| id |
ecaade2024_408 |
| authors |
Mottaghi, Esmaeil; Erhan, Halil; Abuzuraiq, Ahmed M.; Okhoya, Victor; Ampanavos, Spyridon; Bernal, Marcelo; Chen, Cheney; Madkour, Yehia |
| year |
2024 |
| title |
Integrating Surrogate Modeling and Design Analytics for Data-informed Exploration in the Early Phases of Building Design |
| doi |
https://doi.org/10.52842/conf.ecaade.2024.2.301
|
| source |
Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 2, pp. 301–310 |
| summary |
Building design workflows have been influenced by incorporating data-driven decisions, algorithmic content generation, and performance analysis support offered by machine learning methods. The challenge lies in bringing these seemingly isolated but highly related design tasks together in an engaging design environment that can maintain designers' creative decision-making flow while reducing system interferences' complexity. This paper presents D-Predict.v2 as an experimental prototype we developed following a design study methodology to tackle this challenge. As a contribution, we propose a design workflow and a system that can be adapted to support building performance prediction using surrogate models in direct or parametric design modelling driven by interactive data visualizations. Our initial findings demonstrated that expert designers welcomed the proposed workflow with caution and recommendations. Our future work will focus on conducting ecologically valid case studies and rebuilding the system by addressing the concerns raised by the expert designers. |
| keywords |
Generative Design, Building Performance Assessment, Surrogate Modelling, Design Analytics |
| series |
eCAADe |
| email |
|
| full text |
 file.pdf (2,077,630 bytes) |
| references |
Content-type: text/plain
|
Abu Zuraiq, A. (2020)
 DesignSense: A visual analytics interface for navigating generated design spaces
, Master's thesis, Simon Fraser University, SIAT, Surrey, BC, Canada
|
|
|
|
|
Beham, M., Herzner, W., Eduard M.G., and Kehrer, J. (2014)
Cupid: Cluster-Based Exploration of Geometry Generators with Parallel Coordinates and Radial Trees
, IEEE Trans. on Vis. and Comp. Graphics, 20(12):1693-1702
|
|
|
|
|
Chegari, B., Tabaa, M., Simeu, E., Moutaouakkil, F., & Medromi, H. (2022)
An optimal surrogate-model-based approach to support comfortable and nearly zero energy buildings design
, Energy, 248, 123584
|
|
|
|
|
Erhan, H., Abuzuraiq, A. M., Zarei, M., Alsalman, O., Woodbury, R., & Dill, J. (2020)
What do design data say about your model? A case study on reliability and validity
, Proc. of the 25th CAADRIA (Vol. 1, pp. 557-567)
|
|
|
|
|
Erhan, H., Chan, J., Fung, G., Shireen, N., & Wang, I. (2017)
Understanding Cognitive Overload in Generative Design - An Epistemic Action Analysis
, CAADRIA 2017
|
|
|
|
|
Fuchkina, E., Schneider, S., Bertel, S., & Osintseva, I. (2018)
Design Space Exploration Framework: A modular approach to flexibly explore large sets of design variants of parametric models within a single environment
, Proc. of 36th eCAADe 2018
|
|
|
|
|
Herbert A Simon. (1969)
The sciences of the artificial
, MIT Press
|
|
|
|
|
Kastel, J. van. (2018)
Visual Analytics for Generative Design Exploration: An interactive 3D data environment for a computational design system facilitating the performance-driven design process of a nearly Zero-Energy sports hall
, Master's thesis, TUDelft
|
|
|
|
|
Matejka, J., Glueck, M., Bradner, E., Hashemi, A., Grossman, T., & Fitzmaurice, G. (2018)
Dream Lens: Exploration and Visualization of Large-Scale Generative Design Datasets
, Proceedings of the 2018 Conference on Human Factors in Computing Systems
|
|
|
|
|
Mottaghi, E., Abuzuraiq, A. M., & Erhan, H. (2024)
D-Predict: Integrating generative design and surrogate modelling with design analytics
, 29th CAADRIA, Singapore
|
|
|
|
|
Sedlmair, M., Meyer, M., & Munzner, T. (2012)
Design study methodology: Reflections from the trenches and the stacks
, IEEE Trans. on Vis. and Comp. Graphics, 18(12), 2431-2440
|
|
|
|
|
Thornton Tomasetti (2023)
Design Explorer 2
, Accessed 8 May 2023 from https://tt-acm.github.io/DesignExplorer/
|
|
|
|
|
Westermann, P., & Evins, R. (2019)
Surrogate modelling for sustainable building design-A review
, Energy and Buildings, 198, 170-186
|
|
|
|
|
Westermann, P., Christiaanse, T.V., Beckett, W., Kovacs, P., & Evins, R. (2021)
BESOS: Building and Energy Simulation, Optimization and Surrogate Modelling
, J. Open Source Softw
|
|
|
|
|
Wortmann, T., Costa, A., Nannicini, G., & Schroepfer, T. (2015)
Advantages of surrogate models for architectural design optimization
, AI EDAM, 29(4), 471-481
|
|
|
|
|
Yousif, S., & Bolojan, D. (2021)
Deep-Performance - Incorporating Deep Learning for Automating Building Performance Simulation in Generative Systems
, Proc. Of 26th CAADRIA
|
|
|
|
| last changed |
2024/11/17 22:05 |
|
