A robust artificial intelligence informed over complete rational dilation wavelet transform technique coupled with deep learning for long-term rainfall prediction
Bibliographic record
Abstract
The intensity of heavy rainfall, driven by climate change, has significant effects worldwide, including flash flood, droughts, water degradation, landslides and crop damages. To ameliorate these impacts, accurate forecasting is crucial to address the dynamic nature of rainfall for sustainable utilization. But the non-linearity inherited within the rainfall significantly influence the model precision. Artificial Intelligence (AI) models have shown promising results in detecting complex rainfall patterns. This paper proposed a hybrid model using overcomplete rational dilation discrete wavelet transform (ORDWT) integrated with autoregressive integrated moving average (ARIMA) and long-short-term memory (LSTM), constructing ORDWT-ARIMA-LSTM to forecast one-month ahead rainfall. The ORDWT provides multi-scale decomposition and better shift-invariance, while ARIMA with LSTM captures complementary dynamics across ORDWT coefficients, lowering errors. Aiming to extract more representative features, the ORDWT coefficients are investigated, and then sent to the ARIMA-LSTM for prediction. The ORDWT–ARIMA–LSTM achieved highest performance for Melbourne Airport: Root Mean Square Error (RMSE) = 2.9, Mean Absolute Error (MAE) = 1.93, RSE = 0.215, Willmott's Index (WI) = 0.990, Nash–Sutcliffe Index (ENI) = 0.970; Melbourne Botanical Gardens: RMSE = 3.84 MAE = 2.65, RSE = 0.287, WI = 0.710, ENI = 0.962; and Preston Reservoir: RMSE = 3.94 MAE = 2.87 RSE = 0.310, WI = 0.973, ENI = 0.971. The ORDWT–ARIMA–LSTM reduced RMSE by 4.5 % and MAE by 5.3 % on average across stations against comparing models. Results confirmed the efficiency of ORDWT–ARIMA–LSTM in rainfall forecasts, providing valuable support in weather, water management, droughts and floods.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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".