The ability to predict dissolved oxygen, which is a critical water quality (WQ) parameter, is critical for aquatic managers responsible for maintaining ecosystem health and the management of reservoirs affected by WQ. This paper reports forecasting dissolved oxygen (DO) concentration using multivariate adaptive regression splines (MARS) of running river water using a set of water quality and hydro-meteorological variables. This study’s key objectives were to assess input selection methods and five multi-resolution analyses as a data extraction approach. Moreover, the hybrid model is prepared by maximum overlap discrete wavelet transformation (MODWT) with the MARS model (i.e., MODWT-MARS). The proposed model is further compared with numerous machine learning methods. The result shows that the hybrid algorithms (i.e., MODWT-MARS) outperformed the other models (r = 0.981, WI = 0.990, RMAE = 2.47% and MAE = 0.089). This hybrid method may serve as the foundation for forecasting water quality variables with fewer predictor variables.