The application of machine learning(ML)modelling in daylight prediction has been a promising approach for reliable and effective visual comfort assessment.Although many advancements have been made,no standardized ML m...The application of machine learning(ML)modelling in daylight prediction has been a promising approach for reliable and effective visual comfort assessment.Although many advancements have been made,no standardized ML modelling framework exists in daylight assessment.In this study,625 different building layouts were generated to model useful daylight illuminance(UDI).Two state-of-the-art ML algorithms,eXtreme Gradient Boosting(XGBoost)and random forest(RF),were employed to analyze UDI in four categories:UDI-f(fell short),UDI-s(supplementary),UDI-a(autonomous),and UDI-e(exceeded).A feature(internal finish)was introduced to the framework to better reflect real-world representation.The results show that XGBoost models predict UDI with a maximum accuracy of R^(2)=0.992.Compared to RF,the XGBoost ML models can significantly reduce prediction errors.Future research directions have been specified to advance the proposed framework by introducing new features and exploring new ML architectures to standardize ML applications in daylight prediction.展开更多
It is important to improve residential thermal comfort in the high dense cities,in which wind environment is crucial.Waterside buildings take an advantage of micro-hydrological-climate in summer that should be used to...It is important to improve residential thermal comfort in the high dense cities,in which wind environment is crucial.Waterside buildings take an advantage of micro-hydrological-climate in summer that should be used to enhance residential thermal comfort especially in the subtropical region.In order to propose design approaches according to the outdoor thermal comfort of the waterside residential,a case study of Shenzhen She Kou residential district has been made.It focused on various factors that could have influence on wind environment for improving thermal comfort.Using wind velocity ratio(ΔRi)criterion,factors of building development volume,building direction and layout pattern,open space arrangement etc.have been broadly explored using FLUENT simulation.To planning parameters,the Floor Area Ratio(FAR)is significantly influence wind environment,the smaller FAR is better.To the vertical layout of the buildings,multi-storey layout and multi-storey&sub high-rise mixed layout would provide better wind environment.To the horizontal layout,the determinant is better than the peripheral.Other factors such as the buildings’direction towards the road,buildings’height,and open space setting,have influence on wind environment yet.In general,the more benefit of design layout for wind breezing,the better wind environment it could get.展开更多
基金The authors are grateful for support from the Australian Research Council(ARC)through the Linkage Infrastructure,Equipment and Facilities(LE210100019).The assistance of the ASCII Lab members at Monash University is greatly appreciated.
文摘The application of machine learning(ML)modelling in daylight prediction has been a promising approach for reliable and effective visual comfort assessment.Although many advancements have been made,no standardized ML modelling framework exists in daylight assessment.In this study,625 different building layouts were generated to model useful daylight illuminance(UDI).Two state-of-the-art ML algorithms,eXtreme Gradient Boosting(XGBoost)and random forest(RF),were employed to analyze UDI in four categories:UDI-f(fell short),UDI-s(supplementary),UDI-a(autonomous),and UDI-e(exceeded).A feature(internal finish)was introduced to the framework to better reflect real-world representation.The results show that XGBoost models predict UDI with a maximum accuracy of R^(2)=0.992.Compared to RF,the XGBoost ML models can significantly reduce prediction errors.Future research directions have been specified to advance the proposed framework by introducing new features and exploring new ML architectures to standardize ML applications in daylight prediction.
文摘It is important to improve residential thermal comfort in the high dense cities,in which wind environment is crucial.Waterside buildings take an advantage of micro-hydrological-climate in summer that should be used to enhance residential thermal comfort especially in the subtropical region.In order to propose design approaches according to the outdoor thermal comfort of the waterside residential,a case study of Shenzhen She Kou residential district has been made.It focused on various factors that could have influence on wind environment for improving thermal comfort.Using wind velocity ratio(ΔRi)criterion,factors of building development volume,building direction and layout pattern,open space arrangement etc.have been broadly explored using FLUENT simulation.To planning parameters,the Floor Area Ratio(FAR)is significantly influence wind environment,the smaller FAR is better.To the vertical layout of the buildings,multi-storey layout and multi-storey&sub high-rise mixed layout would provide better wind environment.To the horizontal layout,the determinant is better than the peripheral.Other factors such as the buildings’direction towards the road,buildings’height,and open space setting,have influence on wind environment yet.In general,the more benefit of design layout for wind breezing,the better wind environment it could get.
