STATE OF THE ART REVIEW A review of artificial intelligence applications in shallow foundations Mohamed A. Shahin* Geotechnical engineering deals with materials (e.g. soil and rock) that, by their very nature, exhibit varied and uncertain behavior because of the imprecise physical processes associated with the formation of these materials. Modeling the behavior of such materials in geotechnical engineering applications is complex and sometimes beyond the ability of most traditional forms of physically based engineering methods. Artificial intelligence (AI) is becoming more popular and particularly amenable to modeling the complex behavior of most geotechnical engineering applications, including foundations, because it has demonstrated superior predictive ability compared to traditional methods. The main aim of this paper is to review the AI applications in shallow foundations and present the salient features associated with the AI modeling development. The paper also discusses the strengths and limitations of AI techniques compared to other modeling approaches. Keywords: Artificial intelligence, Shallow foundations, Modeling, Neural networks, Genetic programing, Evolutionary polynomial regression Introduction Over the last decade, artificial intelligence (AI) has been applied successfully to virtually every problem in geotech- nical engineering. Among the available AI techniques are artificial neural networks (ANNs), genetic programing (GP), evolutionary polynomial regression (EPR), support vector machines, M5 model trees, and k-nearest neighbors (Elshorbagy et al., 2010). The focus of this paper will be on three AI techniques, including ANNs, GP, and EPR. These three techniques are selected because they have been proved to be the most successful applied AI techniques in geotechnical engineering especially for shallow founda- tions. Of these, ANNs are by far the most commonly used one. Interested readers are referred to Shahin et al. (2001), where the pre-2001 ANN applications in geotechnical engineering are reviewed in some detail, and Shahin et al. (2009) and Shahin (2013), where the post-2001 papers of AI applications in geotechnical engineering are briefly examined. The behavior of foundations (deep and shallow) in soils is complex, uncertain, and not yet entirely understood. This fact has encouraged many researchers to apply the AI techniques for modeling the behavior of foundations. In particular, ANNs have been used for shallow foundations including settlement estimation (Chen et al., 2009; Shahin et al., 2002b, 2003; Sivakugan et al., 1998; Soleimanbeigi and Hataf, 2006) and prediction of ultimate bearing capacity (Behera et al., 2013a, 2013b; Kalinli et al., 2011; Kuo et al., 2009; Padmini et al., 2008; Provenzano et al., 2004; Soleimanbeigi and Hataf, 2005). Likewise, GP and EPR have been investigated for settlement prediction of shallow foundations (Rezania and Javadi, 2007; Shahin, 2014; Shahnazari et al., 2014) as well as ultimate bearing capacity (Adarsh et al., 2012; Pan et al., 2013; Shahin, 2014; Shahnazari and Tutunchian, 2012; Tsai et al., 2013). The objective of this paper is to provide an overview of some of the popular AI techniques, present a review of the AI applications to date in shallow foundations, and discuss some of the current challenges and future directions. Overview of AI Artificial intelligence is a computational method that attempts to mimic, in a very simplistic way, the human cognition capability (e.g. emulating the operation of the human brain at the neural level) to solve engineering problems that have defied solution using conventional computational techniques (Flood, 2008). The essence of AI techniques in solving any engineering problem is to learn by examples of data inputs and outputs presented to them so that the subtle functional relationships among the data are captured, even if the underlying relationships are unknown or the physical meaning is difficult to explain. Thus, AI models are data-driven models that rely on the data alone to determine the structure and parameters that govern a phenomenon (or system) and do not make any assumptions about the physical behavior of the system. This is in Department of Civil Engineering, Curtin University, Perth, WA 6845, Australia *Corresponding author, email m.shahin@curtin.edu.au ß 2014 W. S. Maney & Son Ltd Received 14 March 2014; accepted 19 March 2014 DOI 10.1179/1939787914Y.0000000058 International Journal of Geotechnical Engineering 2014 VOL 000 NO 000 1