In this paper, two different data driven models, genetic programming (GP) and multivariate adoptive regression splines (MARS), have been adopted to create the models for prediction of bridge risk score. Input parameters of bridge risks consists of safe risk rating (SRR), functional risk rating (FRR), sustainability risk rating (SUR), environmental risk rating (ERR) and target output. The total dataset contains 66 bridges data in which 70% of dataset is taken as training and the remaining 30% is considered for testing dataset. The accuracy of the models are determined from the coefficient of determination (R²). If the R² the testing model is close to the R² value of the training model, that particular model is to be consider as robust model. The modeling mechanisms and performance is quite different for both the methods hence comparative study is carried out. Thus concluded robust models performance based on the R² value, is checked with mathematical statistical equations.  In this study both models were performed, examined and compared the results with mathematical methods successfully. From this work, it is found that both the proposed methods have good capability in predestining the results. Finally, the results reveals that genetic Programming is marginally outperforms over the MARS technique.

Several researchers have proved that the constitutive models of concrete based on combination of continuum damage and plasticity theories are able to reproduce the major aspects of concrete behavior. A problem of such damage-plasticity models is associated with the material constants which are needed to be determined before using the model. These constants are in fact the connectors of constitutive models to the experimental results. Experimental determination of these constants is always associated with some problems, which restricts the applicability of such models despite their accuracy and capabilities. In the present paper, the values of material constants for a damage-plasticity model determined in part I of this work were used as a database. Genetic programming was employed to discover equations which directly relate the material constants to the concrete primary variables whose values could be simply inferred from the results of uniaxial tension and compressive tests. The simulations of uniaxial tension and compressive tests performed by using the constants extracted from the proposed equations, exhibited a reasonable level of precision.  The validity of suggested equations were also assessed via simulating experiments which were not involved in the procedure of equation discovery. The comparisons revealed the satisfactory accuracy of proposed equations.