Exploring relationships between mechanical properties of marl core samples by a coupling of mutual information and predictive ensemble model

Document identifier: oai:DiVA.org:ltu-76808
Access full text here:10.1007/s40808-019-00672-1
Keyword: Engineering and Technology, Materials Engineering, Metallurgy and Metallic Materials, Teknik och teknologier, Materialteknik, Metallurgi och metalliska material, Marls, Dam, Variable importance, Maintenance, Brazilian test, Mutual information, Mineral Processing, Mineralteknik
Publication year: 2020

Inappropriate evaluation of uniaxial compression indexes (E and UCS) of rocks in high seismic intensity areas such as dam regions can lead to underestimation of the load, and possible settlement of the structure. Indirect assessments of these rock mechanical indexes based on non-destructive experiments and by using intelligent models is a well-accepted method to overcome associated limitations with laboratory tests of E and UCS. This study introduces the mutual information (MI) method as a unique system for variable importance measurement (VIM) and feature selection. Conducting MI-VIM assessments between various analyses of marl core samples (depth, density, ultrasonic tests (νd, Vp and Vs), Brazilian test (σt), triaxial compression test (C and and ϕ) and point load test (Is(50)) indicated that Vs and σt had the highest importance for E and UCS prediction. adaptive boosting–neural network ensemble (Adaboost–NNE) was used for the prediction of E and UCS. Testing of the generated Adaboost–NNE indicated that this model could accurately predict UCS and E with correlations of determinations 0.98 and 0.92, respectively. These results showed that VIM of MI coupled with Adaboost–NNE could develop a robust model that can be used for the prediction and modeling of other indexes of rocks.


S. Salehin

Rock Mechanics Laboratory, University of Tehran, Tehran, Iran
Other publications >>

E. Hadavandi

Department of Industrial Engineering, Birjand University of Technology, Birjand, Iran
Other publications >>

S. Chehreh Chelgani

Luleå tekniska universitet; Mineralteknik och metallurgi
Other publications >>

Record metadata

Click to view metadata