A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Implementing dynamic subset sensitivity analysis for early design datasets
Abstract Engaging with performance feedback in early building design often involves building a custom parametric model and generating large datasets, which is not always feasible. Alternatively, large parametric datasets of general design problems and filtering methods could be used together to explore specific design decisions. This paper investigates the generalizability of a method that dynamically assesses variable importance and likely influence on performance objectives as a precomputed design space is filtered down. The method first trains linear model trees to predict building performance objectives across a generic design space. Leaf node models are then aggregated to provide feedback on variable importance in different design space regions. This approach is tested on three design problems that vary in number of variables, samples, and design space structure to reveal advantages and potential limitations of the method. Algorithm improvements are proposed, and general recommendations are developed to apply it on future datasets.
Highlights New methods are required to identify distinct variable behavior in the design space. The sensitivity method supports real-time decision making as design criteria emerge. It is important to account for the robustness of the leaf node models. This method provides ranges to design within and supports design freedom. The sampling technique impacts the ability to accurately capture local behaviors.
Implementing dynamic subset sensitivity analysis for early design datasets
Abstract Engaging with performance feedback in early building design often involves building a custom parametric model and generating large datasets, which is not always feasible. Alternatively, large parametric datasets of general design problems and filtering methods could be used together to explore specific design decisions. This paper investigates the generalizability of a method that dynamically assesses variable importance and likely influence on performance objectives as a precomputed design space is filtered down. The method first trains linear model trees to predict building performance objectives across a generic design space. Leaf node models are then aggregated to provide feedback on variable importance in different design space regions. This approach is tested on three design problems that vary in number of variables, samples, and design space structure to reveal advantages and potential limitations of the method. Algorithm improvements are proposed, and general recommendations are developed to apply it on future datasets.
Highlights New methods are required to identify distinct variable behavior in the design space. The sensitivity method supports real-time decision making as design criteria emerge. It is important to account for the robustness of the leaf node models. This method provides ranges to design within and supports design freedom. The sampling technique impacts the ability to accurately capture local behaviors.
Implementing dynamic subset sensitivity analysis for early design datasets
Hinkle, Laura E. (author) / Pavlak, Gregory (author) / Curtis, Leland (author) / Brown, Nathan C. (author)
2023-11-12
Article (Journal)
Electronic Resource
English
Subset selection from large datasets for Kriging modeling
| British Library Online Contents | 2009
Implementing Variational Design Sensitivity Analysis
| British Library Conference Proceedings | 1997
Extension of subset simulation approach for uncertainty propagation and global sensitivity analysis
| Taylor & Francis Verlag | 2012
Dynamic Probability Analysis for Construction Schedule Using Subset Simulation
| DOAJ | 2021