Seasonal precipitation forecasting with large scale climate predictors: a hybrid ensemble empirical mode decomposition-NARX scheme
Bibliographic record
Abstract
Abstract. Much of northern Tunisia regularly experiences extremes of drought and flooding, with high rainfall variability. The development of reliable and accurate seasonal rainfall forecasts can provide valuable information to help mitigate some of the outcome of floods and enhance water management and monitoring, particularly for agriculture. Whether climate indices oscillations contain some information to be useful for hydrological forecasting is worth investigating. Ensemble monthly rainfall forecasts are carried out using a hybrid neural network model. The hybrid model called EEMD-NARX based on a non-linear autoregressive network with exogenous inputs (NARX) coupled to Ensemble Empirical Mode Decomposition (EEMD) method is developed in this work. First, the EEMD is performed to extract significant information from modes of variability (IMF) associated to climate indices and precipitation. Each IMF of selected indices as well as precipitation IMFs are then used as inputs to the NARX forecasting model to forecast each IMF of precipitation. To make forecasts operational, we reconstruct precipitation by summing of all forecasted IMFs to make comparison with observed precipitation in the Medjerda river basin located in north Tunisia. Results show that IMFs of MEI and SOI indices can be distinguished from a white noise at the 95 % level. It is also found that an oscillatory forcing coming from the Atlantic influences the precipitation in the Mediterranean basin. The results indicate that exogenous inputs like climatic indices improve the accuracy of forecasts in some in some precipitation stations. The correlation coefficient between observed and forecasted monthly precipitation is ranging from 0.7 to 0.8. EEMD allows extracting significant components from exogenous inputs like climate indices that help reducing predictive uncertainty as well as improving forecasts of a NARX model at longer lead-times.
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 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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| 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 teacher head, 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".