Researchers from Loughborough University, the University of Sheffield, Newcastle University and Beijing University of Technology have built a deterministic workflow that reads an Industry Foundation Classes, or IFC, file directly and turns it into a complete material decision engine. IFC is the vendor-neutral exchange format maintained by buildingSMART, designed so that a model created in one authoring platform can be understood by another. Instead of treating that file as a mere snapshot for drawings and schedules, the prototype extracts component quantities and material assignments, runs automated data-quality checks, maps the results to a prototype material database, and then evaluates entire wall-floor-roof combinations for both embodied carbon and circularity. Because every step follows fixed rules, the same input file always produces the same output, a property the authors regard as essential for traceable design support.

The test bed was a buildingSMART reference IFC model, a deliberately ordinary assembly of walls, slabs and roofs. The extraction stage targeted eight elements. Seven of them carried enough material and quantity information to proceed into the calculation; one incomplete roof aggregate was excluded, and, crucially, the reason for that exclusion was recorded rather than silently dropped. The retained set comprised four walls, one floor slab and two roof slabs, a small but complete envelope that allowed the researchers to keep the entire decision space within reach of exact evaluation.

That decision space was constructed from six wall materials, five floor materials and five roof materials, producing 150 whole-building configurations. Each configuration was scored on two axes: cradle-to-gate embodied carbon, measured in kilograms of carbon dioxide equivalent, and a prototype Building Circularity Score that reflects how readily materials can be recovered and reused. All 150 combinations were then compared pairwise to identify Pareto-optimal solutions, the mathematical term for configurations in which neither objective can be improved without degrading the other. This is where multi-objective optimisation earns its keep, because it replaces a single ranked list with a map of genuine trade-offs.

The result was strikingly structured. Twelve of the 150 configurations proved non-dominated, and they split cleanly into two camps. Six low-carbon-oriented candidates were dominated by timber-roof systems, while the six circularity-oriented candidates all used aluminium roofs. Not a single configuration met the study’s balanced classification thresholds, meaning no option satisfied both objectives simultaneously at the levels the researchers defined. The contrast illustrates a practical feature of material choice that designers rarely see laid bare: the design space may contain distinct clusters rather than one obvious best answer, and choosing between clusters is a values question, not a calculation.

The roof emerged as the decisive lever in this reference case, and the numbers explain why. The two roof slabs alone accounted for 53.5 percent of the extracted material volume, so whatever sat above the walls shaped the whole-building result. In one paired comparison, swapping a timber roof for an aluminium roof raised embodied carbon from 591.8 to 21,706.5 kilograms of carbon dioxide equivalent, a more than thirtyfold increase, while lifting the circularity score from 0.712 to 0.865. The authors are careful to frame this as a case-specific observation rather than a general rule for buildings, but it demonstrates the kind of quantified, element-level insight the workflow is designed to surface before specifications harden.

On top of the calculation engine sits a controlled semantic query layer with twelve predefined query types. These can retrieve low-carbon or high-circularity options, identify which components drive a building’s material profile, compare Pareto candidates side by side, or explain why a particular option earned its score. Because the queries operate through fixed rules rather than free-form interpretation, reproducibility is guaranteed: the same data and the same query yield the same answer every time. The system can also package its results into structured prompt text suitable for downstream interpretation, though the study explicitly did not call or evaluate a large language model, keeping the pipeline fully deterministic end to end.

Sensitivity testing forms a substantial part of the paper’s argument that the reference-case findings are robust rather than artefacts of arbitrary modelling choices. The same twelve candidate scenarios survived five different weighting schemes applied to the circularity score. The classification of zero balanced, six low-carbon-oriented and six circularity-oriented candidates held across nine different threshold settings. Under uncertainty assumptions tested with 1,000 scenario-based Monte Carlo runs, every baseline candidate remained non-dominated in at least 83.2 percent of the runs. For a field where early-stage carbon estimates often wobble with every assumption, that level of stability is a meaningful claim.

Performance numbers come with an honest caveat. The full 150-configuration case completed in about 0.79 seconds, including roughly 0.023 seconds for the pairwise Pareto filtering, fast enough for interactive design sessions. However, runtime tests with larger synthetic sets showed that exhaustive pairwise comparison does not scale indefinitely; as the number of configurations grows combinatorially, the filtering step becomes a bottleneck. The authors note that much larger design spaces would require more efficient Pareto-search strategies, a recognised challenge in multi-objective optimisation that algorithms such as sorting-based filters have begun to address elsewhere.

The team is candid that the work is a proof of concept built on one reference IFC model and a prototype material database. It does not yet account for structural performance, fire resistance, moisture behaviour, cost, procurement realities, regulation, operational energy, or product-specific verified Environmental Product Declarations, all of which shape real material decisions. Testing across multiple authoring platforms and live projects will be needed before field deployment can be judged. Even so, the study makes a persuasive case that open BIM data can serve as far more than a visual or documentation layer. By keeping quantities, materials, carbon calculations, circularity scores and candidate explanations connected in one deterministic process, the workflow offers a traceable foundation for exploring early-stage trade-offs, exactly the phase of a project where decisions are cheapest to change and most consequential for the built environment’s carbon and material future.

Subject of Research: An open IFC-based BIM workflow for whole-building embodied carbon and circularity assessment

Article Title: Open BIM workflow links whole-building carbon and circularity decisions

Article References: Open BIM workflow links whole-building carbon and circularity decisions. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: BIM, IFC, embodied carbon, circularity, multi-objective optimisation, Pareto optimality, building materials, life cycle assessment, smart construction, decision support, buildingSMART, Monte Carlo analysis