Prediction the compaction properties of lateritic soils by hybrid ANFIS methods

Document Type : Original Article


1 Ho Chi Minh City University of Transport, Ho Chi Minh City, Viet Nam

2 Faculty of Environment and Labour Safety, Ton Duc Thang University, Ho Chi Minh City, Viet Nam


Empirically, soil compaction is an important aspect in the selection of materials for earth constructions. Due to time constraints and attention to completion resources, it is necessary to develop models to forecast compaction parameters (maximum dry unit weight (γ_dmax) and optimum moisture content (ω_opt) from easily measured index properties. The main purpose of this study is to scrutinize the applicability of using the hybrid adaptive neuro-fuzzy inference system (ANFIS) models for predicting the γ_dmax and ω_opt related to the standard proctor compaction test of lateritic soils. Results present that both models have a reasonable performance in predicting the γ_dmax and ω_opt with R^2 larger than 0.9038 and 0.9692 for the training data, representing the acceptable correlation between measured and forecasted γ_dmax and ω_opt. Regarding developed models, the ANFIS model optimized with whale optimization algorithm (WOA) has the best performance than imperialist competitive algorithm (ICA) model in both training and testing phases for predicting γ_dmax and ω_opt.