GA Driven feature selection in object-based classification for forest mapping with IKONOS imagery in Flanders, Belgium
Bibliographic record
Abstract
Land cover map development was done on the base of the Landsat 7 ETM+ images.As a background topographical map of the scale 1:100 000 was used.Satellite image interpretation was done automatically using coefficients of spectral brightness for image and etalon (standard) types of landscape surfaces and the rule of minimum distance.Total number of 14 types of lands for Sankt-Petersburg greenbelt area was identified: broadleaf forest, mix forest, Scots pine dominated forest, Norway spruce dominate forest, clear cuttings, bushes and low dense forest, meadows and hay fields, agricultural lands, open areas (badlands), dacha settlements and villages, cities areas (including roads), areas densely covered by houses, bogs, waters.The results of satellite image interpretation were checked by comparison with ground truth data on 37 sample plots, statistical reliability of classification appears to be equal 85%.As a result of satellite image interpretation the digital land cover map for the Sankt-Petersburg green belt area of the scale 1:100 000 was developed.Each of the 14 types of the land was represented as a separate layer in ArcView3.2GIS in the format SHP (ArcView3.2Shape file).It appears that all kind of the forests cover 56.0% of the total green belt area with serious prevailing of Scots pine dominated forests -31.1%, agricultural lands -22.0%, all kind of populated areas -18.6%, bogs and waters -2.9%.This data and spatial patterns of each type of land distribution were compared with the data and maps obtained from other sources by means of GIS technique.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| 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".