Scouring around a bridge pier removes sediment from the riverbed and banks directly around the bridge pier due to water flow. Local scouring occurs because the water flow is accelerated as it passes through the narrow gaps between the bridge piers, causing a reduction in pressure caused by the erosion of the riverbed material around the bridge piers. This paper modelled local scour depth around bridge piers using XGBoost and support vector machine tuned with particle swarm optimization (SVM-PSO)-based machine learning approaches. Clear water scouring (CWS) datasets were collected from previous literature, considering input parameters such as bridge pier geometry, flow characteristics, and sediment properties. Five non-dimensional influencing input parameters, including the ratio of pier width to flow depth (b/y), ratio of approach mean velocity to critical velocity (V/Vc), Froude number (Fr), ratio of mean particle size to pier width (d50/b), and standard deviation of bed material (σg), were selected as input parameters for modelling of CWS depth. A gamma test was conducted to identify the most effective combinations of input parameters. As indicated by statistical indices, the proposed XGBoost and SVM-PSO models demonstrated superior predictive performance for scour depth compared to existing empirical approaches. The coefficient of determination (R2) value exceeded 0.90 for CWS in the developed models. Compared with four popular selected existing models using statistical indices, the present XGBoost model outperformed the SVM-PSO model and the selected empirical models, providing more accurate predictions for scour depth. Thus, XGBoost (present model) is a more reliable, efficient, and suitable model, and it is recommended for estimating CWS depth around bridge piers under temporal conditions.