We present a two-stage procedure underlying CHIM (clustering-based hybrid inundation model), which is composed of the linear regression models and ANNs to build the regional flood inundation estimation model. The two-stage procedure includes data preprocessing and model building stages. In the data preprocessing stage, the K-means clustering is used to categorize the data points of the different flooding characteristics and to identify the control point(s) from individual flooding cluster(s). In the model building stage, three classes of flood depth estimation models are built in each cluster: the back-propagation neural network (BPNN) for each control point, the linear regression models for the grids those have highly linear correlation with the control point, and a multi-grid BPNN for the grids those do not exist highly linear correlation with the control point. The effectiveness of the proposed approach is tested in the Dacun township in Taiwan. The results show that the CHIM can continuously and adequately provide one-hour-ahead flood inundation maps and effectively reduce 99% CPU time.