This study presents a new concept that integrates the index-overlay method and a physical-based numerical model for predicting groundwater sustainability under various climate conditions and anthropogenic activities. The index-overlay DRASTIC method was modified with an analytical hierarchy process theory and employed to create groundwater vulnerability maps for the Pingtung plain groundwater basin in southern Taiwan. The physical-based MODFLOW model was used for predicting the dynamics of a basin-scale groundwater system. Solutions and calibrated hydrogeological parameters in the MODFLOW model provide feedback to the factors in the modified DRASTIC method which enables predicting groundwater vulnerability. In this study, different climate conditions were considered in the numerical model to obtain the changes in depth of water and net recharge for predicting future groundwater vulnerability and for evaluating the current state of the sustainability indicators. Results show that the depth of water and net recharge obtained from the groundwater model improve the accuracy of the groundwater vulnerability prediction. The variations of future climate conditions have less influence on the variations of groundwater vulnerability because of the dense river network that controls the shallow groundwater levels in the Pingtung plain groundwater basin. Therefore, the influence of climate conditions on the risk of groundwater contamination is also relatively low. Based on the analysis of the sustainability indicators, we found that the groundwater resource system in the Pingtung plain groundwater basin is in a critical condition of high vulnerability.