Advancing Machine Learning for Climate and Water Resilience: Techniques for Precipitation Forecasting

Accurate climate prediction, particularly precipitation forecasting, remains a cornerstone for agriculture, water resource management, and disaster preparedness. With increasing climate variability due to global change, the demand for precise, reliable, and adaptable forecasting methods is more critical than ever.

The rise of machine learning (ML) offers new tools to enhance the prediction of precipitation and climate variability. This Research Topic will explore integrating ML techniques in hydrological and climate sciences to improve forecasting accuracy and optimize water resource management. Topics of interest include, but are not limited to, multi-view learning approaches, model stacking, recurrent neural networks, convolutional architectures, spatiotemporal attention models, physics-informed ML, time-series predictions, and the integration of lagged meteorological or oceanic variables to enhance model accuracy. These approaches, when combined with data from remote sensing, atmospheric models, and in-situ measurements, can significantly strengthen climate resilience strategies and support data-informed decisions for policymakers and practitioners.

Precipitation is one of the most complex variables to predict due to its nonlinear and chaotic nature. Traditional statistical models, while useful, often struggle to capture extreme weather events and long-term variability. Recent advancements in deep learning, ensemble learning, and hybrid modeling techniques have shown promising results in climate science. The ability of ML to analyze large-scale climate datasets, recognize patterns, and improve forecasting accuracy makes it a powerful tool for hydrological applications. However, challenges such as data quality, model interpretability, and transferability to different climatic regions remain open research questions.

The primary goal of this Research Topic is to present cutting-edge ML applications for precipitation forecasting and climate variability analysis, in response to climate change and water resource challenges. The collection aims to:
• Highlight innovative ML techniques that address nonlinearity and temporal dynamics in climate data.
• Explore ensemble methods such as multi-view stacking learning to enhance forecasting reliability.
• Provide region-specific case studies demonstrating the practical applications of ML-based climate forecasting and their policy implications.
• Assess AI-driven decision support systems for climate adaptation and disaster risk mitigation.
• Address challenges related to integrating heterogeneous climate data sources, improving model interpretability, and generalizing ML models across regions.

These advancements aim to enhance early warning systems, optimize resource planning, and mitigate climate-induced risks in vulnerable regions, contributing to sustainable climate resilience strategies.
We invite contributions exploring ML applications in climate science, focusing on precipitation forecasting and water management. Key themes include:

• Machine Learning for Precipitation Prediction: Deep learning, ensemble methods, probabilistic models, hybrid approaches, and transfer learning for climate forecasting
• Extreme Weather and Climate Variability: AI-driven early warning systems and risk assessments for droughts, floods, tropical cyclones, heatwaves, and atmospheric rivers
• Data Fusion and Remote Sensing: Integrating satellite imagery, radar observations, reanalysis products, digital elevation models, and in-situ climate and hydrological data to enhance model performance
• Decision Support Systems for Water Management: AI-driven tools for sustainable water allocation, flood control, irrigation management, reservoir operations, and hydropower optimization
• Model Evaluation and Benchmarking: Developing robust evaluation metrics, explainability tools, uncertainty quantification methods, and reproducibility practices for ML-based climate models
• Scalability and Transferability: Adapting models to data-scarce regions, downscaling approaches, and domain adaptation for cross-regional application

Submissions may include Original Research Articles, Review Papers, Methodological Advances, Case Studies, and Policy and Practice Reviews. This Research Topic fosters interdisciplinary collaboration to advance ML-driven climate forecasting and water sustainability solutions.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Community Case Study
• Conceptual Analysis
• Data Report
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• General Commentary
• Hypothesis and Theory
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Community Case Study
• Conceptual Analysis
• Data Report
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Policy and Practice Reviews
• Policy Brief
• Review
• Systematic Review
• Technology and Code

Keywords: Machine Learning, Deep Learning, Climate Prediction, Precipitation, Multi-View Learning, Time Series Analysis, Ensemble Models, Climate Change, Hydrology, AI in Water Management, Climate Resilience, Remote Sensing, Extreme Weather Prediction

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.