Expert-assisted statistical learning techniques for assessing wetland conditions in urban landscapes
Bibliographic record
Abstract
Wetlands are essential components within the socio-ecological framework of urban areas, providing a wide range of ecosystem services. However, increasing natural and anthropogenic stressors place significant pressure on these wetlands, threatening their ability to sustain these vital services. To effectively assess wetland condition and develop appropriate management strategies, robust monitoring tools are needed. Statistical learning techniques, such as machine learning, have been proposed as a promising approach to enhance the development of these wetland monitoring tools. In this study, we evaluated the performance of the pre-existing wetland assessment tool used in the City of Calgary—the Aquatic Condition Index (ACI). We compared ACI performance using three different approaches for selecting indicators: machine-only selection, expert-only selection, and a hybrid approach where humans selected the indicators, but the machine determined the relationships between the indicators and wetland conditions. Our results showed that hybrid approaches, combining human expertise with statistical learning, outperformed both machine-only and expert-only methods. We then examined whether the ACI could be transitioned from field- and computer-based indicators to fully computer-based indicators using the hybrid method of selecting indicators. Our findings revealed comparable results between the two methods, suggesting that a computer-based monitoring system could help overcome the time and budgetary constraints associated with field-based monitoring while also enabling the examination of larger geographical areas. This study underscores the importance of human expertise in guiding the statistical learning process, particularly in the selection of indicators that accurately represent wetland processes.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".