Forecasting Impacts of Air Pollution and Hydro-Meteorological Extremes: Models, Methods, and Applications

Dear Colleagues,

The frequency and intensity of air pollution and hydro-meteorological extremes—including heatwaves, floods, droughts, coastal storms, and compound hazards—are increasing as climate variability and long-term warming accelerate. These events affect critical infrastructure, water and food security, human health, and social–ecological systems. As such, accurate and actionable forecasting at multiple lead times has become a central scientific and societal priority. Nonetheless, traditional physical models, statistical approaches, and standalone machine-learning systems all face limitations in handling nonlinearity, nonstationarity, data sparsity, extremes and multi-scale dynamics.

This Special Issue focuses on next-generation forecasting methods for air pollution and hydro-meteorological extremes, with emphasis on state-of-the-art ML/AI tools, physics-informed AI, hybrid dynamical–machine-learning frameworks, and post-processing of numerical weather prediction (NWP) and climate models. We particularly welcome studies that push measurements and methodological boundaries—such as generative AI for stochastic forecasting, neural operators, multi-lead-time architectures, attention-based sequence models, downscaling approaches, explainable AI (XAI), and models designed to forecast specific components of time-series systems (e.g., persistence, transitions, and extreme-tail behaviour).

The goal of this Special Issue is to collect papers (original research articles and review papers) that advance forecasting theory, algorithms, uncertainty quantification, and operational applications. Both methodological innovations and applied studies with real-world relevance are encouraged.

This Special Issue will welcome manuscripts that link the following themes:

• ML/AI forecasting systems for extremes (e.g., LSTMs, Transformers, Graph Neural Networks, Neural Operators);
• Physics-informed neural networks (PINNs) and hybrid dynamical–ML modeling;
• Post-processing and bias correction of NWP/climate models using AI;
• Extreme-value forecasting, tail modeling, and rare-event prediction;
• Generative AI, diffusion models, and ensemble surrogates for multi-lead-time forecasting;
• Uncertainty quantification, explainability, and model diagnostics;
• Spatio-temporal forecasting from Earth observation & remote sensing;
• Applications to air pollution, floods, droughts, heatwaves, tropical cyclones, air-quality extremes, etc.

We look forward to receiving your original research articles and reviews.

Dr. Chibuike Chiedozie Ibebuchi
Dr. Richard Damoah
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Forecasting is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.