Weather data is a crucial input for myriad applications in the built environment, including building energy modeling and daylight analysis. Building science practitioners and researchers have been able to select from a variety of weather files, such as Weather Year for Energy Calculation 2 (WYEC2) and the Typical Meteorological Year (TMY). However, commonly used weather files are typically synthesized to represent trends over a relatively longer periods of time, and are often unable to accurately depict climatic conditions that result from local contexts, such as the heat island effect, wind flow, even local temperature and relative humidity. This results in discrepancies in building performance simulations. This study proposes a methodology using recurrent neural networks to generate synthetic localized weather data that are significantly more accurate and representative of local conditions than standard weather files. The predictions were validated against actual on-site measurements, and achieved a low mean square error of 2.96 and over 185% improvement in validation accuracy. Overall, the performance of selected models has shown over 100% improvements in test accuracy compared with standard weather files and weather station data at the nearest airport. The proposed methodology can be used to morph generic weather files to accurately represent localized conditions, or generate localized data for a longer time span with only a subset of data available/ collected. This is useful for downstream built environment applications, especially building energy modeling, since representative weather data capturing trends of temperature and other variables will result in enhanced accuracies of the building energy models. The method can also be used in urban analysis pipelines to enhance resilience against climate change.
Natural ventilation is a promising approach to provide passive cooling in highly energy efficient buildings. A widely applied method to evaluate the performance of natural ventilation is computational fluid dynamics (CFD). However, dynamic modeling of natural ventilation from 1 h to the next is very challenging because state-of-theart CFD simulations treat windows as fixed wall boundary surfaces. The objective of this study is to propose a direct forcing approach to implement dynamic window operations in CFD simulations. The direct forcing approach marks a band of computational cells according to window positions, and adds an ad-hoc body force to the momentum equations and turbulence production term to the kinetic energy equation. The direct forcing approach shows a high level of performance when predicting volume flow rates through window apertures. The relative deviation was found to vary between 2.2% and 14%, depending on the reference wind speeds. Direct forcing also showed good performance when predicting the height of the neutral plane when the wind incident angle was less than 135◦. The direct forcing approach can be applied to study the dynamic daily or weekly CO2 variations in naturally ventilated buildings with predefined control algorithms. Future work will consider the influence of wall shear stresses and zero normal velocity to improve the accuracy of the direct forcing approach as applied to wind incident angles larger than 135◦.