Image segmentation and classification of Landsat Thematic Mapper data using a sampling approach for forest cover assessmentThis article is one of a selection of papers from Extending Forest Inventory and Monitoring over Space and Time.
Bibliographic record
Abstract
Remote sensing surveys for estimating forest cover may be divided into two approaches: wall-to-wall and sampling. Sampling approaches offer a practical alternative to wall-to-wall mapping, but estimates of forest cover may be affected by the sampling rate of the estimation area. This study aimed to obtain stable estimates of forest cover from satellite data using object-oriented classification at the national level. We investigated a suitable value for the scale parameter in object-oriented classification using eCognition software to identify land cover types, and we evaluated the sampling rate for estimating forest cover at the national level. We used eight different scale parameters when applying object-oriented classification to Landsat data for a set of forty-six 10 km × 10 km sampling tiles centered at each degree of latitude and longitude in Japan. The scale parameter of 10 or less was found suitable for obtaining objects with areas of about 5 ha. Overall accuracy in classification was greater than 75% and greatest when the scale parameter was between 6 and 10. We then analyzed the entire land area of Japan using 10 km × 10 km tiles to evaluate the optimum sampling rate for estimating forest cover. A sampling rate greater than 20% was required to stably estimate forest cover in Japan.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".