The objective of this study is to predict salinity concentration (SC) using Artificial Neural Network (ANN) for a case study in SocTrang city, Vietnam. This can be achieved by evaluating the current state of salinity intrusion in the main rivers; setting-up, calibrating and validating the ANN; and then predicting SC at different lead times. The results show that SC in the study area has been found to have increasing trend recently, especially in the months Feb and March, and thus affecting on agricultural production. The calibrated ANN structures have successfully demonstrated that the SC can be predicted considering different input factors and leading time. The predicted results will provide useful information for local government and farmers to be well-prepared to adapt to salinity intrusion for agriculture practice in the Mekong Delta.