Using Machine Learning to Predict Phytoplankton Blooms in the Salish Sea
Bibliographic record
Abstract
Abstract Strong phytoplankton blooms occur every spring in the Salish Sea, but vary significantly, spatially and temporally. Natural variability and climate change make the prediction of the bloom challenging, as they affect both atmospheric drivers and nutrient interactions that contribute to the growth of phytoplankton. Understanding these drivers is essential for a successful bloom prediction. Here, we used a 25‐year data set (18 training, 4 evaluation, and 1 independent year), consisting of 7 atmospheric drivers and 4 phytoplankton variables for the Salish Sea, to build Machine Learning (ML) models that are able to emulate phytoplankton blooms. For phytoplankton productivity, we employed histogram gradient boosting models, whereas for the biomass of phytoplankton, we employed functional regression models, to capture its dynamic nature and dependence on the atmospheric drivers. Feature selection was implemented to identify the optimal set of input features for each model. By using only meteorological drivers (and in some cases spatiotemporal variables) as inputs, the proposed ML models are able to efficiently capture spatial and temporal patterns of phytoplankton blooms over the Salish Sea. Different phytoplankton variables (e.g., biomass, production rates) and different regions require different input features (e.g., precipitation), with shortwave solar radiation being the most frequently used atmospheric driver.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".