A machine learning-enhanced design optimizer for urban cooling

Urban cooling becomes a priority in urban planning and design practices. Limited by the slow running speed and prescriptive nature, existing computational tools such as simulation and optimization are yet to be fully integrated in the design decision-making process. This paper describes the Machine Learning-Enhanced Design Optimizer (MLEDO), a novel workflow in search of optimal design option for urban cooling. A physics-based simulation model was developed to assess the cooling performances of a large database of urban design variations. The database was used to train an Artificial Neural Network model, which was then linked with a Genetic Algorithm to rapidly identify optimal design options. The MLEDO workflow was evaluated using a new development urban site against a traditional Simulation-based Genetic Algorithm Design Optimizer (SGADO) as well as human designers. MLEDO outperformed the latter two in terms of efficiency and the performance of the optimal design options. It can also quantify the importance of design parameters in their contribution to cooling performances, which can be used to enhance the understanding of human designers and inform design revisions. MLEDO has the potential to be further developed into a software tool in support of early-stage urban design.

[1]  Shi-Jie Cao,et al.  Development trend and challenges of sustainable urban design in the digital age , 2020 .

[2]  Mohammadreza Hafezi,et al.  A framework for pedestrian-level wind conditions improvement in urban areas: CFD simulation and optimization , 2020 .

[3]  A. U. Weerasuriya,et al.  Optimizing Lift-up Design to Maximize Pedestrian Wind and Thermal Comfort in ‘Hot-Calm’ and ‘Cold-Windy’ Climates , 2020 .

[4]  Zhu Neng,et al.  Modelling and simulation of the urban heat island effect in a tropical seaside city considering multiple street canyons , 2020, Indoor and Built Environment.

[5]  C. Ren,et al.  Cause-specific mortality attributable to cold and hot ambient temperatures in Hong Kong: a time-series study, 2006–2016 , 2020, Sustainable Cities and Society.

[6]  Xiaopeng Li,et al.  Optimal design of building environment with hybrid genetic algorithm, artificial neural network, multivariate regression analysis and fuzzy logic controller , 2020, Building and Environment.

[7]  P. Jones,et al.  Urban Building Energy and Climate (UrBEC) simulation: Example application and field evaluation in Sai Ying Pun, Hong Kong , 2020 .

[8]  P. Jones,et al.  Simulation-Informed Urban Design: Improving Urban Microclimate in Real-World Practice in a High Density City. , 2019, IOP Conference Series: Earth and Environmental Science.

[9]  Jan Hensen,et al.  Building Performance Simulation for Design and Operation , 2019 .

[10]  Cheuk Ming Mak,et al.  A multi-stage optimization of pedestrian level wind environment and thermal comfort with lift-up design in ideal urban canyons , 2019, Sustainable Cities and Society.

[11]  Steven Jige Quan,et al.  Smart Design for Sustainable Neighborhood Development , 2019, Energy Procedia.

[12]  Ali Malkawi,et al.  Design-based natural ventilation evaluation in early stage for high performance buildings , 2019, Sustainable Cities and Society.

[13]  Danil Nagy,et al.  Generative urban design: integrating financial and energy goals for automated neighborhood layout , 2018 .

[14]  P. Jones,et al.  A zonal model for assessing street canyon air temperature of high-density cities , 2018 .

[15]  E. Hawkins,et al.  Global risk of deadly heat , 2017 .

[16]  Lea A. Ruefenacht,et al.  Strategies for Cooling Singapore: A catalogue of 80+ measures to mitigate urban heat island and improve outdoor thermal comfort , 2017 .

[17]  Ali Cheshmehzangi,et al.  Multi-spatial environmental performance evaluation towards integrated urban design: A procedural approach with computational simulations , 2016 .

[18]  Chaobin Zhou,et al.  Outdoor thermal environments and activities in open space: An experiment study in humid subtropical climates , 2016 .

