Colour in thermally modified wood of beech, Norway spruce and Scots pine. Part 2: Property predictions from colour changes
Bibliographic record
Abstract
Abstract In the woodworking industry, image analysis is routinely used for quality control and for matching and classification during various processes. An extension of these automated systems for the prediction of physical properties of thermally modified wood (TMW) is enticing, because to date there is no generalised procedure for the quality assurance of TMW. In this work, the feasibility of predicting 13 physical parameters from the analysis of colour changes is demonstrated using small thermally modified specimens of three wood species. Simple linear regression models for anti-swelling efficiency, nominal density, heat-induced weight loss and 10 strength parameters in six forms of stress were all very or highly significant, with R2 statistics for the best predictor from 0.24 to 0.94. ΔE* was found to be a better predictor than ΔL* for most properties. Multiple linear regression with 11 colour variables increased the prediction ability of most models in terms of R2, although these improvements varied with the property and species concerned. The best models altogether were obtained by partial least squares regression, with relative prediction error values >0 in all cases. Our results demonstrate that physical properties of small specimens of TMW can be efficiently predicted with only one after treatment measurement of colour in the CIEL*a*b* colour space by means of image analysis of TMW surfaces. We anticipate that our approach would be a starting point for more refined modelling of physical properties of larger wood members and other properties of interest in TMW (e.g., decay resistance).
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".