GIS, Remote Sensing and Machine Learning: Data Integration to Support the Management of Coastal Island Ecosystems
Bibliographic record
Abstract
Islands are important components of many coastal areas around the world; however, by virtue of their geographical isolation, the state of these ecosystems is often poorly known. To address the knowledge gap for the province of Nova Scotia, Canada, geographic information systems (GIS), remote sensing (RS), and machine learning (ML) were used to examine the status of nearly 4000 islands. We classified islands topographically and determined, based on 1 m resolution LiDAR, that approximately 70% are <2 m average elevation and highly vulnerable to partial or complete flooding under near-term regimes of sea level rise and storm surge potential. Vegetation cover was strongly related to topographic class, with higher, more steeply-sided islands having more tree cover and less sand, rock, and wetland. Climatic changes were most pronounced in the form of sea surface temperature (SST) warming, with August changes (+0.063 °C yr −1 ) being 6.3× higher than the global mean background rate, particularly affecting the Gulf of St. Lawrence subregion. Human activity, in the form of marine traffic, is a pervasive stress. To integrate all these factors, a random forest ML model was trained using tree mortality from forest inventory records as the environmental response, and the predictions were used to define a region-wide Ecosystem Stress Index (ESI). These findings demonstrate the kinds of insights geospatial data and ML can provide, and offer tools for improving our understanding of coastal island vulnerability.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".