Using near-infrared hyperspectral images on subalpine fir board. Part 2: Density and basic specific gravity estimation
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
Wood density (ρMC) and basic specific gravity (BSG) are important properties in several forest products manufacturing processes. In this study, near-infrared hyperspectral images were tested to produce two-dimensional (2D) ρMC and BSG images of subalpine fir (Abies lasiocarpa Hook) board. A total of 107 cubic samples with the size of 4 cm were prepared from 14 boards. All samples were dried to various moisture contents (MCs) during several steps until being completely dried. The resulting MCs ranged from 1% to 137% (dry basis). After the last drying step, the samples were soaked in water to determine BSG. Hyperspectral images and weight measurements were acquired over each sample at each drying step. ρMC was also estimated at each MC level. Partial least squares (PLS) models were developed for estimating both ρMC and BSG from the near-infrared hyperspectral imaging (NIR-HSI) system absorbance spectra acquired over all the samples during each drying step. The ρMC model provides a reasonable accuracy with the validation data-set (R2 = 0.81, RMSE = 39 kg/m3, and RPD = 2.3). For BSG, only models built with samples having MC of less than 12% are significant. The calibration data-set provides similar accuracy as the ρMC model (RMSE = 0.004, R2 = 0.82, and RPD = 2.28), but the accuracy is lower with the validation data-set (RMSE = 0.007, R2 = 0.53, and RPD = 1.39). Our data-set has BSG values varying only from 0.326 to 0.374, and further work is needed to apply these methods to a data-set that includes a more extended range of BSG variations for improving estimation accuracy.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 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) | 0.000 | 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