Aboveground Carbon Estimation in a Mangrove Ecosystem Using UAV-Based Remote Sensing and Machine Learning
Bibliographic record
Abstract
Mangroves are an important part of coastal blue carbon ecosystems, efficiently absorbing atmospheric carbon dioxide (CO 2 ). Accurate quantification of mangrove carbon stocks aids climate change mitigation and adaptation strategies. This study uses UAV-based remote sensing datasets to model Aboveground Carbon (AGC) in a juvenile mangrove ecosystem in Kenya, characterized by relatively open canopies. We developed an Ensemble regression model to estimate AGC, achieving a Mean Absolute Error (MAE) of 1.79 kg when validated against ground truth data. Instead of plot-level metrics, which lack detailed spatial information about individual trees or areas smaller than the mapping unit, our model was developed based on tree-level metrics, using data on hundreds of trees from fewer forest inventory plots. This methodology enabled the extraction of detailed spatial information on AGC at the tree level. We also explored the potential of two different UAV-based remote sensing data (LiDAR point cloud data vs point cloud data generated from high overlap images) for estimating mangrove AGC. Furthermore, a pixel-level comparison of difference values (“AGC LiDAR – AGC High overlap ”) was conducted to quantify and evaluate the estimated AGC differences (R 2 = 0.71, RMSE = 0.97 kg/m 2 ). The results suggest that both LiDAR data and superior high overlap images have the potential to accurately predict mangrove biomass/carbon stocks, although LiDAR outperforms high overlap images due to its involvement in unique intensity metrics. The tree-level-based modeling methodology presented in this work offers a different insight for biomass or carbon stock modeling.
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 | 0.000 | 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 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".