Unsupervised land cover classification in Ontario using multi-sensor satellite imagery
Bibliographic record
Abstract
High-resolution land cover classification is essential for environmental monitoring and resource management. This thesis presents a fully unsupervised framework for land cover classification in Ontario, Canada, using fused Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 optical imagery at 10-meter resolution. A cloud-native export pipeline in Google Earth Engine produces seasonally consistent, cloud-free, and snow-free composites. A comprehensive feature engineering process extracts spectral indices, SAR backscatter metrics, terrain attributes from digital elevation models (DEMs), and temporal statistics to form a rich multi-sensor feature space. Dimensionality reduction via Sparse Principal Component Analysis (SparsePCA) and mutual information–based feature selection is applied to improve class separability. Three clustering algorithms—K-means (centroid-based), HDBSCAN (densitybased), and OPTICS (reachability-based)—are employed to capture diverse structural patterns in the data. The final land cover labels are determined via a majority-voting ensemble strategy, with OPTICS acting as a deterministic tie-breaker. Classification outputs are evaluated against the Dynamic World dataset using overall accuracy (OA), precision, recall, F1-score, Adjusted Rand Index (ARI), and Normalized Mutual Information (NMI). The ensemble model consistently outperforms individual clustering methods, achieving an OA of 99%, ARI of 96.70%, and NMI of 92.20%. These results demonstrate the effectiveness of the proposed ensemble-based, label-free methodology for scalable and accurate land cover mapping using multisensor Earth observation data.
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 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| 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".