To minimize the damage from contaminant accidents in rivers, early identification of the contaminant source is crucial. Thus, in this study, a framework combining Machine Learning (ML) and the Transient Storage zone Model (TSM) was developed to predict the spill location and mass of a contaminant source. The TSM model was employed to simulate non-Fickian Breakthrough Curves (BTCs), which entails relevant information of the contaminant source. Then, the ML models were used to identify the BTC features, characterized by 21 variables, to predict the spill location and mass. The proposed framework was applied to the Gam Creek, South Korea, in which two tracer tests were conducted. In this study, six ML methods were applied for the prediction of spill location and mass, while the most relevant BTC features were selected by Recursive Feature Elimination Cross-Validation (RFECV). Model applications to field data showed that the ensemble Decision tree models, Random Forest (RF) and Xgboost (XGB), were the most efficient and feasible in predicting the contaminant source.

River meanders form complex 3D flow patterns, including secondary flows and flow separation. In particular, the flow separation traps solutes and delays their transport via storage effects associated with recirculating flows. The simulation of the separated flows highly relies in the performance of turbulence models. Thus, these closure schemes can control dispersion behaviors simulated in rivers. This study performs 3D simulations to quantify the impact of the turbulence models on solute transport simulations in channels under different sinuosity conditions. The 3D Reynolds-averaged Navier-Stokes equations coupled with the $k-\epsilon$ , $k-\omega$ and SST $k-\omega$ models are adopted for flow simulations. The 3D Lagrangian particle-tracking model simulates solute transport. An increase in sinuosity causes strong transverse gradients of mean velocity, thereby driving the onset of the separated flow recirculation along the outer bank. Here, the onset and extent of the flow separation are strongly influenced by the turbulence models. The $k-\epsilon$ model fails to reproduce the flow separation or underestimates its size. As a result, the $k-\epsilon$ model yields residence times shorter than those of other models. In contrast, the SST $k-\omega$ model exhibits a strong tailing of breakthrough curves by generating more pronounced flow separation.