Soil salinization poses a major threat to agricultural sustainability in arid regions worldwide, where it is intrinsically linked to irrigated agriculture. In these water-scarce environments, the equilibrium of the water and salt balance is easily disrupted, causing salts to accumulate in the root zone and directly constraining crop growth, thereby creating an urgent need for precise water and salt management strategies. While precise water and salt transport models are essential for prediction and control, their accuracy is often compromised by parameter uncertainty. To address this, we developed a lumped water-salt balance model for the Hetao Irrigation District (HID) in China, integrating farmland and non-farmland areas and vertically structured into root zone, transition layer, and aquifer. A novel calibration approach, combining random sampling with Kernel Density Estimation (KDE), was introduced to identify optimal parameter ranges rather than single values, thereby enhancing model robustness. The model was calibrated and validated using data from the Yichang sub-district. Results showed that the water balance module performed satisfactorily in simulating groundwater depth (R2 = 0.79 for calibration, 0.65 for validation). The salt balance module effectively replicated the general trends of soil salinity dynamics, albeit with lower R2 values, which reflects the challenges of high spatial variability and data scarcity. This method innovatively addresses the common challenge of parameter uncertainty in the model, narrows the parameter value ranges, enhances model reliability, and incorporates sensitivity analysis (SA) to identify key parameters in the water-salt model. This study not only provides a practical tool for managing water and salt dynamics in HID but also offers a methodological reference for addressing parameter uncertainty in hydrological modeling of other data-scarce regions.