A new framework for mapping rubber plantations through the combination of semiautomatic sample migration, dynamic phenology, and change detection variables based on time series Landsat images
Bibliographic record
Abstract
Reliable mapping of rubber plantations is essential for yield estimation and sustainable land management, yet existing methods struggle with the lack of historical samples and the underuse of dynamic phenological information. We propose a novel time-series mapping framework that overcomes these limitations through three methodological innovations: (1) propose a semiautomatic sample migration algorithm to generate reliable historical samples, (2) develop dynamic phenology indices to capture seasonal growth patterns, and (3) change detection variables were utilized to capture the temporal characteristics of the rubber plantation time series. The variable importance analysis revealed that elevation was consistently highly ranked in rubber plantations classification. Dynamic phenology indices were also crucial, especially those based on the month of major leaf fall. The change detection variables, particularly the NDFI, ranked highly across all years. Overall, the highest classification accuracy for rubber plantations was achieved by using all six variable types: spectral bands, composite indices, terrain, textures, change detection, and dynamic phenology indices. When applied at an experimental site in China, the framework achieved over 97% accuracy for historically migrated samples and the rubber plantations mapping accuracy (RPMA) of 93.68% between 2003 and 2022. Transfer tests in Myanmar and Thailand confirmed its robustness, with RPMA of 94.34% and 93.73%, respectively. The maps showed high spatial consistency with Google Earth imagery, clearly distinguishing rubber plantations from other vegetation. By integrating sample migration with dynamic spatiotemporal features, this framework provides a transferable and scalable solution for long-term rubber plantation monitoring. This highlights the critical role of phenology and change detection in improving classification accuracy, offering new opportunities for regional-scale plantation mapping in Southeast Asia.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".