Exploring Sustainable Solutions: Parametric Analysis and Machine Learning for Finger-Jointed Casuarina Glauca Beams
Bibliographic record
Abstract
The construction industry is responsible for approximately 39% of global carbon dioxide emissions, driven by the energyintensive production of materials like cement and steel, as well as resource-depleting practices that contribute to deforestation, biodiversity loss, and pollution.To mitigate this environmental impact, the adoption of sustainable construction materials is critical.Casuarina Glauca, a hardwood species, emerges as a promising alternative due to its eco-friendly nature, high mechanical strength, and availability in regions with arid climates.However, its short timber lengths (0.8-1.2 m) limit its direct application in structural framing.This study explores the use of adhesive-reliant finger joints to address this limitation, enabling the creation of longer beams while retaining environmental benefits.A parametric analysis using finite element modelling in Abaqus was conducted to optimize joint configuration, amplitude, finger density, and adhesive type.Results show that increasing finger count (up to 16 per 10 cm) and amplitude (up to 50 mm) significantly enhances bending capacity, with Epoxy-bonded joints achieving up to 95% capacity, outperforming PVAbased alternatives.Additionally, a machine learning framework was developed to predict beam performance, leveraging models such as XGBoost, which achieved an R² of 0.9263 and RMSE of 0.0329.This predictive approach enables efficient design optimization, minimizing resource consumption and reducing testing costs.By combining numerical modelling and machine learning, this research addresses the limitations of Casuarina Glauca, promoting its use as a sustainable, high-performance material in construction.These findings pave the way for reducing construction-related emissions and costs while advancing eco-friendly engineering solutions.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".