Streams are important freshwater habitats in large-scale carbon budgets because of their high CO2 fluxes which are driven by high CO2 concentrations and surface-water turbulence. High CO2 concentrations are promoted by terrestrial carbon inputs, groundwater flow, and internal respiration, all of which vary greatly across space and time. We used environmental monitoring data to calculate CO2 concentrations along with a wide range of predictor variables including outputs from a national hydrological model and trained machine learning models to predict spatially distributed seasonal CO2 concentrations in Danish streams. We found that streams were supersaturated in dissolved CO2 (mean = 118 μM) and higher during autumn and winter than during spring and summer. The best model, a Random Forest model, scored R2 = 0.46, MAE = 46.0 μM, and ⍴ = 0.72 on a test set. The most important predictor variables were catchment slope, seasonality, height above nearest drainage, and depth to groundwater, highlighting the importance of landscape morphometry and soil-groundwater-stream connectivity. Stream CO2 fluxes determined from the predicted concentrations and gas transfer velocities estimated using empirical relationships averaged 253 mmol m−2 d−1, and the annual emissions were 513 Gg CO2 from the national stream network (area = 139 km2). Our analysis presents a framework for modeling seasonal CO2 concentrations and estimating fluxes at a national scale by means of large-scale hydrological model outputs. Future efforts should consider further improving the temporal resolution, direct measurements of fluxes and gas transfer velocities, and seasonal variation in stream surface area.