Improvement of the Low Resolution of the Dataset and Prediction of the Water Quality Using the SWAT-LSTM Hybrid Model
Bibliographic record
Abstract
The river environment where people, animals, and plants exist together is a significant place to continue their own lives. Especially, since the river water quality directly impacts the survival of living things, it is crucial to effectively manage the quality of river water. To manage the river water quality effectively, it is important to make appropriate water quality management plans by accurately predicting the river water quality. Many researchers have utilized various tools for modelling the water quality of the river environment. Until now, river water quality has been modelled using the watershed model such as Soil and Water Assessment Tool (SWAT) [1], Hydrological Simulation Program-Fortran (HSPF) [2], and QUAL2E [3]. However, those models are developed in the US government (United States Department of Agriculture and United States Environmental Protection Agency), so it is challenging work to adapt those models to Korean watershed direct. And nowadays, the application of Artificial Intelligence (AI) is gradually increasing, because of its high prediction accuracy, adaptability for non-linearity, and high speed rather than other methodologies Despite the increasing use of AI in river water quality modelling, a challenge is that AI requires high-resolution dataset for effective modelling. However, in Korea, the resolution of the dataset for water quality of river environment is low because of lack of the number of conducted water quality monitoring stations.
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 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".