Evaluation of alternative methods for using LiDAR to predict aboveground biomass in mixed species and structurally complex forests in northeastern North America
Bibliographic record
Abstract
Light detection and ranging (LiDAR) has become a common means for predicting key forest structural attributes, but comparisons of alternative statistical methods and the spatial extent of LiDAR metrics extraction on independent datasets have been minimal. The primary objective of this study was to assess the performance of local and non-local LiDAR aboveground biomass (AGB) prediction models at two locations in the Acadian Forest. Two common statistical techniques, nonlinear mixed effects (NLME) and random forest (RF), were used to fit the prediction models and compared. Finally, this study evaluated the influence of alternative plot radii for LiDAR metrics extraction on model fit and prediction accuracy. AGB models were independently developed at each forest and tested both locally (model applied to same forest used for development) and non-locally (model applied to different forest) using an extensive network of ground-based plots. In general, RF was found to outperform NLME when applied locally, but the differences between the approaches were negligible when applied to the non-local dataset. NLME was found to perform equally well locally and non-locally. LiDAR extraction radius had very little influence on model performance as well. Minimal differences between models developed using fixed- and variable-radius methods were found, while the optimal LiDAR extraction radius was not consistent among forests, statistical technique, or local vs. non-local. Overall, the results highlight the importance of a robust calibration dataset that covers the full range of observed variation for developing accurate prediction models based on remote sensing data.
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 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 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".