Enhancing long-term water quality forecasting with a hybrid deep-learning approach integrating MODWT, CNN, and GRU
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Effective water quality forecasting is crucial for managing pollution and mitigating its environmental impacts. Machine learning (ML) and deep learning (DL) models often fail in long-term WQ forecasting accuracy due to complex data patterns and inadequate feature extraction. Although several data-driven forecasting approaches have been employed in the literature for WQ forecasting, to our knowledge, the literature lacks a comprehensive comparison of singular and hybrid data-driven algorithms considering various time steps. Thus, the current investigation introduces a new approach of integrating DL models, MODWT-CNN-GRU, which integrates maximal overlap discrete wavelet transform (MODWT), Convolutional Neural Networks (CNNs), and Gated Recurrent Units (GRUs) to handle dynamic temporal patterns. Comparative analysis indicated that the MODWT-CNN-GRU model outperformed singular Support Vector Regression (SVR), CNN, GRU and hybrid CNN-GRU models. It showed particularly strong performance in weekly forecasting, achieving a 31% improvement over SVR, 28% over CNN, 27% over GRU, and 16% over CNN-GRU.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 it