Accurate monthly forecasting of Rainfall pattern in Atlantic climates: an Empirical Fourier Decomposition-based Deep ensemble learning paradigm
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
The rainfall pattern plays a vital role in agriculture and overall climate resilience in the Atlantic provinces of Canada. Prince Edward Island and New Brunswick, two Atlantic provinces, have great potential to grow potatoes, grains, and blueberries. Thus, accurate forecasting of the rainfall pattern helps farmers determine the optimal time for planting, irrigation, fertilisation, and harvesting based on predicted rainfall patterns. Here, a new complementary multi-level intelligent framework comprised of the recursive feature elimination (RFE), Empirical Fourier Decomposition (EFD), and deep ensemble random vector functional link (Deep RVFL) has been developed to forecast the monthly (one month ahead) rainfall pattern in Charlottetown and Fredericton stations. Aiming for this, first, the significant antecedent information (lag sequences) was indicated using the RFE scheme. Then, all the optimal lags were decomposed using the EDF scheme to deduce the complexities of rainfall sub-component signals before feeding the Deep RVFL algorithm. Two comparative deep learning models, namely, RVFL and CNN-LSTM, were incorporated with the implemented multi-level pre-processing scheme in hybrid and standalone forms. In order to validate the models, several statistical indices, such as correlation coefficient (R), root mean square error (RMSE), and Kling-Gupta efficiency (KGE), scatter plots, signal trend analysis, and diagnostic assessment, were utilized. The outcomes of the results ascertained that the RFE-EDF-Deep RVFL framework, owing to superior forecasting performance, outperformed the RFE-EDF-Deep CNN-LSTM, RFE-EDF-RVFL and all the standalone counterpart models.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| 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