Upscaling UAV and Lidar-derived forest gap area and edge length extractions using radar and optical sentinel images
Bibliographic record
Abstract
UAV and LiDAR data are valuable for mapping forest gaps in small areas but face cost and accessibility challenges for larger regions. This study explored using UAV and LiDAR data to create reference information on forest gaps and edge lengths for upscaling (that is providing information on forest across wider spatial extents) with satellite data. We examined forest gap mapping across four global sites: Daland Forest Park (Iran), Hardtwald Forest (Germany), Petawawa Research Forest (Canada), and Luxembourg Forest (Luxembourg). High-quality UAV and ALS LiDAR data were used to extract and map forest gaps by creating Canopy Height Models (CHM) and applying height thresholds. SAR Sentinel-1 and optical Sentinel-2 images were then employed to upscale the results using the Random Forest (RF) regression model. Gap area and edge length were calculated within grid cells using varied grid sizes to determine the optimal spatial grain for upscaling. The study also evaluated the impact of sampling strategies and feature selection on model performance. Results showed that grids with dimensions of 20 × 20 meters showed the best results for estimating gap areas. The UAV- and LiDAR-derived gap area could be upscaled with satellite data with R2 values of 0.587, 0.711, 0.843, and 0.835 for the DFP, HF, PRF, and LF regions, respectively (all RMSE (scaled between 0 and 1) were smaller than 0.108). For edge length we obtained good model performances as well with R2 of 0.840, 0.690, 0.712, and 0.612, respectively for DFP, HF, PRF, and LF regions (all RMSE were smaller than 0.137). Feature selection and balancing dependent samples improved the upscaling results. The study demonstrates the potential of using Sentinel data to upscale canopy gap information from UAV and LiDAR data in areas with limited high-quality data, providing valuable insights for forest managers and ecologists in temperate forests.
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 | 0.000 | 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 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".