Shuvo et al. (2026) Rainfall Forecasting: A Review of Current Practice

Identification

• Journal: Lecture notes in civil engineering
• Year: 2026
• Date: 2026-01-01
• Authors: Shafiq Shuvo, Nilufa Afrin, Xiao Pan, Gokhan Yildirim, Ataur Rahman
• DOI: 10.1007/978-3-032-18708-6_22

Research Groups

• School of Engineering, Design and Built Environment, Western Sydney University, Sydney, New South Wales, Australia
• Department of Environmental Engineering, Faculty of Engineering, Aksaray University, Aksaray, Turkey

Short Summary

This paper reviews the evolution of daily rainfall forecasting methodologies, highlighting recent advancements, particularly with artificial intelligence and deep learning techniques. It outlines key challenges and future research directions in the context of climate change, data limitations, and the demand for hyperlocal predictions.

Objective

• To review the development of daily rainfall forecasting methodologies, identify recent advancements, and outline key challenges and future research directions considering climate change, data limitations, and the growing demand for hyperlocal predictions.

Study Configuration

• Spatial Scale: Variable, ranging from hyperlocal predictions to large-scale meteorological datasets, covering global to regional applications depending on the reviewed method.
• Temporal Scale: Daily rainfall forecasting, with the review spanning developments over the past few decades and projecting future directions.

Methodology and Data

• Models used: Empirical and basic statistical approaches (e.g., autoregressive models, Markov chains), Numerical Weather Prediction (NWP) models, Machine Learning (ML) and Deep Learning (DL) techniques (e.g., Artificial Neural Networks (ANNs), Long Short-Term Memory (LSTM) networks, hybrid ensemble models), and other Artificial Intelligence (AI)-based approaches.
• Data sources: Large-scale meteorological datasets, satellite data, reanalysis products, and high-resolution climate models.

Main Results

• Rainfall forecasting has evolved from early empirical and statistical methods to advanced Numerical Weather Prediction (NWP) models.
• The integration of Machine Learning (ML) and Deep Learning (DL) techniques, including ANNs, LSTMs, and hybrid ensemble models, has significantly improved forecasting accuracy by capturing complex, nonlinear patterns.
• The use of satellite data, reanalysis products, and high-resolution climate models has enhanced forecasting reliability.
• Future rainfall forecasting is anticipated to rely on adaptive, data-driven systems, integration with climate change projections, and the application of interpretable AI methodologies.

Contributions

• Provides a comprehensive review of the historical development, current state-of-the-art, and future trends in daily rainfall forecasting.
• Emphasizes the transformative impact of AI/ML/DL techniques on prediction accuracy and the role of diverse data sources.
• Identifies critical challenges and outlines future research directions, particularly in the context of climate change and the demand for hyperlocal predictions.

Funding

• Not specified in the provided text.

Citation

@article{Shuvo2026Rainfall,
  author = {Shuvo, Shafiq and Afrin, Nilufa and Pan, Xiao and Yildirim, Gokhan and Rahman, Ataur},
  title = {Rainfall Forecasting: A Review of Current Practice},
  journal = {Lecture notes in civil engineering},
  year = {2026},
  doi = {10.1007/978-3-032-18708-6_22},
  url = {https://doi.org/10.1007/978-3-032-18708-6_22}
}