AI for Inland Water, Atmospheric Environments, and Ocean Modelling
(AIWAVOM)

Riga, Latvia, 23-26 August, 2026

AI for Inland Water, Atmospheric Environments, and Ocean Modelling (AIWAVOM) brings together researchers applying intelligent systems to understand and predict the full water–atmosphere continuum. The session spans rivers, lakes, wetlands, the atmosphere, coastal zones, and the open ocean, recognizing that extreme events often emerge from interactions across these domains. We welcome contributions that turn data (in situ observations, remote sensing, reanalyses, and high-resolution simulations) into insight for weather prediction, climate assessment, and environmental forecasting: from extreme waves, storm tides, and compound flooding to atmospheric rivers, hydro-climatic extremes, and air–sea exchange processes.

We are particularly interested in hybrid and knowledge-guided approaches: physics-aware learning, neural operators for geophysical fields, AI-based downscaling, probabilistic and uncertainty-aware forecasts, and symbolic or neural-symbolic methods for process discovery. Case studies linking inland hydrology, meteorology, and oceanography, as well as applications relevant to ports, renewable energy, civil protection, and water-resource management, are especially encouraged. The goal is to foster a practical, cross-disciplinary conversation about what AI can contribute to environmental prediction today, and where it can take us next.

Topics

Topics:

Data-driven prediction and forecasting

Machine-learning models for weather, hydrological, and ocean forecasts
AI methods for extreme events: storm tides, extreme waves, heavy precipitation, and atmospheric rivers
Hybrid physical–statistical forecasting of water levels, river discharge, and coastal flooding
AI-based nowcasting using radar, satellite, buoy, or station data

Environmental modelling and downscaling

AI downscaling of winds, waves, currents, and hydroclimatic variables
Data-driven emulators for numerical weather prediction and ocean circulation models
Neural operators and surrogate models for geophysical fields
Spatio-temporal learning for inland-water, atmospheric, and ocean dynamics

Environmental monitoring and data integration

Machine learning for remote-sensing retrievals (ocean colour, turbidity, chlorophyll, soil moisture, cloud properties)
Fusion of observations from in-situ sensors, satellites, reanalyses, and model outputs
Anomaly detection and quality-control methods for environmental datasets

Hydrology, inland water systems, and air–sea interaction

AI for river flow, lake levels, sediment transport, and water-quality indicators
Data-driven modelling of evaporation, fluxes, turbulence, and boundary-layer processes
AI approaches to compound events linking atmosphere, rivers, coasts, and the open ocean

Climate and long-term environmental applications

Machine learning for climate variability and long-term changes in coastal and ocean conditions
Statistical and ML methods for climate projections and scenario assessment
Detection and attribution of environmental trends using AI techniques

Methodological advances and cross-cutting tools

Physics-informed learning, constraint-aware models, and hybrid AI–numerical approaches
Neural operators and differentiable surrogates for geophysical processes
Neural-symbolic AI, symbolic regression, and XAI approaches for interpretable environmental modelling
Probabilistic forecasting, uncertainty quantification, and ensemble learning
Spatio-temporal architectures for environmental data (CNN–LSTM, transformers, graph networks)
Reproducible workflows, benchmark datasets, and open-source tools

Applications with societal relevance

AI for renewable energy (wind, wave, and hydropower)
Environmental risk assessment and early-warning systems
Port operations, shipping safety, and coastal management
Water-resource decision support under climate change

Topical Area Curators

Farina, Leandro, Federal University of Rio Grande do Sul, Brazil
Korotov, Sergey, Mälardalen University, Sweden
Bethers Uldis, University of Latvia, Latvia

Contact: aiwavom@fedcsis.org

Submission rules

Authors should submit their papers as Postscript, PDF or MSWord files.
The total length of a paper should not exceed 12 pages IEEE style (including tables, figures and references). More pages can be added, for an additional fee. IEEE style templates are available here.
Papers will be refereed and accepted on the basis of their scientific merit and relevance to the Topical Area.
Preprints containing accepted papers will be published online.
Only papers presented at the conference will be published in Conference Proceedings and submitted for inclusion in the IEEE Xplore® database.
Conference proceedings will be published in a volume with ISBN, ISSN and DOI numbers and posted at the conference WWW site.
Conference proceedings will be submitted for indexation according to information here.
Organizers reserve right to move accepted papers between FedCSIS Sessions.