An artificial neural network model reveals water level changes alter bioavailable PCB concentrations in the Detroit River
Bibliographic record
Abstract
Temporal trends of bioavailable PCB water concentrations from a long running mussel biomonitoring program (1998–2023) in the Detroit River, Ontario, Canada. Bioavailable sum PCB10 concentrations exhibited long term declines at two biomonitoring locations but such declines were influenced by changes in water levels and showed different responses among individual congeners. Temporal declines in PCBs were highest rising water levels, PCBs reverted to an increasing trend for all congeners at the upstream biomonitoring location. At the midstream location, only PCBs 28 + 31 and 52 changed their temporal trajectories, while other PCBs slowed their decline relative to the constant water level regime. A deep neural network (DNN) model was trained to the data. The parsimony optimized model identified sediment PCB concentrations, chemical KOW, mean annual water level and year as the most important predictors of PCB water concentrations and explained more than double the variation compared to a multiple regression model. Overall, both empirical and modeled results show that hydrological fluctuations significantly affected bioavailable PCB concentrations and their temporal trends in this system. As water levels continue to decline in the Detroit River, PCBs are expected to resume their previous decreasing trend in the coming years. • DNN modeled 1996–2023 trends in bioavailable PCB water levels. • Inputs: sediment PCBs, log Kow, mean water level, year; R 2 = 0.38–0.61. • Most congeners declined 9.2–94 %; PCB 28/31 rose 35 % at one site. • Higher 2014–2020 water levels raised PCBs; effects vary by site/congener. • Falling water levels suggest PCB declines will accelerate again soon.
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 | 0.000 | 0.001 |
| 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 | 0.001 | 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".