Disturbance capture and attribution through the integration of Landsat and IRS-1C imagery
Bibliographic record
Abstract
A primary activity required to support sustainable forest management is the detection and mitigation of forest disturbances. These disturbances can be planned, through urbanization and harvesting, or unplanned, through insect infestations or fire. Detection and characterization of disturbance types are important, as different disturbances have different ecological effects and may require unique managerial responses. As such, it is necessary for forest managers to have as complete and current information as possible to support decision making. In this study, we developed a framework to automatically detect and label disturbances derived from remotely sensed images. Disturbances were detected through traditional image differencing of medium-resolution imagery (Landsat-7 Enhanced Thematic Mapper Plus (ETM+), resampled to 30 m) but were refined and augmented through comparison with edge features extracted from high spatial resolution satellite imagery (Indian Remote Sensing (IRS) satellite 1C panchromatic imagery, resampled to 5 m). By incorporating spectral information, derived composite band values (tasselled cap transformations), spatial and contextual information, and secondary datasets, we were able to capture and label disturbance features with a high level of overall agreement (91%). Areal features, such as harvest areas, are captured and labelled more reliably than linear features such as roads, with 92% and 72% agreement when compared with control data, respectively. By incorporating rule-based disturbance attribution with remote sensing change detection, we envision the update of land cover databases with reduced human intervention, aiding more rapid data integration and opportunities for timely managerial responses.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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 teacher head, 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".