Automated analysis of aerial photographs and potential for historic forest mapping
Bibliographic record
Abstract
Historic information regarding forest status is essential to management and conservation. Manual interpretation of aerial photography has long been the standard for forest inventory; however, manual interpretation can be subjective, inconsistent, and labor-intensive. This research compares automated techniques with manual interpretation results. First, we used an automated process (called segmentation) to delineate homogeneous stands of forests (or objects), analogous to the goal of manually delineating of polygons. Second, we used classification and regression tree (CART) analysis to classify polygons into the forest and terrain schemes used in British Columbia. Most characteristics of objects created via segmentation were similar to manually delineated polygons, as >70% of attributes were statistically similar across local, polygon, and landscape-level comparisons. Using manual interpretations for comparative reference, automated classifications produced overall accuracies ranging from 62% to 86% with per-class accuracies ranging from 0% to 96%. Automated methods yielded classifications meeting provincial overlap accuracy targets and helped identify classifications most suited to automation. Automated procedures have potential for aiding swift utilization of extensive historical photography archives with several caveats for future consideration. While automated techniques may never replicate all aspects of forest inventory classification, automated techniques may be valuable in assisting different phases of the process.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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".