Land use change in an agriculturally impaired sub-watershed of the Chesapeake Bay
Bibliographic record
Abstract
The Chesapeake Bay watershed spans several states, supports diverse ecosystems, and is economically crucial to local communities. However, the land use throughout this region often has detrimental impacts on stream health. In particular, agricultural land use negatively affects water quality through nutrient and pesticide input, cattle trampling of streams, and increased sedimentation. In the Shenandoah Valley region of northwestern Virginia, part of the Chesapeake Bay watershed, agriculture is the primary land use. This has led to the designation of the Smith Creek watershed, located in the Shenandoah Valley, as a United States Department of Agriculture showcase watershed in 2010. Widespread restoration efforts have been conducted throughout the watershed over the past decade, such as improving in-stream habitat, establishing riparian buffers, and excluding cattle from streams. Linking stream health to land use, however, requires high resolution, up-to-date land cover classifications. The most recent such product for the study area was generated using 2013 imagery, which does not capture the restoration progress that has occurred in the Smith Creek watershed since 2010. The goals of this project are two-fold. First, this project aims to produce a high-resolution land cover classification using 2020 and 2021 imagery. Second, using the new land cover classification, the study will analyze land cover change in the Smith Creek watershed over the past decade. The project represents a collaboration between a Biology Department Master’s student and undergraduate students in the Geography Department at James Madison University. Ten meter (m) resolution imagery with four bands (red, green, blue, and red-edge) collected by the Sentinel 2 satellite in April 2020, September 2020, and January 2021 on days with no cloud cover obscuring the study region was obtained from the United States Geological Survey’s Earth Explorer database. Images were clipped to the Smith Creek watershed boundary using ArcPro v 2.7 (Esri, Redlands, CA) then merged together in PCI Geomatica 2018 (PCI Geomatics, Markham, Canada) to produce one 12-band image. A principal components analysis was conducted to identify the image bands that best differentiated pixels from one another, and the image was narrowed down to the five best bands. The image was then segmented and an object-based classification was conducted to classify land cover following the same categories as previous classifications in the study area. Once manual corrections and ground-truthing have been completed, a land cover change analysis will be conducted by comparing land use classification rasters from 2013 and potentially previous years as well.
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 | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 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".