Advances in AI-based rainfall forecasting: a comprehensive review of past, present, and future directions with intelligent data fusion and climate change models
Farhan Amir Fardush Sham, Ahmed El‐Shafie, Wan Zurina Wan Jaafar, S. Adarsh, Mohsen Sherif, Ali Najah Ahmed
Abstract
Accurate rainfall forecasting is crucial for managing water resources, supporting agriculture, and preparing for natural disasters, especially as climate variability becomes more pronounced. Traditional methods often struggle with the complexity and unpredictability of rainfall patterns across different climates, driving interest in advanced modelling approaches capable of capturing such nonlinear dynamics. Artificial Intelligent (AI) model are well-suited for detecting complex temporal pattern in rainfall data, enabling improved short-, medium- and long-term performance. A key feature of the purposed framework is the integration of AI models with climate change simulation output through a fusion process that combines historical climate projections and rainfall data using a hybrid input strategy. This fusion enables the AI models to learn not only from observed rainfall sequences but also from anticipated climate-driven variations, thus improving the model’s adaptability and robustness under changing environmental conditions. These findings highlight the potential of more reliable and resilient forecasting systems that support informed decision-making in agriculture, urban planning, and disaster preparedness, reinforcing the promise of AI in climate-aware rainfall prediction.