Computational fluid dynamics and artificial neural network‐based analysis and forecasting of wind effects on obliquely parallel multiple building models using categorical variable encoding

Summary This research investigates the influence of wind on four closely spaced parallel building models using computational fluid dynamics (CFD). The buildings are positioned either perpendicular to the wind direction or at various oblique angles. The aerodynamic results obtained for these buildings in an interfering condition are compared to those of an isolated tall building using the interference and obliquity effect (IOE) factor. Graphical comparisons are made among the different models and faces, considering various obliquity angles (OAs). The inner building models exhibit higher pressure and force coefficients at higher OAs. The variation of pressure coefficients along the horizontal peripheral direction is also analyzed, and the trade‐offs of higher and lower OAs are discussed for the different building models. Furthermore, an artificial neural network (ANN) is trained using surface pressure coefficients from approximately 6000 data points distributed over different facets of building models. Categorical encoding is employed using one‐hot encoding‐based dummy variables for different building models, while numerical variables such as OA and X, Y, and Z coordinates are included as input for the ANN. The ANN is trained using a total of 238,340 data points (considering different building models and different OA scenarios), and its parameters are monitored during training to minimize errors and achieve high predictability. Finally, a representative case is used to plot the pressure contour obtained from the trained ANN, which is shown to be highly comparable to the CFD‐based contour.