Accurate prediction of wetland soil organic carbon concentration and an understanding of its controlling factors are important for studying regional climate change and wetland carbon cycles; with that knowledge mechanisms can be put in place that are conducive to sustainable ecosystem management for environmental health. In this study, a hybrid approach combining an artificial neural network and ordinary kriging and 103 soil samples at three soil depth ranges (0–30, 30–60, and 60–100 cm) were used to predict wetland soil organic carbon concentration in China’s Liao River Basin. The model evaluation indicated that a combination of artificial neural network and ordinary kriging and limited soil samples achieved good performance in predicting wetland soil organic carbon concentration. Wetland soil organic carbon concentration in the Liao River Basin has apparent spatial and vertical heterogeneities with values decreasing from southeast to northwest and concentrates present mainly in the topsoil (0–30 cm). Mean wetland soil organic carbon concentration values at the three soil depths were 10.43 ± 0.38, 7.93 ± 0.25, and 7.61 ± 0.22 g/kg, respectively, which are smaller than those over other wetland regions in Northeast China. Terrain aspect contributed the most in predicting wetland soil organic carbon concentration at each of the three soil depths, followed by normalized difference vegetation index at 0–30 cm and mean annual precipitation at 30–60 and 60–100 cm. This study provides a framework method and baseline to quantify the soil organic carbon concentration dynamics in response to climatic and anthropogenic drivers.