Delineating Grassland in British Columbia using Object-Based Image Analysis (GEOBIA) through Google Earth Engine
Bibliographic record
Abstract
Grasslands in British Columbia (BC) play a pivotal role in biodiversity, supporting over 30% of the region's endangered species. However, rapid urbanization and forest encroachment threaten these habitats. This study addresses the urgent need for an accurate, automated method for delineating and monitoring BC's grasslands by employing Object-Based Image Analysis (GEOBIA) within the Google Earth Engine platform, utilizing high-resolution Sentinel-2 satellite imagery. The approach innovates by integrating Superpixel Segmentation Based on Simple Non-Iterative Clustering (SNIC) with Random Forest classification, aimed at overcoming the mixed pixel effect prevalent in pixel-based methods. The methodology demonstrates a significant improvement in the accuracy of grassland delineation, achieving an overall classification accuracy of 96%. Specifically, the accuracy for grassland identification increased by 26.6% compared to the previous study, underscoring the effectiveness of GEOBIA for environmental monitoring. This advancement offers a promising tool for the conservation and management of grassland ecosystems in BC, suggesting a scalable model for similar ecological studies worldwide. The findings advocate for the adoption of GEOBIA in remote sensing practices, potentially transforming how grasslands are monitored and conserved, thereby contributing to the preservation of biodiversity.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.004 |
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".