Predictive modeling of particleboard properties derived from agricultural waste biomass using machine learning algorithms
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.
Bibliographic record
Abstract
Important advances in ethical resource use, self-determination, and equitable access to sustainable building materials have long been recognized as strategies for achieving affordable housing. This research systematically evaluates the physical and mechanical properties of particleboards manufactured from diverse agricultural wastes. This study also investigates the prediction of their thickness swelling (TS) based on the water absorption (WA) and their modulus of rupture (MOR) and internal bond (IB) based on the modulus of elasticity (MOE) using machine learning (ML) algorithms. Notably, particleboards made with macadamia nutshell and castor oil achieved TS values of 2.7%, meeting the ANSI/A208.1-1999 general-purpose board standard, while macadamia nutshell and gum Arabic panels can be used as P1 and P2 panels in accordance with BS EN 312. Pearson correlation analysis illustrated a strong positive relationship between WA and TS (r = 0.7162) and a significant negative correlation between density and WA (r = -0.7744), highlighting the importance of high-density formulations for moisture resistance. Mechanical properties were also strongly interrelated, with MOR-MOE (r = 0.8633) and MOR-IB (r = 0.8063) correlations indicating that strength enhancements often occur simultaneously. The predictive modeling demonstrated that decision tree (DT) models achieve the best performance compared to random forest (RF) models, with r², MAE, and RMSE values of 0.9910, 0.6889, and 1.1355 for TS, 0.8731, 0.2973, and 0.3905 for IB, and 0.9433, 1.1417, and 1.9834 for MOR prediction, respectively. Furthermore, DT models established threshold prediction, including WA ≤ 60.95% for TS equal to 16.28% and MOE ≤ 2318.0 MPa for MOR and IB exhibiting 10.86 MPa and 0.65 MPa, respectively. However, k-fold cross-validation results indicate low performance for DT models' generalization compared to training models due to outliers in the dataset. The present study recommends expanding datasets to include more agricultural residues in panel production, integrating cost and environmental impact metrics, and applying advanced ML algorithms for greater predictive accuracy and holistic sustainability assessment in future research for affordable housing.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it