Detection of Annual Spruce Budworm Defoliation and Severity Classification Using Landsat Imagery
Bibliographic record
Abstract
Spruce budworm (SBW) is the most destructive forest pest in eastern forests of North America. Mapping annual current-year SBW defoliation is challenging because of the large landscape scale of infestations, high temporal/spatial variability, and the short period of time when detection is possible. We used Landsat-5 and Landsat-MSS data to develop a method to detect and map SBW defoliation, which can be used as ancillary or alternative information for aerial sketch maps (ASMs). Results indicated that Landsat-5 data were capable of detecting and classifying SBW defoliation into three levels comparable to ASMs. For SBW defoliation classification, a combination of three vegetation indices, including normalized difference moisture index (NDMI), enhanced vegetation index (EVI), and normalized difference vegetation index (NDVI), were found to provide the highest accuracy (non-defoliated: 77%, light defoliation: 60%, moderate defoliation: 52%, and severe defoliation: 77%) compared to using only NDMI (non-defoliated: 76%, light defoliation: 40%, moderate defoliation: 43%, and severe defoliation: 67%). Detection of historical SBW defoliation was possible using Landsat-MSS NDVI data, and the produced maps were used to complement coarse-resolution aerial sketch maps of the past outbreak. The method developed for Landsat-5 data can be used for current SBW outbreak mapping in North America using Landsat-8 and Sentinel-2 imagery. Overall, the work highlights the potential of moderate resolution optical remote sensing data to detect and classify fine-scale patterns in tree defoliation.
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 | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".