Design and Implementation of a Deep Learning Model and Stochastic Model for the Forecasting of the Monthly Lake Water Level
Bibliographic record
Abstract
Freshwater is becoming increasingly vulnerable to pollution due to both climate change and an escalation in water consumption. The management of water resource systems relies heavily on accurately predicting fluctuations in lake water levels. In this study, an artificial neural network (ANN), a deep learning (DL) neural network model, and an autoregressive integrated moving average (ARIMA) model were employed for the water level forecasting of the St. Clair and Ontario Lakes from 1981 to 2021. To develop the models, we utilized the average mutual information and incorporated lag periods of up to 6 months to identify the optimal inputs for the water level assessment in the lakes. The results were compared in terms of the root mean square error (RMSE), coefficient of correlation (r), and mean absolute percentage error (MAPE) and graphical criteria. Upon evaluating the results, it was observed that the error values for the deep learning models were insignificant at the designated stations: Lake St. Clair—0.16606 m < RMSE < 1.0467 m and Lake Ontario—0.0211 m < RMSE < 0.7436 m. The developed deep learning model increased the accuracy of the models by 5% and 3.5% for Lake St. Clair and Lake Ontario, respectively. Moreover, the violin plot of the deep learning model for each lake was most similar to the violin plot of the observed data. Hence, the deep learning model outperformed the ANN and ARIMA model in each lake.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".