Harmful Algal Blooms Prediction Model: Dealing With Limited Datasets
Bibliographic record
Abstract
HABs pose serious threats to natural aquatic systems, such as mass mortality of aquatic organisms, degradation of water quality, and human poisoning from consuming aquatic organisms exposed to HABs. Monitoring water quality and weather data through buoy data loggers is very useful nowadays. Through these buoys, environmental data can be accessed in real time. Various technical constraints on these buoys will directly and indirectly result in missing values (limited data sets). It often happens that one has a good idea of a learning model, but due to its complexity and smaller number of data sets, the model performs far below expectations. Transfer learning approaches and data synthesis with the CT GAN algorithm have been applied to deal with modelling on limited datasets. The transfer learning model gives better results. It can be seen from the value of model evaluation parameters (AUC and MSE) that the transfer learning model provides better results than other models (model-based CTGAN and deep learning model without transfer learning). The process of adapting (fine-tuning) knowledge is an important process in improving the performance of the model in the transfer learning procedure.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".