The Iowa Department of Transportation (DOT) has been collecting falling weight deflectometer (FWD) data on a regular basis. However, the pavement layer moduli backcalculation techniques used so far have been cumbersome and time consuming. More efficient and faster methods in FWD test data analysis were demanded and deemed necessary for routine analysis. Researchers at Iowa State University (ISU) have developed a suite of advanced pavement layer moduli backcalculation models using the artificial neural networks (ANN) methodology for flexible, rigid, and composite pavements. The current study aims to develop a fully automated backcalculation software system, referred to as I-BACK, with improved accuracy and usability of Iowa FWD data. Evolutionary optimization/nonlinear optimization algorithms were implemented with the developed ANN models to improve the accuracy of predictions.