Models that simulate water flow and quality, particularly related to nitrate ions, are commonly used on a catchment-scale. However, tracking nitrate ions is a challenging task due to the intricate processes that affect them, such as phase exchanges, transformations, and interactions with various environmental media. In general, models capable of carrying out all tasks required to simulate water flow and quality at the same time, are rare. Additionally, most available models focus only on specific compartments of the watershed, such as surface water, topsoil, unsaturated zone, or groundwater. Taken together, these two challenges can lead to oversimplified representations of a system's hydrology, as catchment internal processes become neglected due to missing information (lack of informative measurements, or models not focusing on all watershed compartments). Attempting to combine these models or to couple different watershed compartments results in complex calculations, increased run times, and a large number of parameters to estimate. Artificial Intelligence (AI) models have been massively used in environmental studies but, so far, the majority of them have been tested theoretically and not under real conditions. To overcome these challenges, stable isotope data are often employed to calibrate and validate internal catchment processes of these models. While water stable isotopes (δ¹⁸O and δ²H of H₂O) have been extensively used in many water flow models, the use of nitrate isotopes (δ¹⁵N and δ¹⁸O of NO₃^–) in water quality models remains poorly explored. Nitrate isotopes can help trace the origin of NO₃^– contamination and disentangle the complex reactions and dynamics that nitrate undergoes during transport. Hence, we propose that incorporating nitrate isotopes into catchment-scale water flow and quality models can substantially enhance the accuracy of these models. This review provides an overview of the current use of catchment hydrological models in predicting flow and fate of solutes. We discuss their limitations and highlight the potential of combining these models with nitrate isotopes. Ultimately, this approach may reduce prediction uncertainties and provide more effective guidance for water management decisions.