GEDI waveform metrics in vegetation mapping—a case study from a heterogeneous tropical forest landscape
Bibliographic record
Abstract
Abstract The distribution of different vegetation types is important information for landscape management, especially in the context of tackling global environmental change. Vegetation types can be mapped using satellite and airborne passive remote sensing. However, spectrally similar yet structurally different vegetation types, like different tree-dominated land covers, are often challenging to map using spectral information alone. We examined the potential of vertical vegetation structure acquired in the global ecosystem dynamics investigation (GEDI) mission that harnesses a space-borne waveform lidar sensor in vegetation mapping across a heterogeneous tropical landscape in Cambodia. We extracted 121 waveform metrics from Level-1B and Level-2A data products at 1062 locations across five key vegetation types. After reducing the relative height variables’ dimensionality through simple linear regressions, we developed a Random Forest classifier to predict vegetation classes based on 23 GEDI metrics. We then used this model to classify the vegetation types across more than 77 000 GEDI footprints in the study area. GEDI metrics alone were useful in identifying vegetation types with 81% accuracy. Cropland/grassland class had the highest prediction accuracy (user’s accuracy [UA] = 89%; producer’s accuracy [PA] = 91%), while dry deciduous forest had the lowest accuracy (UA = 73%; PA = 69%). By comparing the GEDI-only classification with an optical-radar map, we found that structural and topographic information from GEDI Level-1B and Level-2A can complement the spectral information in assessing natural habitats that neighbor other vegetation types in a heterogeneous landscape. The highest classification accuracy at the footprint scale was obtained from the combination of GEDI, Sentinel-1, and Sentinel-2 (88.3%). We also demonstrated how wall-to-wall vegetation mapping is possible by combining the three data sources. These findings expand the potential use of GEDI waveform lidar data in supporting the development of policy-relevant maps that depict the distribution of forests together with other vegetation types.
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 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.003 |
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".