Isolating Anthropogenic Wetland Loss by Concurrently Tracking Inundation and Land Cover Disturbance across the Mid-Atlantic Region, U.S.
Bibliographic record
Abstract
Global trends in wetland degradation and loss have created an urgency to monitor wetland extent, as well as track the distribution and causes of wetland loss. Satellite imagery can be used to monitor wetlands over time, but few efforts have attempted to distinguish anthropogenic wetland loss from climate-driven variability in wetland extent. We present an approach to concurrently track land cover disturbance and inundation extent across the Mid-Atlantic region, United States, using the Landsat archive in Google Earth Engine. Disturbance was identified as a change in greenness, using a harmonic linear regression approach, or as a change in growing season brightness. Inundation extent was mapped using a modified version of the U.S. Geological Survey’s Dynamic Surface Water Extent (DSWE) algorithm. Annual (2015–2018) disturbance averaged 0.32% (1095 km2 year-1) of the study area per year and was most common in forested areas. While inundation extent showed substantial interannual variability, the co-occurrence of disturbance and declines in inundation extent represented a minority of both change types, totaling 109 km2 over the four-year period, and 186 km2, using the National Wetland Inventory dataset in place of the Landsat-derived inundation extent. When the annual products were evaluated with permitted wetland and stream fill points, 95% of the fill points were detected, with most found by the disturbance product (89%) and fewer found by the inundation decline product (25%). The results suggest that mapping inundation alone is unlikely to be adequate to find and track anthropogenic wetland loss. Alternatively, remotely tracking both disturbance and inundation can potentially focus efforts to protect, manage, and restore wetlands.
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 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".