Machine-learning unravels spatial shifting in homogeneous rainfall subregions in Central Africa under global warming
Bibliographic record
Abstract
Abstract Modifications in precipitation regimes significantly affect various socio-economic sectors, including agriculture and water resource management. Although the rainfall regimes characterizing Central Africa (CA) have just recently been described, it is equally urgent to investigate potential changes in their spatial extent under different global warming pathways, which motivates the present study. For this purpose, we utilized results from the dynamical downscaling performed by regional climate models (RCMs) under the CORDEX-CORE (Coordinated Regional Climate Downscaling Experiment–Coordinated Output for Regional Evaluations) initiative. The warming pathways are based on low (RCP2.6) and high (RCP8.5) emission scenarios. The K-means clustering technique is employed to classify areas with homogeneous rainfall regimes. Our findings indicate that the ability of experiments to mimic the spatial patterns of these subregions is model-dependent. REMO and CCLM5 RCMs outperform RegCM4, achieving the highest Adjusted Rand (AR) index values compared to the observational datasets CHIRPS2 and TAMSAT3.1. Projections based on individual experiments and the multimodel ensemble-mean suggest that the warming level will influence clusters’ spatial extent. Broadly, the ensemble mean shows that an expansion of Equatorial CA is projected (4.8% and 9.7%, respectively), while a contraction of Southern CA is anticipated (4.2% and 4.5%, respectively), consistently under both scenarios. In contrast, the signal of change in Northern CA differs between the two warming pathways. Under the highly mitigated RCP2.6 scenario, an expansion of the cluster is projected (1%), whereas the low-mitigation RCP8.5 scenario projects a shrinking of its spatial extent (0.8%).
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".