Mapping potential wetlands by a new framework method using random forest algorithm and big Earth data: A case study in China's Yangtze River Basin
Bibliographic record
Abstract
Mapping potential wetlands provides a promising approach to get such information rapidly, and thus is of great significance to understanding ecosystem sustainability and support wetland conservation and restoration. This study proposed a new processing pipeline to map potential wetlands in the Yangtze River Basin, the largest basin in China, by combining a random forest (RF) algorithm and an indicator system constituted by several indicators, including vegetation, soil, terrain, and climatic features. Results reveal that slope, annual precipitation (APRE), digital elevation model (DEM), normalized difference vegetation index (NDVI), and annual mean temperature (AMT) are the most important variables affecting the distribution of potential wetlands, with a relative importance value of 7.5 %, 5.9 %, 5.5 %, 5.2 %, and 5.2 %, respectively. Mapping potential wetlands in the Yangtze River Basin was achieved using the RF model with overall accuracy of 79.31 % and Kappa coefficient of 0.58. The estimated total area of potential wetlands in this basin is approximately 39,677 km2, mainly distributed in the Yalong River watershed, the Dongting Lake watershed, and the regions bordering main streams of the Yangtze River. The proposed approach in this study evidenced its generalizability in terms of the good accuracy and distribution consistency with the natural wetlands observed from satellites and field investigation. We expect that this approach can be further used to generate potential wetland datasets at a broader scale in a long time series and benefit the evaluation of Sustainable Development Goals (SDGs).
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".