Chlorophyll-a Prediction Based on Machine Learning and Satellite Data in the South Sea of Korea
Bibliographic record
Abstract
Chlorophyll-a (Chl-a) is a critical indicator of phytoplankton biomass, offering key insights into changes in marine ecosystems, including algal blooms and nutrient cycling. However, predicting Chl-a concentrations using numerical models remains challenging due to the intricate interplay of climatic and geographical factors. Moreover, conventional studies relying heavily on localized marine measurement instruments face limitations in both scope and generalizability. To address these challenges, this study integrates high-resolution satellite imagery with advanced machine learning (ML) techniques to develop a robust and scalable model for predicting Chl-a concentrations in the South Sea of Korea. Multiple linear regression, random forest, and extreme gradient boosting models were evaluated, along with an averaging ensemble that combines their predictions. A feature ablation study was also conducted to assess the contribution of individual input variables. The results showed that the Ensemble model achieved the highest performance, withR2values of 0.821 for 1-day predictions, 0.750 for 2-day predictions, and 0.713 for 3-day predictions. These findings demonstrate the potential of integrating high-resolution (250 m) satellite data with ML to achieve accurate and wide-scale predictions of Chl-a concentrations. These advancements are expected to provide foundational data for applications in marine environmental monitoring, sustainable aquaculture management, and harmful algal bloom prediction.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".