Intelligent modelling of clay compressibility using hybrid meta-heuristic and machine learning algorithms

doi:10.1016/j.gsf.2020.02.014

IMECH-IR > 流固耦合系统力学重点实验室

	Intelligent modelling of clay compressibility using hybrid meta-heuristic and machine learning algorithms
	Zhang, Pin 1; Yin, Zhen-Yu 1; Jin, Yin-Fu 1; Chan, Tommy H. T.2; Gao FP(高福平)3,4
通讯作者	Yin, Zhen-Yu(zhenyu.yin@polyu.edu.hk)
发表期刊	GEOSCIENCE FRONTIERS
	2021
卷号	12 期号:1 页码:441-452
ISSN	1674-9871
摘要	Compression index C c is an essential parameter in geotechnical design for which the effectiveness of correlation is still a challenge. This paper suggests a novel modelling approach using machine learning (ML) technique. The performance of five commonly used machine learning (ML) algorithms, i.e. back-propagation neural network (BPNN), extreme learning machine (ELM), support vector machine (SVM), random forest (RF) and evolutionary polynomial regression (EPR) in predicting C-c is comprehensively investigated. A database with a total number of 311 datasets including three input variables, i.e. initial void ratio e(0), liquid limit water content W-L, plasticity index I-p, and one output variable C-c is first established. Genetic algorithm (GA) is used to optimize the hyper-parameters in five ML algorithms, and the average prediction error for the 10-fold cross-validation (CV) sets is set as the fitness function in the GA for enhancing the robustness of ML models. The results indicate that ML models outperform empirical prediction formulations with lower prediction error. RF yields the lowest error followed by BPNN, ELM, EPR and SVM. If the ranges of input variables in the database are large enough, BPNN and RF models are recommended to predict C-c. Furthermore, if the distribution of input variables is continuous, RF model is the best one. Otherwise, EPR model is recommended if the ranges of input variables are small. The predicted correlations between input and output variables using five ML models show great agreement with the physical explanation.
关键词	Compressibility Clays Machine learning Optimization Random forest Genetic algorithm
DOI	10.1016/j.gsf.2020.02.014
收录类别	SCI
语种	英语
WOS记录号	WOS:000597401000033
关键词[WOS]	SHEAR-STRENGTH ; IDENTIFYING PARAMETERS ; SENSITIVITY-ANALYSIS ; WATER-CONTENT ; INDEX ; PREDICTION ; BEHAVIOR ; SOILS ; SAND ; ANN
WOS研究方向	Geology
WOS类目	Geosciences, Multidisciplinary
资助项目	RIF project from the Research Grants Council (RGC) of Hong Kong[PolyU R5037-18F]
项目资助者	RIF project from the Research Grants Council (RGC) of Hong Kong
论文分区	一类
力学所作者排名	5+
RpAuthor	Yin, Zhen-Yu
引用统计	被引频次：65[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://dspace.imech.ac.cn/handle/311007/85862
专题	流固耦合系统力学重点实验室
作者单位	1.Hong Kong Polytech Univ, Dept Civil & Environm Engn, Hung Hom, Hong Kong, Peoples R China; 2.Queensland Univ Technol QUT, Sci & Engn Fac, Sch Civil Engn & Built Environm, Brisbane, Qld 4001, Australia; 3.Chinese Acad Sci, Inst Mech, Key Lab Mech Fluid Solid Coupling Syst, Beijing 100190, Peoples R China; 4.Univ Chinese Acad Sci, China Sch Engn Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Pin,Yin, Zhen-Yu,Jin, Yin-Fu,et al. Intelligent modelling of clay compressibility using hybrid meta-heuristic and machine learning algorithms[J]. GEOSCIENCE FRONTIERS,2021,12,1,:441-452.
APA	Zhang, Pin,Yin, Zhen-Yu,Jin, Yin-Fu,Chan, Tommy H. T.,&高福平.(2021).Intelligent modelling of clay compressibility using hybrid meta-heuristic and machine learning algorithms.GEOSCIENCE FRONTIERS,12(1),441-452.
MLA	Zhang, Pin,et al."Intelligent modelling of clay compressibility using hybrid meta-heuristic and machine learning algorithms".GEOSCIENCE FRONTIERS 12.1(2021):441-452.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Intelligent modellin（2604KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载