Prediction of wind properties in urban environments using artificial neural network

Artificial neural network (ANN) modeling has been performed to predict turbulent boundary layer characteristics for rough terrain based on experimental tests conducted in a boundary-layer wind tunnel to simulate atmospheric boundary layer using passive roughness devices such as spires, barriers, roughness elements on the floor, and slots in the extended test section. Different configurations of passive devices assisted to simulate urban terrains. A part of the wind tunnel test results are used as training sets for the ANN, and the other part of the test results are used to compare the prediction results of the ANN. Two ANN models have been developed in this study. The first one has been used to predict mean velocity, turbulence intensity, and model length scale factor. Results show that ANN is an efficient, accurate, and robust modeling procedure to predict turbulent characteristics of wind. In particular, it was found that the ANN-predicted wind mean velocities are within 4.7%, turbulence intensities are within 6.2%, and model length scale factors are within 3.8% of the actual measured values. In addition, another ANN model has been developed to predict instantaneous velocities that enables calculating the power spectral density of longitudinal velocity fluctuations. Results show that the predicted power spectra are in a good agreement with the power spectra obtained from measured instantaneous velocities.