Accurately predicting dynamic noise levels in urban environments is non- trivial. This study aims to optimally combine both simulated and empirical data. Acoustic data from microphone arrays, tra_c and weather data was merged with a simulated noise map, created with a statistical emulator tool (meta-model). Each hour, a noise map is generated by the meta-model with the measured tra_c and weather data. This map is algorithmically merged with the measured readings to form a new composite map. The resulting an- alyzed map is the best linear unbiased estimator under certain assumptions. The performance is evaluated with leave-one-out cross-validation. The per- formance of the method depends on the accuracy of the meta-model, the input parameters of the meta-model and the structure of the error covari- ances between the simulated noise level errors. With 16 microphones over an area of 3km2, this new method achieves a reduction of 30% of the root- mean-square error when compared to a meta-model only.