Coastal Zone Mapping of the Great Lakes: A Machine Learning Approach
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Coastal systems on the Laurentian Great Lakes are affected by meter scale water level fluctuations that can occur over hourly to decadal time scales which can cause erosion and damage to infrastructure. Changes in water levels, ice coverage, and storm activity have been projected under various climate change scenarios and will likely alter historic coastal processes across the region. Monitoring changes in the descriptive morphometrics of coastal systems, such as coastal bluffs and shorelines, over time can offer insight into how these systems might respond to projected climate scenarios. With increasing access to geospatial data through open- source aerial and satellite imagery, an improved observational record will enhance our understanding of the spatiotemporal scales and environmental and anthropogenic controls on coastal dynamics of the Great Lakes. To take full advantage of these large data sets, this study utilizes a machine learning (ML) approach to automate the identification of coastal features, such as the shoreline indicated by the wet/dry boundary, vegetation, and coastal bluffs. Random Trees (RT) classifier models were trained using manual classifications of satellite imagery of the northwestern shore of Lake Erie. Results demonstrate that coastal features can be sufficiently identified using independent ML models, indicating the potential for an effective tool to map coastlines across large spatial scales. Over time, a similar methodology can be used to monitor coastal system dynamics to inform coastal managers and policy makers on the response of the Great Lakes coastal systems to climate change.
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.
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 it