Purpose: of this research paper is to select optimal welding condition for a root-pass welding for pipeline and to provide a best process for desirable welding quality. Design/methodology/approach: In this study, a variety of welding experiments were carried out to optimize an automated welding process using a GMA (Gas Metal Arc) process, these has been applied for root-pass welding. Welding current, welding speed, wire feed speed and torch angle were chosen as input parameters, while back-bead geometry representing quality of root-pass welding as output parameter. Findings: Based on the results from welding experiments, optimal welding conditions were selected after analyzing correlation between welding parameters and back-bead geometry such as back-bead width and back-bead height. Moreover, not only effectiveness of empirical models developed was compared and analyzed. The optimized empirical models were finally developed for predicting backbead geometry by analyzing the main effect of each factor and their influence on interaction. Research limitations/implications: This research was concentrated on the developed empirical models that can predict back-bead width and height for root-pass welding in pipeline. Originality/value: This study is intended to define correlations between process parameters and back-bead geometry as welding quality and eventually select optimal welding condition by performing root-pass welding experiment under various conditions.