Remote Sensing of Forest Composition and Diversity: Assessing Spectral Predictors and Long-Term Changes in Quebec’s Forests
Bibliographic record
Abstract
Forest biodiversity and composition are shifting in response to anthropogenic pressures, natural disturbances, and climate change, especially in regions like Quebec where many broadleaf and conifer species coexist. This thesis investigates how remote sensing can support large scale forest monitoring through two research components. The first evaluates the relationship between satellite derived spectral diversity and ground measured tree diversity metrics across Quebec’s deciduous, mixed, and boreal forests. Using Sentinel-2 imagery and forest inventory plots, we tested the Spectral Variation Hypothesis (SVH) through spectral analysis, clustering, and machine learning. While models poorly predicted species richness, Shannon diversity, and functional dispersion (r2 < 0.46 for all), they performed well for percent conifer (r2 = 0.77), suggesting that structural traits are more detectable via optical sensors than taxonomic diversity. The second component tracks changes in conifer composition (through conifer basal area percentage index) across three decades from 1985 to 2021 using forest inventory plots and Cubist regression models trained on Landsat imagery. Ground data showed widespread increases in conifer basal area, particularly in mixed forests largely driven by balsam fir (Abies balsamea). Cubist models generated spatially continuous maps of conifer basal area percentage and captured general trends, though their change detection accuracy at the plot scale was moderate. Together, these studies demonstrate both the strengths and limitations of remote sensing for biodiversity assessment and forest composition monitoring and emphasize the value of focusing on structural characteristics when interpreting spectral signals.
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 | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 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".