Comparing Pixel- and Object-Based Classification Methods for Determining Land-Cover in the Gee Creek Watershed, Washington
Bibliographic record
Abstract
This study analyzes land-cover types in the Gee Creek Watershed of southern Washington using the pixel-based and object-based image analysis approaches. Landsat imagery has traditionally been used for pixel-based classification and change detection in land-cover studies. In recent years, the availability of high-resolution satellite and aerial imagery have enabled for land-cover classification to occur at scales not possible using traditional Landsat imagery. High-resolution aerial imagery of 1 meter or greater has become readily available for free. Yet, commonly found black and white (or panchromatic) aerial imagery is without the multiple spectrum bands found in Landsat imagery, thereby limiting the accuracy of traditional pixel-based multispectral classification approaches. Instead, object-based image classification can be used as an alternative analysis approach for determining land-cover types on high-resolution imageries. This paper examines and compares two traditional Landsat pixel-based techniques with the high-resolution object-based approach. Both approaches are used to conduct land-cover classification within the highly variable landscape of the Gee Creek Watershed. The high variability found within the Watershed is the result of recent years of development that have changed the landscape from predominantly forest and agriculture to one of the fastest growing suburbia's outside the Portland-Vancouver metropolitan area. Two pixel-based classification analyses are conducted using Landsat imagery; supervised classification of multispectral bands and unsupervised classification of transformed Tasseled Cap bands. These traditional approaches are then compared to object-based classification using 1 meter resolution natural color aerial imagery obtained from the United States Department of Agriculture. The result of this analysis suggests that Landsat pixel-based approaches are only suitable for determining general land-cover types, whereas the use of object-based classification on high-resolution imagery resulted in increased accuracy and ultimately led to a higher number of land-cover classes being distinguished.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".