A robust artificial intelligence informed over complete rational dilation wavelet transform technique coupled with deep learning for long-term rainfall prediction
Article
| Article Title | A robust artificial intelligence informed over complete rational dilation wavelet transform technique coupled with deep learning for long-term rainfall prediction |
|---|---|
| ERA Journal ID | 32032 |
| Article Category | Article |
| Authors | Diykh, Mohammed Mohammed, Ali, Mumtaz, Farooque, Aitazaz Ahsan, Aldhafeeri, Anwar Ali, Jamei, Mehdi Mehdi Mehdi and Labban, Abdulhaleem |
| Journal Title | Engineering Applications of Artificial Intelligence |
| Journal Citation | 165 (Part B) |
| Article Number | 113426 |
| Number of Pages | 20 |
| Year | 2026 |
| Publisher | Elsevier |
| Place of Publication | United Kingdom |
| ISSN | 0952-1976 |
| 1873-6769 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1016/j.engappai.2025.113426 |
| Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S0952197625034578 |
| 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. |
| Keywords | Artificial intelligence; Overcomplete rational dilation discrete wavelet transform; Rainfall; Prediction; Drought; Climate warming |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 461103. Deep learning |
| Byline Affiliations | UniSQ College |
| University of Prince Edward Island, Canada | |
| Al-Ayen University, Iraq | |
| King Faisal University, Saudi Arabia | |
| King Abdulaziz University, Saudi Arabia |
https://research.usq.edu.au/item/100wy2/a-robust-artificial-intelligence-informed-over-complete-rational-dilation-wavelet-transform-technique-coupled-with-deep-learning-for-long-term-rainfall-prediction
Download files
Published Version
| A robust artificial intelligence informed over complete rational dilation.pdf | ||
| License: CC BY 4.0 | ||
| File access level: Anyone | ||
29
total views5
total downloads1
views this month0
downloads this month