Mapping coastal Great Lakes wetlands and adjacent land use through hybrid optical-infrared and radar image classification techniques
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
In the U.S., the National Wetland Inventory (NWI) is the most contiguous and current wetland map available, yet it lacks information on lands adjacent to wetlands and the distribution of invasive plants. Existing Canadian maps are comprised of a mosaic of mapping techniques, sources, and resolutions. A consistent baseline map is needed to monitor change in coastal ecosystems. Short falls in long-term monitoring is in part caused by reliance on dated, static, and inconsistent maps. Use of SOLEC or GLEI indicators is impeded by limitations of current maps, impacting the ability to monitor and detect effects from significant wetlands stressors; urban development and invasive plant species. Current work is underway to produce an international and contemporary baseline map for the Great Lakes Basin. Due to the complexity of wetland ecosystems, detection of species and extent as well as adjacent land use can be accomplished using sensor fusion approach. Synthetic Aperture Radar (SAR) is sensitive to flood condition as well as structure and biomass. Optical sensors, such as Landsat TM, are complementary in the classification and monitoring of wetland ecosystems. Previous research demonstrated the capability of ALOS PALSAR L-band data for detecting and mapping invasive Phragmites australis. The international wetlands map is being produced from a fusion of PALSAR and Landsat data and aims at detection of large stands of problematic plant species such Phragmites australis and Typha spp. A Random Forests classifier is used to create a land cover map through the integration of field and air photo interpreted data with underling sensor fusion data. The Lake Michigan map is complete and is being evaluated for accuracy through randomly selected field and air photo interpreted validation data. The basin wide maps will provide the first ever international Great Lakes coastal land cover map suitable for coastal wetland assessment and management.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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