Monitoring Mangrove Recovery in the Bay of Assassins, Madagascar
Bibliographic record
Abstract
Mangroves are unique plant species that support livelihoods and provide critical ecosystem services. Globally, mangroves have faced significant threats from deforestation, causing rapid decline; however, recent restoration efforts have made a positive impact. Effective restoration requires regular monitoring and evaluation to ensure its long-term success. This study aims to support mangrove restoration efforts in the Bay of Assassins, Madagascar by evaluating the utility of remote sensing technologies for short-term monitoring. Since 2015, restoration efforts in the area have achieved notable success making continued monitoring essential for sustainability. Blue Ventures’ Google Earth Mangrove Mapping Methodology (GEM), a cloud computing tool hosted on Google Earth Engine, along with Sentinel-2 satellite imagery, were leveraged to examine mangroves from 2019 to 2024. The objective was to assess and quantify mangrove growth and health dynamics, identifying trends in gain and loss over the five-year period. Previous GEM applications exclusively used Landsat imagery with each pixel representing 30 by 30 meters of ground area. This study aimed to build on this work by using the higher level of detail provided by Sentinel-2’s 10-meter resolution. The findings demonstrate that Sentinel-2 imagery, and GEM effectively captured changes in mangrove extent and health, revealing a net increase in total mangrove cover from 2019 to 2024. Mangrove health assessments using spectral indices indicated that many restored areas improved in health, while some exhibited stagnation or decline, suggesting the need for further investigation into site-specific conditions. With an average accuracy of 96% across all mangrove maps, this study successfully demonstrated the utility of the GEM tool in performing high-resolution analysis and assessing mangrove growth
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 | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| 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".