Identification and Classification of Complex Agricultural Croplands Using Multi-Temporal ALOS-2/PALSAR-2 Data: A Case Study in Central Java, Indonesia
Bibliographic record
Abstract
The agriculture sector makes a significant contribution to the Indonesian economy and has become one of the sources of national income. Therefore, precise agricultural mapping is very important to national and regional administrations. Satellite remote sensing provides the most effective tool for identifying a wide expanse of agriculture croplands. However, cloud coverage in tropical regions limits the use of optical remote sensing. SAR is an active remote sensing technique, which offers completely cloud-free observation data. The multi-temporal ALOS-2/PALSAR-2 data were used in this study, complemented by optical multi-temporal remote sensing data, that is, Landsat 8 OLI for classifying complex agricultural croplands. The study area, located in the Klaten Regency, Central Java Province, with 112 km2 coverage, was selected because of its dynamic cropping pattern and complex agricultural land use types. In this study, the RGB composite of HH, HV and HV-HH, derived from ALOS-2/PALSAR-2 polarizations, was found to be effective at separating two types of paddy field cropping pattern: all-year paddy (paddy-I) and paddy upland fields (paddy-II). The multi-temporal Landsat 8 data were also found to be useful for observing the cropping pattern. Moreover, the classification accuracy, which was as high as 85.02% in terms of overall accuracy, with a kappa coefficient of 0.824, from multi-temporal ALOS-2/PALSAR-2 data, was obtained. These results show that multi-temporal ALOS-2/PALSAR-2 data are capable of discriminating between two different paddy field cropping types, as well as beneficial for discriminating between the cropping stage and cropping pattern information for several other land uses.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".