MétaCan
Menu
Back to cohort
Record W6950212827 · doi:10.5683/sp3/unztih

Comparison Between Sentinel-2 and Landsat in Mapping Mangroves in The Gambia Using the Google Earth Engine Mangrove Mapping Methodology (GEM v2)

2025· dataset· en· W6950212827 on OpenAlexaff

Bibliographic record

VenueBorealis · 2025
Typedataset
Languageen
Field
Topic
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsMangroveLand coverEarth observationMangrove ecosystemSatelliteSatellite imagery

Abstract

fetched live from OpenAlex

Mangroves play a vital role in coastal environments by supporting biodiversity, protecting shorelines, and storing carbon. However, these ecosystems are under growing pressure from land use change, development, and rising sea levels. Monitoring changes in mangrove cover is essential for guiding conservation and management efforts, but on the ground, methods are often time-consuming, expensive, and difficult to carry out across large or remote areas. This is where remote sensing offers a practical solution. By using satellite imagery, it becomes possible to track changes in mangrove extent over time, detect patterns of loss and regrowth, and support decision-making at both local and national levels. This study compared the effectiveness of Sentinel-2 and Landsat satellite data in mapping mangrove dynamics in The Gambia, using the Google Earth Engine Mangrove Mapping Methodology version 2 (GEM v2) from Blue Venture, a marine and conservation organization. A Random Forest classifier was applied to classify land cover types, and the accuracy of each dataset was evaluated. Sentinel-2 was better at detecting small, detailed changes, including narrow strips of loss and early signs of regrowth. Landsat, while less detailed, provided more stable classifications across broader areas. Sentinel-2 also showed greater variation in spectral data, which led to more classification errors in some mangrove classes, while Landsat maintained higher overall accuracy. The results show that both datasets have strengths, Sentinel-2 is well-suited for close-up monitoring of small-scale changes, while Landsat is reliable for long-term, large-scale analysis. A combined approach using both sensors may offer the complete overview of mangrove change. Future studies should consider using field data from the same area to improve classification accuracy and support more effective monitoring and protection of mangrove ecosystems.

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 imitation

Not 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.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Dataset · Consensus signal: none
Teacher disagreement score0.046
Threshold uncertainty score0.092

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.148
GPT teacher head0.375
Teacher spread0.228 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreDataset

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueBorealisFrench-language works237,207