Extending the forecasting horizon of daily new COVID-19 cases using non-pharmaceutical measures and the effective reproduction number (Rt): A deep learning-based framework
Bibliographic record
Abstract
Amid the ongoing pandemic, such as the Covid-19 outbreak, there exists a critical need to comprehend and forecast the dynamic trends of daily confirmed cases to effectively prevent and mitigate the impact of its consequences. This study aims to investigate the essential factors acting as predictors for forecasting daily new confirmed cases specifically within the Indonesian setting. Utilizing advanced Deep Learning (DL) methodologies, including Deep Feedforward Neural Networks (DFNN), Long Short-Term Memory (LSTM), one-dimensional convolutional neural networks (CONV1D), and Gated Recurrent Units (GRU), this research endeavors to predict daily confirmed Covid-19 cases in Indonesia. To achieve this, a comprehensive set of 80 variables (predictors), encompassing the effective reproduction number (Rt), was utilized as input parameters. Before model construction, rigorous variable selection procedures and statistical analyses were conducted to enhance data understanding. The effectiveness of the predictive model was assessed using various metrics, such as Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Scaled Error (MASE), which evaluates MAE relative to a baseline model. Results indicate that DL models incorporating two key predictors—daily confirmed case count and Rt—exhibited superior predictive performance, capable of forecasting daily confirmed cases up to 13 days in advance. The inclusion of additional variables was found to diminish the predictive accuracy of DL algorithms.
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 | 0.001 |
| 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 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".