Predicting the presence of hypoxic hypolimnia in lakes at large spatial scales
Bibliographic record
Abstract
Abstract Lakes and reservoirs provide multiple essential ecosystem services to humans, and several of these require the presence of a cool, oxygen‐rich hypolimnion. These ecosystem services include supporting habitat for recreational fish species and the maintenance of a non‐eutrophic state by limiting internal nutrient loading. However, changes in land use and global warming are modifying the thermal structure of lakes worldwide, creating episodic or prolonged periods of hypoxia, changing a lakes ability to deliver certain ecosystem services. Here, we used National Lake Assessment data and machine learning approaches to identify which lake or watershed features determined the presence of a hypolimnion and which contributed to the development of hypoxia. A random forest of 1000 trees predicted the presence of a hypolimnion with 85% accuracy using commonly measured morphometric and physicochemical variables as well as land use. Mean and maximum depths had a disproportionate influence, entirely obscuring the influence of variables commonly associated with lake mixing, such as light penetration and fetch. In contrast, depth had a more restrained role to predict the presence of hypoxia; the latter was predicted with an overall accuracy of 85%, from epilimnetic nitrogen and carbon concentrations. Although the nutrient‐color groups had a minor influence in the random forests, there was a clear trend of increased hypoxia with higher turbidity. Our approach allows for the broad‐scale assessment of lakes with hypolimnia and suggests that increasing eutrophication and browning will promote profundal hypoxia, altering the delivery of certain ecosystems services.
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 | 0.001 | 0.001 |
| 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 | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| 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".