MétaCan
Menu
Back to cohort
Record W7042524756

Probabilistic and AI-based Methods for Moisture-safe and Sustainable Building Envelope Design

2025· article· en· W7042524756 on OpenAlexaboutno aff

Bibliographic record

VenueLund University Publications (Lund University) · 2025
Typearticle
Languageen
FieldEngineering
TopicHygrothermal properties of building materials
Canadian institutionsnot available
Fundersnot available
KeywordsProbabilistic logicContext (archaeology)PopulationWork (physics)Staring
DOInot available

Abstract

fetched live from OpenAlex

The increasing demand for energy-efficient and sustainable construction necessitates the need for building envelope designs that effectively balance moisture safety with sustainability. Improper moisture management in building envelopes can lead to severe consequences, including construction damage, decreased energy performance, and health risks associated with microbial growth. For instance, water infiltration in multi-family wood-frame buildings between 1993 and 2000 caused an estimated one billion Canadian dollars in damage. Similarly, in Belgium, water-tightness issues accounted for nearly half of all documented building damage cases between 2010 and 2015, with water penetration being the most prevalent issue. In Sweden, over 30% of single-family homes have been affected by mould and other moisture-related problems, with microbial growth impacting 60–80% of single-family houses with cold attics in the Gothenburg region.This thesis begins with a comprehensive state-of-the-art literature review of probabilistic hygrothermal analyses for building envelopes, through which critical research gaps are identified. In response to these gaps, the thesis introduces a set of probabilistic methodologies that integrate machine learning algorithms and decision analysis frameworks to optimise the design of moisture-safe and sustainable building envelopes. Three novel methodologies are proposed: Mould Reliability Analysis (MRA), Mould Sensitivity Analysis (MSA), and Inutility Decision Analysis (IDA). MRA leverages a probabilistic approach to address uncertainties in hygrothermal performance, employing a machine learning metamodel (based on random forests algorithm) to predict mould indices efficiently. MSA combines linear and non-linear sensitivity analyses to identify important variables affecting moisture-related damage. IDA expands traditional decision-making frameworks by incorporating sustainability metrics, such as life cycle costing (LCC) and life cycle assessment (LCA), alongside hygrothermal performance.The results from case studies demonstrate the effectiveness of these methodologies. Probabilistic analyses exposed the limitations of deterministic approaches, which often underestimate moisture-related risks. The integration of machine learning significantly reduced computational time, enabling the evaluation of millions of scenarios with high precision. Sensitivity analyses pinpointed influential variables and highlighted variations in their importance under different conditions. IDA findings revealed that designs with no probability of mould growth might not always be optimal if their initial environmental and economic impacts are high. In certain cases, designs with manageable mould growth risks, lower initial costs, and environmental impacts were found to be more advantageous over the building’s lifespan.This research demonstrates the potential of integrating AI-based probabilistic moisture safety design with sustainability to develop robustness and environmentally responsible building envelopes. The proposed methodologies provide practitioners with advanced framework to address uncertainties, enhance design robustness, and incorporate multi-criteria decision-making into construction projects. Future research opportunities include expanding the framework to encompass energy performance and health consequences, further enhancing its utility and impact in the construction industry.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.006
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.005
Threshold uncertainty score0.016

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.006
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0020.002
Science and technology studies0.0010.001
Scholarly communication0.0020.001
Open science0.0020.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0050.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.016
GPT teacher head0.243
Teacher spread0.227 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueLund University Publications (Lund University)Same topicHygrothermal properties of building materialsFrench-language works237,207