×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerSoil classification is a significant tool for the interpretation of soil properties and the selection of the appropriate parameters to express soil types in geotechnical engineering applications. In this paper, a comparative analysis on the prediction of soil classification using different soil parameters via Neural Network, Decision Tree, and Ensemble classifier algorithms in the machine learning tool box of MATLAB is conducted. The data is classified into 14 sets of input parameters according to the parameters of the Unified Soil Classification System (USCS), which is a standard system in practice for classifying soils based on their physical properties and their engineering behavior. The input parameters of the USCS, Passing No. 4 Sieve, Passing No. 200 Sieve, Gravel, Sand, Fines, Liquid Limit, Plastic Limit and Plasticity Index, are specified within the certain ranges to generate a synthetic data base including 478 data for the purpose of training and testing. Five Neural Network models (Medium, Trilayered, Bilayered, Narrow and Wide), three Decision Tree models (Fine, Medium, Coarse) and three Ensemble models (Boosted Trees, Bagged Trees, RUSBoosted Trees) are tested for the different test split ratios (10, 20, and 30). The results show that the Neural Network models proposed in this study have the highest prediction capability, with a classification accuracy of up to 100 % for some variable sets, and can classify soils automatically and precisely based on the soil index properties. Among the individual models, WNN and NNN generally showed the best performance for all variable sets. The Ensemble models presented high prediction capability with respect to generalization. Among the DT models, although they are fast, they presented relatively lower accuracy than the other models, especially the Coarse Tree model. This study can be used as a reference for the future development of automated soil classification systems and can offer practical suggestions for the selection of machine learning models for geotechnical engineering problems.
The trend of using natural fibers in geotechnical engineering has become of great interest to improve weak soils due to some of its advantages such as local availability, environmental friendliness, and lower cost. In this study, a set of unconfined compression strength and direct shear tests were conducted to evaluate the performance of Al-Nasiriya clayey soil reinforced with natural fibers. Three different types of natural fibers were investigated as sustainable ones, including wheat straw fiber and palm frond fiber, as well as imperata cylindrica fiber. The effects of various fiber contents (0.25 %, 0.5 %, 0.75 %, and 1 %) and lengths (20 mm, 30 mm, and 40 mm) were experimentally evaluated. The results indicated that the compressive strength increased significantly with the increase of fiber content and length up to an optimum value and then decreased. The optimum fiber content and length were 0.5 % and 30 mm, respectively. Compared to the unreinforced soil, the compressive strength values at the optimum content and length increased by 102 %, 126 %, and 66 % for samples reinforced with wheat straw, palm fronds, and imperata cylindrica fibers, respectively. The shear properties improved due to soil reinforcement with natural fibers. Compared to the unreinforced soil, the internal friction angle of the samples reinforced with wheat straw, palm fronds, and imperata cylindrica fibers increased by 17.7 %, 42 %, and 9 %, respectively. Forever, the cohesion and shear strength are also improved due to inclusion of natural fibers.