Monitoring seedling stands using national forest inventory and multispectral airborne laser scanning data
Bibliographic record
Abstract
Characterizing seedling stands with respect to their species proportions and co-occurring vegetation is important for monitoring the desired development of the forest stand. Related inventory information has traditionally been collected with costly field surveys and National Forest Inventory (NFI)-based models. Here, we present a novel fusion approach to combine remote sensing (RS)-based models and NFI-based models to predict seedling stand characteristics, i.e., height, density, and tending needs. We used the best linear unbiased predictor for the fusion of the NFI- and RS-based models. The NFI-based models were derived using NFI sample plots and stand features. The RS-based models were derived using airborne laser scanning and color–infrared images and separate field-measured data. NFI-based models were found to be rather unreliable (RMSE = 65%–115% for stem density and 59%–78% for height), but they were always available without the need for any additional RS data. RS-based models provided an RMSE of 41%–92% for stem density and 26%–45% for height. The fusion procedure used at the prediction stage consistently increased the accuracy of all variables of interest, but the improvements were minor. In addition, we classified the tending need in seedling stands if the height of the coniferous tree was less than 1 m compared to broadleaved trees. If we simulate the decision-making situation of tending needs, we can predict tending needs (91% user accuracy) fairly well for a stand.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| 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".