The compaction parameters of fine-grained soils, maximum dry density (MDD) and optimum moisture content (OMC) are fundamental data required for the design, construction and choosing construction materials. This paper presents two multi-layer perceptron (MLP) artificial neural network (ANN) models to estimate the MDD and OMC of marl soils. Marl soil is a fine-grained soil. The Levenberg-Marquadt learning algorithm was used to train the networks. Existing models estimate soil compaction parameters based on physical and soil index parameters. The present study considers the effects of chemical factors on the behavior and characteristics of fine-grained soils along with the common soil index parameters. The model used test results from 60 marl soil samples taken from marl formations in the Neogene basin in central Iran. The models were designed to use different input data sets and structures to determine which soil properties and ANN structures correlate well with the compaction parameters. Electrical conductivity (EC) of saturated soil was a new input parameter used in addition to the physical and soil index parameters that include the Atterberg limit, and the activity and content of the clay, silt and sand. The results show that inclusion of EC improved the accuracy of the models. It was found that the accuracy of the generalizations and estimations of the ANN models was further increased by clustering data before the data division stage.

Keywords