Work

Can Integrated Machine Learning Models Improve Rainfall Forecasting? A Case Study from the Australian Tropics

Year: 2026

Type: article

Abstract: This study investigates the integration of wavelet preprocessing with machine learning models to enhance wet-period rainfall prediction in the Northern Territory of Australia. Lagged large-scale climate indices, including the El Niño Southern Oscillation (ENSO), Dipole Mode Index (DMI), Madden-Julian Oscillation (MJO), and Interdecadal Pacific Oscillation (IPO), were employed as predictors for Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) models, both with and without wavelet transformation. Results indicate that hybrid models consistently outperformed their standalone counterparts, with the Wavelet-LSTM (W-LSTM) using Daubechies (db) wavelet emerging as the most effective configuration. Across three stations (Warruwi, Waterloo, and Avon Downs), the W-LSTM (db) achieved high correlations with observed rainfall (0.86–0.95) and substantially reduced RMSE, by up to 89.6% at Warruwi. It also demonstrated a strong ability to capture rainfall peaks and troughs, with correlations ranging from 0.76 to 0.91. Performance metrics further confirmed its superiority, with R² values of 0.80–0.89 and NSE values of 0.78–0.87, compared to the relatively lower performance of individual models (R² ranges 0.74–0.81). Although some challenges remain in accurately predicting extreme rainfall events, the overall findings present the advantages of combining wavelet preprocessing with machine learning. The W-LSTM (db) model provides a more robust and reliable approach to rainfall forecasting by improving the representation of variability and extremes. These results indicate the potential of hybrid wavelet-machine learning frameworks for enhancing predictive capability in regions influenced by high climate variability, with broader applicability to other tropical and monsoonal environments. This study presents an approach to predicting wet-season rainfall in Australia’s Northern Territory by combining wavelet transformation with advanced machine learning models. The process starts with using major climate signals, such as ENSO, DMI, MJO, and IPO, that strongly influence rainfall patterns in the region. These signals were used in both raw and transformed forms to train two models: Support Vector Machine (SVM) and Long Short-Term Memory (LSTM). Wavelet transformation, especially with Daubechies wavelets, helps break down the complex climate data into simpler components, making it easier for the models to detect important patterns. When this wavelet preprocessing was added, the performance of both models improved noticeably, especially the W-LSTM model. It predicted rainfall more accurately, captured the timing of rainfall peaks and lows better, and reduced prediction errors by up to 89.6% at some stations like Warruwi. The graphical summary highlights key results, including higher correlation with actual rainfall (up to 0.95), improved R² (up to 0.89), and lower RMSE values (as low as 0.15). This clearly shows that combining wavelets with machine learning gives more reliable and accurate rainfall forecasts. This method can help with better water planning and disaster preparation in climate-sensitive regions.

Source: Earth Systems and Environment

DOI: 10.1007/s41748-025-01020-3

Authors: Rashid Farooq, Monzur Alam Imteaz, Muhammad Atiq Ur Rehman Tariq, Kamila Hlavčová, Muhammad Waseem

Institutions: International Islamic University, Islamabad, Swinburne University of Technology, Slovak University of Technology in Bratislava, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology

Language: English

Topic: Hydrological Forecasting Using AI

Subfield: Environmental Engineering

Field: Environmental Science

Domain: Physical Sciences

SDGs: Climate action, Industry, innovation and infrastructure

Open Access status: hybrid

Estimated APC paid: $4,090