Abstract: As an important recharge source for the Baiyangdian lake, the quality of groundwater directly affects the health and stability of the aquatic ecosystem in the lake area. An indicator system for identifying potential risks of groundwater nitrate pollution and the Groundwater Nitrate Pollution Risk Index (NPRIGW) were constructed in the plain area of the Baiyangdian lake watershed. The system includes eight indicators: annual precipitation, groundwater depth, soil type, annual vegetation coverage, landform type, landuse type, apparent nitrogen balance in farmland, and the proportion of the total output value of agriculture, forestry, animal husbandry and fishery to Gross Domestic Product (GDP). The Analytic Hierarchy Process (AHP) and Random Forest (RF) were used to determine the weights of the indicators. The potential risks of nitrate pollution in shallow groundwater in the Baiyangdian lake watershed were identified. And the impacts of different weighting methods on the spatial patterns of potential risk zoning for groundwater nitrate pollution were evaluated systematically through pixel level deviation analysis. The results showed that the areas with slight pollution risk and low pollution risk account for 16.08% and 25.97% of the study area, respectively. Moreover, 56.51% of the areas faced the potential nitrate pollution risks of moderate or above levels. They were concentrated in the southeastern part of Fangshan District in Beijing, the western and northern parts of Baoding City, as well as some counties in the west and the north of Shijiazhuang City. There are also sporadic distributions in the central part of the plain area. The potential risk zoning of groundwater nitrate pollution obtained by the two weighting methods was highly consistent in space. It had the same risk grades about 64.24% of the study area, and there was a slight deviation of one grade with 34.78% of the study area. The area proportion with deviations of two or more grades was extremely low. These findings validated the reliability of the indicator system for identifying potential risks of groundwater nitrate pollution in the Baiyangdian lake watershed. This study not only provides a refined spatial decision-making basis for the prevention and control of groundwater pollution risks in the Baiyangdian lake watershed, but also provides a methodological reference for groundwater environmental risk assessment in agricultural dominated plain areas.