Development of a machine-learning framework for overall daylight and visual comfort assessment in early design stages

Hanieh Nourkojouri; Nastaran Seyed Shafavi; Mohammad Tahsildoost; Zahra Sadat Zomorodian

doi:10.15627/jd.2021.21

Author(s)

Hanieh Nourkojouri Department of Architecture and Urban planning, Shahid beheshti University,Tehran,Iran

Nastaran Seyed Shafavi Department of Architecture and Urban planning, Shahid beheshti University,Tehran,Iran

Mohammad Tahsildoost Department of Architecture and Urban planning, Shahid beheshti University,Tehran,Iran

Zahra Sadat Zomorodian Department of Architecture and Urban planning, Shahid beheshti University,Tehran,Iran

Abstract

Application of machine learning methods as an alternative for building simulation software has been progressive in recent years. This research is mainly focused on the assessment of machine learning algorithms in prediction of daylight and visual comfort metrics in the early design stages and providing a framework for the required analyses. A dataset was primarily derived from 2880 simulations developed from Honeybee for Grasshopper. The simulations were conducted for a side-lit shoebox model. The alternatives emerged from different physical features, including room dimensions, interior surfaces' reflectance factor, window dimensions, room orientations, number of windows, and shading states. Five metrics were applied for daylight evaluations, including useful daylight illuminance, spatial daylight autonomy, mean daylight autonomy, annual sunlit exposure, and spatial visual discomfort. Moreover, view quality was analyzed via a grasshopper-based algorithm, developed from the LEED v4 evaluation framework. The dataset was further analyzed with an artificial neural network algorithm. The proposed predictive model had an architecture with a single hidden layer consisting of 40 neurons. The predictive model learns through a trial and error method with the aid of loss functions of mean absolute error and mean square error. The model was further analyzed with a new set of data for the validation process. The accuracy of the predictions was estimated at 97% on average. The View range metric in the quality view assessment, mean daylight autonomy and useful daylight illuminance had the best prediction accuracy among others respectively. The developed model which is presented as a framework could be used in early design stage analyses without the requirement of time-consuming simulations.

Publication Details

Page(s) 270-283

DOI 10.15627/jd.2021.21

Published Journal: Journal of Daylighting, Volume: 8, Issue: 2, Year: 2021

Request the full text from PASTIC

Keywords

Visual Comfort, artificial neural networks, Machine learning, Daylight assessment

References

Mariana G.,Steverson B.,Heerwagen J.,Kampschroer K.,Hunter C.,K. C. . .. , : .

Gonzales B.,Plitnick M.,Rea M. .2017 .The impact of daytime light exposures on sleep and mood in office workers. Sleep Health, 3 : .

IEA ,Lighting .2006 .-policies-for-energy-efficient-lighting.. International Energy Agency, 26 Jun, : .

Ürge-Vorsatz D.,Eyre N.,Graham P.,Harvey D.,Jiang Y.,Kornevall C. .2012 .Toward a sustainable future. , : .

IEA ,Energy Efficiency .2019 .. International energy agency, : .

Reinhart .2014 .Daylighting handbook I: Funamentals, designing with the sun. , : .

Ayoub M. .2019 .A multivariate regression to predict daylighting and energy consumption of residential buildings within hybrid settlements in hot-desert climates. Indoor and built environment 28, : 848-866.

Aries M.,Aarts M.,Hoof J. v. .2015 .Daylight and health: A review of the evidence and consequences for the built environment. Lighting research and technology 47, : 6-27.

Konis K.,Selkowitz S. .2017 .Effective daylighting with high performance facade. , : .

Ayoub M. .2020 .A review on machine learning algorithms to predict daylighting inside buildings. Solar energy 202, : 249-275.

Ward G.,States United .1994 .The RADIANCE lighting simulation and rendering system. in: Proceedings of the 21st annual conference on Computer Graphics and Interactive Techniques, : 459-472.

Nault E.,Moonen P.,Rey E.,Andersen M. .2017 .Predictive models for assessing the passive solar and daylight potential of neighborhood designs: A comparative proof-of-concept study. Building and Environment, 116 : 1-16.

C. L. Lorenza A. B.,Spaetha M. S.,Packianatherb M. S. .2019 .Artificial Neural Networks for parametric daylight design. Architectural Science and Review, 63 : 210-221.

Mardaljevic J. .2015 .Climate-based daylight modelling and its discontents, in Simple Buildings Better Buildings? Delivering Performance through Engineered Solutions. CIBSE Technical Symposium, : 180-192.

Ayoub M. .2019 .A multivariate regression to predict daylighting and energy consumption of residential buildingswithin hybrid settlements in hot-desert climates. Indoor Building Environment, 28 : 848-866.

Radziszeweski K.,Waczynska M. .2018 .Machine learning algorithm-based tool and digital framework for substituting daylight simulation in earlystage architectural design evaluation, in The symposium on simulation for architecture and. , : .

Liu Z.,Wu D.,Liu Y.,Han Z.,L Z.,Gao J.,Gao G. .2019 .Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction, Energy Explor. Exploit, 37 : 1426-1451.

Becalli M.,Bonomolo M.,Ciulla G.,Brano V. .2018 .Assessment of indoor illuminance and study on best photosensors' position for design and commissioning of daylight linked control systems. A new method based on artificial neural networks, Energy, 154 : 466-476.

Hon Y.,Shen L.,Sun C. .2021 .Developing a parametric morphable annual daylight prediction model with improved generalization capability for the early stages of office building design. Building and Environment, 200 : 107932.

Lorenz C.,Packianather M.,Spaeth A.,C. De Souza A. .2018 .Artificial neural network based modeling for daylight evaluation, in The symposium on simulation for architecture and. , : .

Yacine S.,Noureddine Z.,Piga B.,Morello E. .2017 .Developing neural networks to investigate relationships between lighting quality and lighting glare indices. Energy Procedia, 122 : 799-804.

Rathi P.,Approach to Feature A Novel .2020 ./a-novel-approach-to-feature-importanceshapley-additive-explanations-d18af30fc21b.. , : .

USGBC ,Washington D.C: The U.S Green Building Council .2016 .LEED® green building program v.4. , : .