An improved global land cover mapping in 2015 with 30 m resolution (GLC-2015) based on a multisource product-fusion approach
Bibliographic record
Abstract
Abstract. Global land cover (GLC) information with fine spatial resolution is a fundamental data input for studies on biogeochemical cycles of the Earth system and global climate change. Although there are several public GLC products with 30 m resolution, considerable inconsistencies were found among them, especially in fragmented regions and transition zones, which brings great uncertainties to various application tasks. In this paper, we developed an improved global land cover map in 2015 with 30 m resolution (GLC-2015) by fusing multiple existing land cover (LC) products based on the Dempster–Shafer theory of evidence (DSET). Firstly, we used more than 160 000 global point-based samples to locally evaluate the reliability of the input products for each land cover class within each 4∘ × 4∘ geographical grid for the establishment of the basic probability assignment (BPA) function. Then, Dempster's rule of combination was used for each 30 m pixel to derive the combined probability mass of each possible land cover class from all the candidate maps. Finally, each pixel was determined with a land cover class based on a decision rule. Through this fusing process, each pixel is expected to be assigned the land cover class that contributes to achieving a higher accuracy. We assessed our product separately with 34 711 global point-based samples and 201 global patch-based samples. Results show that the GLC-2015 map achieved the highest mapping performance globally, continentally, and ecoregionally compared with the existing 30 m GLC maps, with an overall accuracy of 79.5 % (83.6 %) and a kappa coefficient of 0.757 (0.566) against the point-based (patch-based) validation samples. Additionally, we found that the GLC-2015 map showed substantial outperformance in the areas of inconsistency, with an accuracy improvement of 19.3 %–28.0 % in areas of moderate inconsistency and 27.5 %–29.7 % in areas of high inconsistency. Hopefully, this improved GLC-2015 product can be applied to reduce uncertainties in the research on global environmental changes, ecosystem service assessments, and hazard damage evaluations. The GLC-2015 map developed in this study is available at https://doi.org/10.6084/m9.figshare.22358143.v2 (Li et al., 2023).
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".