MétaCan
Menu
Back to cohort
Record W4417000517 · doi:10.1016/j.clema.2025.100364

AI-based meta model for predicting the performance of low-carbon concrete, considering the effects of multiple waste materials

2025· article· en· W4417000517 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueCleaner Materials · 2025
Typearticle
Languageen
FieldEngineering
TopicConcrete and Cement Materials Research
Canadian institutionsLakehead University
FundersOntario Ministry of Natural Resources and Forestry
KeywordsComponent (thermodynamics)Work (physics)Meta-analysisKey (lock)Production (economics)

Abstract

fetched live from OpenAlex

Low-carbon concrete incorporating waste materials offers significant environmental benefits while maintaining structural performance. However, designing an optimal mix of these waste materials is challenging due to their potential impact on the concrete properties. To address this challenge, this paper presents a novel meta model that introduces a non-deterministic mix design framework and simultaneously optimizes four performance metrics: environmental (global warming potential), durability (rapid chloride permeability and bulk electrical resistivity), mechanical (compressive strength and splitting tensile strength), and workability (air content and slump). The model is trained using a hybrid dataset combining literature data with response surface methodology (RSM) generated samples. To this end, a Multilayer Perceptron (MLP) neural network is trained to capture the effects of waste materials, including shredded rubber (SR), glass powder (GP), and biomass fly ash (BFA), on concrete performance and is further combined with Monte Carlo simulation to identify optimal mix designs based on specific performance targets. The results demonstrate the AI model’s accuracy in predicting concrete performance, as evidenced by statistical measures such as root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R 2 ). This accuracy is further validated by comparing the AI predictions with laboratory concrete mix results. The results indicated that a 23.1% increase in compressive strength and an 83% decrease in chloride ion permeability were achieved by partially substituting 30% GP for cement. The incorporation of 15% BFA consistently reduced slump by 65% and increased air content by 49%. Moreover, the control mix had the highest GWP at 325 kg CO 2 -eq/m 3 . Using 30% GP, 15% BFA, and 15% SR reduced it to 135 kg CO 2 -eq/m 3 , a 41% decrease. Additionally, the back analysis provides optimized mix designs tailored to specific performance constraints. According to the specified target for designing low-carbon, chloride-resistant, and normal strength (45–55 MPa) concrete, a mixture of waste materials with SR = 3.2%, GP = 25.8%, and BFA = 7.4% is proposed by the developed meta model.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.179
Threshold uncertainty score0.590

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.017
GPT teacher head0.244
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