ORIGINAL PAPER Ultimate Shear Resistance of Silty Sands Improved by Stone Columns Estimation Using Neural Network and Imperialist Competitive Algorithm Alireza Ardakani . Reza Dinarvand . Ali Namaei Received: 11 July 2019 / Accepted: 18 October 2019 Ó Springer Nature Switzerland AG 2019 Abstract One of the most popular soil improvement methods is stone columns. So as to investigate the performance of this approach under different types of loadings, it is essential to obtain the displacement– load curve of the stone columns. In this paper, the effect of geotextile-encased stone columns has been evaluated based on 39 large scale tests in sand with different silt content. Furthermore, artiﬁcial neural network is carried on to estimate the shear resistance of the modeled stone columns by considering some factors such as ﬁne content of bed soil, area replace- ment of stone columns, and normal stress on the sample. In the present research, artiﬁcial neural networks optimized by colonial competitive algorithm (ANN-ICA) were used and their results were com- pared with other methods. The obtained results showed that ICA-based artiﬁcial neural networks predicted lateral bearing capacity of short piles with a correlation coefﬁcient of 0.9738 for training data and 0.9913 for test data. Moreover, the results of the model showed the superiority of ICA-based artiﬁcial neural networks compared to back-propagation artiﬁcial neural network methods. Keywords Geotextile-encased stone columns  Sand  Shear resistance  Neural network 1 Introduction Different ground improvement methods like cement stabilization, lime treatment, deep soil mixing, and stone columns have been used to improvement problematic soil (Babu et al. 2013). Stone columns are widely used as a cost and energy efﬁcient and environmentally friendly methods for improving loose soils (Chen et al. 2015). The ground improved with stone columns has a higher resistance and stiffness than intact soil (Murugesan and Rajagopal 2010). With the installation of stone columns, the vertical load capacity increases and the settlement decreases, the consolidation rate increases (Castro and Sagaseta 2011; Alikroosh and Nikraz 2012; Zhang et al. 2012; Dash and Bora 2013), as well as the liquefaction potential is reduced (Seed and Booker 1977; Adalier et al. 2003; Asgari et al. 2013). The bearing capacity of stone columns is achieved by the surrounding soil. However, there is not enough lateral conﬁnement in the case of very soft soils (Murugesan and Rajagopal 2007; Mohapatra et al. A. Ardakani  R. Dinarvand  A. Namaei (&) Department of Civil Engineering, Imam Khomeini International University, Qazvin, Iran e-mail: namaeiali@yahoo.com A. Ardakani e-mail: a.ardakani@eng.ikiu.ac.ir R. Dinarvand e-mail: rezadinarvand1991@gmail.com 123 Geotech Geol Eng https://doi.org/10.1007/s10706-019-01104-8