Carbon dioxide(CO₂) emission from rivers to the atmosphere is a key component in the global carbon cycle. Most of the rivers are supersaturated with CO₂. At a global scale, the amount of CO₂ emission from rivers is reported to be five-fold greater than that from lakes and reservoirs, but relevant data are rare in Korea. The objectives of this study is to estimate the CO₂ net atmospheric flux(NAF) from the upstream of Gangjeong-Goryeong Weir(GGW), Dalseong Weir(DSW), Hapcheon-Changnyeong Weir(HCW), and Changnyeong-Haman Weir(CHW) located in Nakdong RiverSouth Korea) using field and laboratory experimentsand to apply data mining techniques to develop parsimonious prediction models that can be used to estimate CO₂ NAF with physical and water quality variables that can becollected easily. As a result, the study sites were all heterotrophic systems that often released CO₂ to the atmosphere, except when the algal photosynthesis was active.The median CO₂ NAF was minimum 391.5 mg-CO₂/m²day at GGW and maximum 1472.7 mg-CO₂/m²day at DSW. The CO₂ NAF showed a negative correlation with pH and Chl-a since the overgrowth of the algae consumed CO₂ in the water and increased the pH. As the parsimonious multiple regression model and random forest model developed, this study showed an excellent performance with the Adj.R² value higher than 0.77 in all weirs. Thus, these methods can be used to estimate CO₂ NAF in the river even if there is no pCO₂ measurement data.