increase the strength of soils. To study the practical application of biopolymers for seepage and ground water control, in this study, we explored the injection capabilities of biopolymer-based grout materials in both linear aperture and particulate media (i.e., sand and glassbeads) considering different injection pressures, biopolymer concentrations, and flow channel geometries. The hydraulic conductivity control of a biopolymer-based grout material was evaluated after injection into sandy soil under confined boundary conditions. The results showed that the performance of xanthan gum injection was mainly affected by the injection pressure and pore geometry (e.g., porosity) inside the soil. Additionally, with an increase in the xanthan gum concentration, the injection efficiency diminished while the hydraulic conductivity reduction efficiency enhanced significantly. The results of this study provide the potential capabilities of injection grouting to be performed with biopolymer-based materials for field application.

Key Words
biopolymer; injection grouting; hydrogel; penetrability; hydraulic conductivity

Address
Minhyeong Lee, Jooyoung Im and Gye-Chun Cho:Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea

Ilhan Chang: Department of Civil Systems Engineering, Ajou University, 206 World cup-ro, Yeongtong-gu, Suwon-si 16499, Gyeonggi-do, Republic of Korea


Abstract
In cold regions, the integrity of the infrastructures built on weak soils can be extensively damaged by weathering actions due to the cyclic freezing and thawing. This damage can be mitigated by exploiting soil stabilization techniques. Generally, ordinary Portland cement (OPC) is the most commonly used binding material for investigating the chemo-hydro-mechanical behavior. However, due to the environmental issue of OPC producing a significant amount of carbon dioxide emission, calcium sulfoaluminate (CSA) cement can be used as one of the eco-sustainable alternatives. Although recently several studies have examined the strength development of CSA treated sand, no research has been concerned about CSA cement-stabilized sand affected by cyclic freeze and thaw. This study aims to conduct a comprehensive laboratory work to assess the effect of the cyclic freeze-thaw action on strength and durability of CSA cement-treated sand. For this purpose, unconfined compressive strength (UCS) and ultrasonic pulse velocity (UPV) tests were performed on the stabilized soil specimens cured for 7 and 14 days which are subjected to 0, 1, 3, 5, and 7 freeze-thaw cycles. The test results show that the strength and durability index of the samples decrease with the increase of the freeze-thaw cycles. The loss of the strength and durability considerably decreases for all soil samples subjected to the freeze-thaw cycles. Overall, the use of CSA as a stabilizer for sandy soils would be an eco-friendly option to achieve sufficient strength and durability against the freeze-thaw action in cold regions.

Key Words
freeze-thaw; cement-treated sand; calcium sulfoaluminate; unconfined compressive strength; durability

Address
Assel Jumassultan, Nazerke Sagidullina, Jong Kim and Sung-Woo Moon: Department of Civil and Environmental Engineering, Nazarbayev University, Nur-Sultan, 010000, Kazakhstan

Taeseo Ku: Department of Civil and Environmental Engineering, National University of Singapore, Singapore, 117576, Singapore

Abstract
The resistance of soil to the tractive force of flowing water is one of the essential parameters for the stability of the soil when directly exposed to the movement of water such as in rivers and ocean beds. Biopolymers, which are new to sustainable geotechnical engineering practices, are known to enhance the mechanical properties of soil. This study addresses the surface erosion resistance of river-sand treated with several biopolymers that originated from micro-organisms, plants, and dairy products. We used a state-of-the-art erosion function apparatus with P-wave reflection monitoring. Experimental results have shown that biopolymers significantly improve the erosion resistance of soil surfaces. Specifically, the critical shear stress (i.e., the minimum shear stress needed to detach individual soil grains) of biopolymer-treated soils increased by 2 to 500 times. The erodibility coefficient (i.e., the rate of increase in erodibility as the shear stress increases) decreased following biopolymer treatment from 1 x 10-2 to 1 x 10-6 times compared to that of untreated river-sands. The scour prediction calculated using the SRICOS-EFA program has shown that a height of 14 m of an untreated surface is eroded during the ten years flow of the Nakdong River, while biopolymer treatment reduced this height to less than 2.5 m. The result of this study has demonstrated the possibility of cross-linked biopolymers for river-bed stabilization agents.

Key Words
river-bed terrain; surface erosion; EFA experiment; biopolymer; cross-linking

Address
Yeong-Man Kwon and Gye-Chun Cho: Department of Civil and Environmental Engineering, KAIST, Daejeon 34141, Republic of Korea

Moon-Kyung Chung: Vice President for Research, Korea Institute of Civil Engineering and Building Technology, Goyang-si 10233, Republic of Korea

Ilhan Chang: Department of Civil Systems Engineering, Ajou University, Suwon-si 16499, Republic of Korea


Abstract
There frequently exists inadequacy regarding the number of boreholes installed along tunnel alignment. While geophysical imaging techniques are available for pre-tunnelling geological characterization, they aim to detect specific object (e.g., water body and karst cave). There remains great motivation for the industry to develop a real-time identification technology relating complex geological conditions with the existing tunnelling parameters. This study explores the potential for the use of machine learning-based data driven approaches to identify the change in geology during tunnel excavation. Further, the feasibility for machine learning-based anomaly detection approaches to detect the development of clayey clogging is also assessed. The results of an application of the machine learning-based approaches to Xi'an Metro line 4 are presented in this paper where two tunnels buried in the water-rich sandy soils at depths of 12-14 m are excavated using a 6.288 m diameter EPB shield machine. A reasonable agreement with the measurements verifies their applicability towards widening the application horizon of machine learning-based approaches.

Key Words
Xi'an Metro; EPB shield; machine learning; clogging; silt soil

Address
Xue-Dong Bai and Ge Li: 1.) School of Civil Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China
2.) Shaanxi Key Laboratory of Geotechnical and Underground Space Engineering (XAUAT), Xi'an 710055, China

Wen-Chieh Cheng: School of Civil Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China

Dominic E.L. Ong: School of Engineering and Built Environment, Griffith University, Queensland 4111, Australia



Techno-Press: Publishers of international journals and conference proceedings.       Copyright © 2024 Techno-Press ALL RIGHTS RESERVED.
P.O. Box 33, Yuseong, Daejeon 34186 Korea, Email: admin@techno-press.com