[19]  Ivana Bajsanski,et al.  Evaluation and improvement of outdoor thermal comfort in urban areas on extreme temperature days: Applications of automatic algorithms , 2015 .

[20]  Donglin Zeng,et al.  Reinforcement Learning Trees , 2015, Journal of the American Statistical Association.

[21]  Pierre Villon,et al.  Urban layout optimization framework to maximize direct solar irradiation , 2015, Comput. Environ. Urban Syst..

[22]  Jianxiang Huang,et al.  CityComfort+: A simulation-based method for predicting mean radiant temperature in dense urban areas , 2014 .

[23]  Luis C. Dias,et al.  Multi-objective optimization for building retrofit: A model using genetic algorithm and artificial neural network and an application , 2014 .

[24]  D. Gossard,et al.  Multi-objective optimization of a building envelope for thermal performance using genetic algorithms and artificial neural network , 2013 .

[25]  Wenjie Yang,et al.  Performance-driven architectural design and optimization technique from a perspective of architects , 2013 .

[26]  Ralph Evins,et al.  A review of computational optimisation methods applied to sustainable building design , 2013 .

[27]  David Rutten,et al.  Galapagos: On the Logic and Limitations of Generic Solvers , 2013 .

[28]  Rex Britter,et al.  Combining a Detailed Building Energy Model with a Physically-Based Urban Canopy Model , 2011 .

[29]  Hong Min Kim,et al.  Multi-objective optimization in urban design , 2011, SpringSim.

[30]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[31]  Fariborz Haghighat,et al.  Multiobjective optimization of building design using TRNSYS simulations, genetic algorithm, and Artificial Neural Network , 2010 .

[32]  Maria Kolokotroni,et al.  Urban heat island intensity in London: An investigation of the impact of physical characteristics on changes in outdoor air temperature during summer , 2008 .

[33]  E. Ng.  Policies and technical guidelines for urban planning of high-density cities – air ventilation assessment (AVA) of Hong Kong , 2008, Building and Environment.

[34]  H. Mayer,et al.  Modelling radiation fluxes in simple and complex environments: basics of the RayMan model , 2007, International journal of biometeorology.

[35]  Boon Lay Ong,et al.  Green plot ratio: an ecological measure for architecture and urban planning , 2003 .

[36]  Leslie K. Norford,et al.  A design optimization tool based on a genetic algorithm , 2002 .

[37]  L. Breiman.  Random Forests , 2001, Encyclopedia of Machine Learning and Data Mining.

[38]  Javier Monedero,et al.  Parametric Design. A Review and Some Experiences , 2000, Proceedings of the 15th International Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe).

[39]  M. Bruse,et al.  Simulating surface–plant–air interactions inside urban environments with a three dimensional numerical model , 1998 .

[40]  Roberto Battiti,et al.  First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.

[41]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[42]  Wowo Ding,et al.  An Urban Form Experiment on Urban Heat Island Effect in High Density Area , 2016 .

[43]  George Havenith,et al.  UTCI—Why another thermal index? , 2011, International Journal of Biometeorology.

[44]  Wong Nyuk Hien,et al.  Development of empirical models for an estate level air temperature prediction in Singapore , 2009 .

[45]  Alberto Hernandez Neto,et al.  Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption , 2008 .

[46]  Ryozo Ooka,et al.  Study on optimum design method for pleasant outdoor thermal environment using genetic algorithms (GA) and coupled simulation of convection, radiation and conduction , 2008 .

[47]  Luisa Gama Caldas,et al.  An evolution-based generative design system : using adaptation to shape architectural form , 2001 .

[48]  Qingyan Chen,et al.  APPLICATION OF CFD TOOLS FOR INDOOR AND OUTDOOR ENVIRONMENT DESIGN , 2000 .

[49]  D. Heiss-Czedik.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[50]  Stephen A. Billings,et al.  Non-linear system identification using neural networks , 1990 .