EOLakeWatch; delivering a comprehensive suite of remote sensing algal bloom indices for enhanced monitoring of Canadian eutrophic lakes
Bibliographic record
Abstract
Early detection and comprehensive monitoring of inland water algal blooms is fundamental to their effective management and mitigation of potential ecosystem and public health impacts. With the spatial and temporal limitations of in situ sampling, algal bloom monitoring capabilities have been enhanced greatly by advancements in satellite Earth Observation (EO). Three turbid, eutrophic Canadian lakes (Lake Winnipeg (LW); Lake Erie (LE); Lake of the Woods (LoW)) have been the focus of Environment and Climate Change Canada (ECCC) research and monitoring initiatives due to concerns over persistent degraded water quality from recurring algal blooms. ECCC’s EOLakeWatch was developed to deliver a suite of useful, easily interpretable, and accessible EO-derived products to support algal bloom monitoring on these three lakes. Algal bloom indices, describing bloom spatial extent, intensity, duration, and severity were derived using the European Space Agency’s OLCI (Ocean and Land Colour Instrument) sensor for observations from 2016 to present and its predecessor MERIS (Medium Resolution Imaging Spectrometer) for 2002 to 2011. Results document widespread blooms on each lake, with maximum spatial extent of 21,641 km2 (representing 88.1% of the lake area) on LW, 3070 km2 (79.5%) on LoW and 5257 km2 (19.7%) on LE. Bloom intensity showed seasonal and inter-annual variability on all three lakes, with a suggestion that LoW may be responding to reduced nutrient loads with a recent decrease in bloom intensity. Annual bloom duration on LW and LoW was on average 44 and 47 days respectively, while on LE blooms were significantly shorter in duration at an average of 24 days. Variance among the derived bloom indices was shown to be significant (i.e. the most extensive bloom was not necessarily the longest or most intensive), demonstrating the need for the indices to be used collectively, or for any single comprehensive bloom indicator to capture the variability of all individual metrics. Bloom indices are processed in a fully automated operational capacity, distributed in near-real-time through a web portal and collated into end-user-friendly annual algal bloom reports for each lake. These products go a long way to address existing monitoring gaps, delivering prompt, consistent measures of lake-wide algal bloom conditions required to provide stakeholders with early warning of bloom risks, identify areas of potential concern, quantify spatio-temporal trends, further understand bloom dynamics and drivers, as well as guide and determine the effectiveness of implemented management actions.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.001 | 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) | 0.004 | 0.001 |
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".