Today, every building material in a given context is associated to a carbon equivalent factor CO2e, corresponding to its Global Warming Potential (GWP). The digitalization of the building industry has facilitated the introduction of GWP assessment tools in the structural engineering practice. However, it is rarely computed at early design stages, when changes with highest impact are made, as quantitative volumetric and material information – ‘hard’ features – are still unavailable. This research uses machine learning regression models and investigates alternative strategies to predict the GWP of a building structure, using descriptive data available in competition briefs – “soft” features. To this end, we have compared a linear regression model to 9 other regression methods, with different hypothesis and errors functions. The models are ranked based on their predictive accuracy and residual plots. Despite the limited data available, and preliminary results, an accuracy of 70% was reached and residuals had relatively small standard deviations. This indicates that the models are functioning and proves the potential of soft-feature based prediction of GWP. Moreover, a first sensitivity analysis of soft-feature weights on calibrated models helped identify their relative impact on GWP. This understanding could help guiding design decisions at early stages, and could be implemented into an interactive tool for data-driven low carbon structural design.
Sandie Kate Fenton
Sandie Kate Fenton
Sandie Kate Fenton is an Architectural Engineer with a strong interest in sustainable structural design and advanced architectural technologies. She graduated from the Brussels Faculty of Engineering (VUB-ULB), Belgium, in 2018. As part of her master course, she spent one exchange year in EPFL Lausanne and specialized in structural design. She then followed an internship at the ITKE Institute for Building Structure and Structural Design in the University of Stuttgart, where she worked on biomimetic design in Architecture.
After the Masters, her concern for social architecture and her will to learn about seismic building and architecture techniques motivated her to work in social housing in Chile, with the GNO Techo para Chile. She followed with a year-long internship with the Block Research Group at the ETH Zurich, specializing in parametric and computational design, form-finding and structurally-informed design, and contributed to the digital fabrication and prototyping of funicular shells.
Since 2020, she joined the structural engineering company Bollinger+Grohmann, in Paris, where she has been working part-time as a structural engineer, and undertaking a part-time applied PhD, investigating strategies for data-driven sustainable design of lightweight structures. This research is part of the University Research School PSGS HCH Humanities, Creation, Heritage, Investment of the Future ANR-17-EURE-0021- and carried out jointly between CY Paris University and the Vrije Universiteit Brussel under the supervision of Prof. Lars De Laet, Prof. Samuel Rufat (CY Paris) and Klaas De Rycke (B+G).
PhD research
Strategies for data-driven low carbon structural design
| Date | 2021 - 2023 |
| Supervisors | Lars De Laet, Gabriele Pierluisi and Klaas De Rycke |
| Funds | CIFRE and Bollinger+Grohmann |