Empirical models to predict compaction parameters for soils in the state of Ceará, northeastern Brazil

Abstract

This work developed prediction models for maximum dry unit weight (γd,max) and optimum moisture content (OMC) for compactedsoils in Ceará, Brazil, based on index and physical properties and physical properties. The methodology included data from soils usedin the construction of 15 dams in Ceará, with available information regarding laboratory tests of interest. Correlations were developedusing non-linear regression, from 169 laboratory results (83 for training and 86 for validating the models), which presented a R2of0,763 for MoPesm (prediction model forγd,max) and 0,761 for MoTuo (model for OMC).A posteriori, the same physical indexesused to train and validate MoPesm and MoTuo were used as inputs of other prediction models available in the literature, whoseoutputs differed considerably from laboratory results for the evaluated soils. MoPesm and MoTuo were able to satisfactorily predictcompaction parameters, with outputs close to those obtained in laboratory for tested soil samples. Their performance justifies theiruse for predicting compaction parameters in geotechnical structures that use employ soils when there are financial restraints, shorttimeframes, or unavailability of test equipment, particularly in early design stages and preliminary studies, before appropriate soilsampling and field investigation can be conducted, thus saving substantial time and financial resources.