Hybrid wetland city map: Improved wetland characterization through the synergy of global land cover products
Bibliographic record
Abstract
Global wetlands are experiencing severe degradation due to climate change and human activities. Under the Ramsar Convention, the Wetland City Accreditation promotes cities to protect and sustainably manage their urban wetlands. The accreditation system was launched in 2015. To date, 43 cities worldwide have obtained this certification, whose dynamic assessment depends on precise mapping of land use and wetlands. Existing global land cover datasets often show low accuracy in identifying wetlands and limited capacity to characterize wetland types within urban areas. we developed a hybrid Wetland City Map (WCM), by fusing three global 10 m-resolution products: Dynamic World, ESA WorldCover, and ESRI Land Cover. We applied a Weighted Voting and Knowledge-based Decision Rule method to achieve this fusion. This method overcomes the limitations of the input datasets by combining their complementary strengths to improve overall wetland classification and by applying expert-derived rules to enhance the delineation of wetland types within cities. The WCM achieves an average overall accuracy of 86.93 % and a kappa of 0.825. In all cities, its accuracy surpasses the three land cover products by 2 %-26 %. The visual comparison shows WCM performs better in wetland classification and spatial detail, with F1 scores of 90.33 % (water), 64.09 % (marsh), 71.67 % (tidal flat/flooded flat), and 92.17 % (mangrove). It more accurately reflects wetland coverage and changes. Wetland coverage varies across cities, with higher coverage in Asia and lower in Europe and Africa. Individual cities experienced a maximum increase of 6.5 % and decrease of 1.3 % from 2020 to 2021.The WCM supports wetland monitoring, city accreditation, and research aligned with the Ramsar Strategic Plan and Sustainable Development Goals.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".